Company Report
Last edited 5 years ago
PerformanceCommunity EngagementCommunity Endorsement
Performance
n/a
Followed by
0
Straws
Sort by:
Recent
Content is delayed by one month. Upgrade your membership to unlock all content. Click for membership options.
#ASX Announcements
Added 2 months ago

Bombshell from $APX this morning. Full text of the release is below.

This kind of announcement has been foreshadowed by many here, so it will not really be a surprise to them. However, the market has taken a sharp intake of breath with SP down almost 40%. This says that some holders remain in denial that this business model has had its day.

I first took a position in $APX in December 2016 as part of the MF PRO recommendations, like many here. And over the next year built a sizeable position premised on the growth of demand for data to train AI models. I'll admit to being initially skeptical when some started saying the model would be short-lived, but as the chorus of respected voices grew, I progressively exited (missing the peak on the way down) and pocketing between $12.90 and $39,00 over the period Feb-2020 to July-2021. How long ago that now seems.

Today's announceent is surely a very important milestone. Full text follows.

As a personal observation, I teach business operations as one of my occupations. A current student of mine last week showed how he coached ChatGPT 4.0 to solve a rather complex analytical problem I set for the class. The level of coaching was non-trivial, but the progress LLM's have made in one year is remarkable.


ASX Announcement

----------------------------

Appen Limited (Appen) (ASX: APX) received notification on Saturday, 20 January 2024 AEDT from a material customer, Google LLC, that as part of a strategic review processit will be terminating its global inbound services contract with Appen, resulting in the cessation of all projects with Appen by 19 March 2024. Appen had no prior knowledge of Google’s decision to terminate the contract.

In FY23, Appen’s revenue from Google was $82.8m1 at a gross margin2 of 26%.

The news is unexpected and disappointing, particularly considering the progress made against Appen’s transformation and performance in November and December 2023. Appen saw Q4 on Q3 growth in both Global Services and New Markets (including China). On a YoY basis, Global Services Q4 2023 revenue was down while New Markets (including China) was up. Within the New Markets division, China achieved a quarterly revenue record in Q4 2023 of $11.1m. At a group level, based on unaudited management accounts, Appen recorded revenue of $24.1m and $25.9m in November and December 2023 respectively, along with execution of cost management initiatives, which enabled achievement of cash EBITDA breakeven objectives.

Based on the unaudited management accounts, Appen also recorded:

• Underlying EBITDA3 (excluding FX) of $3.2m and Underlying cash EBITDA (excluding FX)4 of $2.3m in December 2023;

• Revenue of $273.0m and an Underlying EBITDA (excluding FX) loss of $20.4m for the full year; and

• $32.1m cash on hand at 31 December 2023.

These results are preliminary and subject to change as the audit process is finalised. Appen’s full year FY23 results remain unaudited and are subject to Board review and approval as well as completion of the external audit.

Appen continues to focus on cost management, business turnaround and delivery of high-quality AI data for its customers. Appen will immediately adjust its strategic priorities following the notification of the Google contract termination and provide further details in its FY23 full year results on 27 February 2024.

Authorised for release by the Board of Appen Limited.

#Business Model/Strategy
Added 2 months ago

Its a bit of a long read but for those of you willing to spend the time on a deep dive into the Aspen business b=model going forward, is worth the effort.

The bottom line is there is probably a viable business in there, it just hasn't got much cash to make it come to fruition:

Source: Scott Middleton


Appen: the $309m fall in AI revenue

How segmenting between AI Builders and AI Adopters might help it return to growth

SCOTT MIDDLETON

FEB 1

 READ IN APP 

Being at the forefront of AI isn’t a straightforward ticket to rocket-ship growth. Appen, an AI data annotation company listed on the ASX, is going through some severe performance issues. 

Appen has gone from profitable with growing revenue to declining revenue and losses. To add salt to the wound, Google recently ended an $82m contract.

But, through analysing Appen and the forces at play in AI, it looks like there might be a segment of the business that has a high gross margin, probably growing and supported by strong tailwinds. 

This hidden segment, data annotation for the AI Adopters, is obscured by the significant revenues Appen gets from massive technology companies like Amazon, Facebook and Google. 

The AI Adopters segment is only 29% of total revenue, but its gross margin is 38% of the overall margin. 

Appen needs to navigate servicing large contracts with the world’s biggest technology companies while quickly growing into the market for companies adopting AI. They’ve just raised ~$30m in working capital to help them start to figure this out. 

If they can’t figure it out then they’ll need to either take drastic action or sell the company to someone that can take on the turnaround. 

It’s an intriguing situation. Let’s take a closer look at Appen.

Each week we dive deep into listed tech companies to get insights on managing and investing better

Subscribed

About Appen

Linguist Dr Julie Vonwiller founded Appen in 1996 with her engineer husband, Chirs Vonwiller.

In 2009, Anacacia Capital acquired a 51% share of Appen as the Vonwillers looked to transition out and retire. Over the next 18 months, Appen increased its holding to 70% for a total investment of $5.5m. 

Appen was then merged with the Butler Hill Group, a US-based firm with a similar offering to Appen. The Butler Hill Group was founded in 1993 by ex-IBM Watson researcher Lisa Braden-Harder.

The merged group was IPO’d in 2015, led by Braden-Harder.

Appen went on to make a handful of acquisitions: Wikman Remer, Mendip Media Group, Leapforce for $80m USDFigure Eight for $300m USD and Quadrant for $45m.

Appen’s stock price surged but has fallen in line with falling revenues and losses. Appen recently raised a $30m round to help fund working capital to ensure the business survives.

Product (or Solution): A workforce for tagging AI, supported by specialised data and software

Appen’s solution is about tagging and reviewing data used in AI and Machine Learning. 

It’s primarily a large army of people working away to tag, review, edit, and markup data to feed into algorithms or that has come out of algorithms. These people are made more efficient and effective by Appen’s technology and prebuilt data sets.

Source: FY21 Annual Report

The key features of Appen’s solution are:

  1. Ready to go data sets to help train, tune or validate AI. Like data sets for domains like health care, finance and vehicles.
  2. The Crowd (the people) to build data, prepare data and evaluate results. These can be relatively unskilled or trained copywriters/linguists.
  3. Software to make data preparation, sourcing and evaluation better. Including algorithms to automatically fix data, make tagging easier and prefill.
  4. Management of the people, software and data to make this efficient and effective. Including hiring the people, determining pay, scheduling them and training them.

Subscribed

Business Model: 

Appen’s business model boils down to:

  1. A Salesperson sells a project for an average size of $120,000 (as per annual report)
  2. The Crowd works it (i.e. tags, labels, evaluates), Appen’s technology helps the client and the crowd.
  3. Appen makes a Gross Margin of ~38% (as per annual report)
  4. Client (might) do repeat projects, especially with some Account Management. This could expand to millions in revenue. 
  5. Reinvest the margin in better ways to help build, prepare and evaluate AI data.

Appen has had some substantial customers (Facebook, Google, Microsoft) who have been in the repeat projects loop with substantially larger-than-average projects. For example, Google did $82.8 million with Appen in FY2023. But these massive customers are falling away. 

Market: the challenge and opportunity of being on the edge of AI

The market for Appen is interesting in how rapidly it is evolving and how turbulent markets at the forefront of technology can be.

Appen is primarily in the now fairly competitive ‘data annotation market’ and, to some extent, the crowd-sourcing market with a specialism in AI. Both markets are estimated to each be $4-$5 billion markets that are growing.

Companies in annotation, like Snorkel AI, reported a five times increase in enquiries in late November 2023.

What’s happening in AI?

Everything AI-related is undergoing a significant shift due to recent innovation. 

The most well-known is the explosion of large language models like OpenAI’s ChatGPT. 

However, behind the scenes, progress has been made by cloud vendors and data platform providers. They are looking to commoditise and give greater access to the tooling and infrastructure required to configure and run artificial intelligence and machine learning.

In some cases, especially in the larger or more AI-focused tech companies, algorithms have been built to help annotate and label faster.

Algorithms need data, and lots of it, to be developed. Then, once developed, they need to be tuned from time to time with more data. 

We do have large, open annotated data sets for images (e.g. ImageNet), speech (e.g. the 10 data sets on Stanford’s website), and language. There is also a much larger trove of data within Amazon, Google, Microsoft, OpenAI and others (including Appen). Amazon, for example, has hours of recordings from people talking to Alexa.

But, we haven’t yet built “The Final Algorithm”. So, this process of annotating large data sets, training AI on it, and then tuning it is likely to continue for some time. 

The building of new algorithms, generally, requires volumes of new data that is annotated and output that is evaluated. This needs large data sets to be labelled that haven’t been labelled or annotated before in the way you need.

Adapting these algorithms, which is what most organisations applying AI are doing, is where you tune or customise algorithms to your specific requirements.

Appen’s Market Segments: Adopters,Builders, and Users

This broadly means the market for Appen breaks into these segments:

  • AI Builders: the companies building new algorithms such as Google, OpenAI and Microsoft, as well as more specialised technology companies.
  • AI Adopters: companies looking to customise what the AI Builders have created for their own uses. 
  • AI Users: companies that will use the AI and algorithms others create without any modification.

The AI Builders will continue to need to build algorithms. So they will continue to need labelled data, and they will continue to need to evaluate their algorithms’ output.

The key questions for this segment are:

  1. Have the major data sets been mostly annotated (for now)? The AI Builders have possibly performed the bulk of annotation for datasets around image, language, and speech. If so, it’s into tuning mode (less need for annotation).
  2. Is there another major data set or algorithm on the horizon? If so, what element of human intelligence would it be? If there is, then there will be another massive need for annotation and data preparation.
  3. Do the algorithms they’ve developed now allow their AI to annotate and evaluate itself? If this is even partly correct, then the need for humans in the loop has decreased (Appen’s loss of Google might be a sign of this). 

The AI Adopters are currently working to apply the recent advances made by the AI Builders. This requires data, data annotation and labelling but not at the same scale as building AI models. 

The AI Users don’t require any data annotation services. Most small to medium businesses will be AI users. Larger businesses may be AI Adopters in one department (where it gives a competitive advantage) and AI Users in another where it provides no real advantage (i.e. payroll for most).

The number of AI Adopters is large; almost every meaningfully sized company on the planet is arguably in this market. While the number of AI Builders is small: in the tens, maybe hundreds. 

Customer Value Proposition

The Customer Value Proposition (or CVP) differs for the AI Builders and AI Adopters. We won’t cover AI Users because they don’t have a need for annotation.

AI Builders

AI Adopters

Competition: Pressure from big customers and marketing machines

Appen’s competition comes from other Data Annotation SolutionsCrowdsourcing more broadly, and the AI Builders themselves creating better Annotation AI.

Companies providing Data Annotation Solutions provide a fairly similar offering to Appen. They help prepare data and evaluate algorithm output with teams of people and software to help manage this workflow. Some provide ‘value adds’ like off-the-shelf data sets, advisory, and algorithms to help others just provide the people capacity. 

Customers needing to get data annotated can also do it themselves within their company or crowd-source themselves. There are a variety of Crowdsourcing options available. Customers going down this path just need to manage the process themselves.

Given the amount of processing the AI Builders have to do, they have a need to make this faster and more efficient (let’s call it Annotation AI). They’re constantly looking to apply the AI they’ve built or build new AI to help with annotation. You can, for example, use a large language model to quite accurately classify documents now. Previously, this needed a person. Similarly, image recognition advances mean AI can annotate images to help train another AI without needing a human. 

Appen, and data annotation providers, face pressure from multiple directions. 

  1. The general Crowdsourcing companies are powerful machines when it comes to winning new customers and growing revenue, particularly in the broad market Appen now finds itself in.  
  2. Appen’s original customers, the AI Builders, are heavily incentivised to automate this away (speed to market and cost to a lesser extent) and are continually improving their ability to do so.

But they also have the tailwind of the broad AI Adopter market segment in which all businesses are looking to increase their AI projects.

Go-to-market: Sales Teams and Account Management

Appen uses a sales-led approach to winning business from new customers and account management to expand their existing relationships. 

Appen has sales representatives in each of the regions they want to win business, including Australia, the United States, China, Japan and Korea.

They don’t use a self-service sign-up. You have to request a call and quote from a salesperson.

The go-to-market will likely go through a shift as well. The type of account management team you need to manage an $82 million relationship with Google is different to the type of salesperson you need to win $120,000 projects from enterprises.

To get a feel for their go-to-market motion, I applied for a demo with a legitimate use case and haven’t received any contact. In contrast, for another analysis I did, I received a phone call within an hour after submitting a request for a demo form. For a company desperate to grow revenue, it was a little surprising not to hear back quickly.

There is little information about Appen’s go-to-market in publicly published investor information, so I’ve had to infer what is happening from their website, reports, and other sources.

Finances

Appen was a profitable growth machine as recently as 2021. Yet, as the AI Builders have decreased their workloads, Appen’s financial results have turned into a serious problem. As revenues fell, Appen didn’t adjust its expense base, posting a $34m operating loss in 2022.

The Gross Margin held, though. Crowd costs adjusted down with the decrease in revenue. This is promising because it gives a 39-40% gross margin to work with that can scale relatively well with revenue up or down. This margin shows the business has (or can have) underlying resilience.

So what needs to happen with expenses? How can we get profitability and growth happening again? 

Splitting the business

Splitting the business might work as a solution going forward. Let’s split the two tracks: the declining business of servicing the AI Builders, and a business for servicing AI Adopters that has signs of market growth.

AI Builders

This business is about servicing the AI Builders, which is primarily about account management and, it seems, some improvements around efficiency. 

From the disclosure on the Google contract, we can also see that Google’s contract had only a 26% gross margin. So we can infer that contracts with Meta and any other large remaining AI Builders probably have a lower margin as well.

If we assume that Google, Meta, and Amazon made up 80% of revenue prior to Google ending the contract, then Appen’s AI Builders Business would have $218m in 2023 and something like $191m in 2024.

The probability of further revenue or margin decline in this segment is likely, such as losing another big account or being squeezed on cost respectively. So, the stance here would need to be one of cash flow and profitability through the lowest possible expense base to continue to service the revenue (i.e. no new major product development and no ‘new account’ teams - just focus on what’s in front of you). 

AI Adopters

The AI Adopters business is made up of hundreds of customers doing, it seems, smaller projects at higher margins. This business is adding new accounts.

The expense base here likely has a slightly different stance of a mixture of profitability and investment in growth. That investment in growth could be marketing and sales. Given recent performance, this can’t be an overinvestment, though, until the business unit proves itself.

Runway

At the ~$30m loss rate of 2022, Appen’s recent capital raise gives it 12 months of losses of a similar magnitude. Appen says it has cut costs substantially but was still incurring losses as of the last update and may still need to adjust further based on the loss of Google. 

Runway is a real concern.


Disc: not held

#Capital Raise
Last edited 4 months ago

Barely 6 months after raising at more than 3x the current CR price, the company is out again with its hat (or begging bowl) extended eagerly to the market.

It's $30m now, but still highly dilutionary given the steep discount to the current market price (~35%). The reason for the raise is just as bad - to fund working capital needs.

And oh, the CTO has moved on barely after few months into his job.

Why would any market participant bother to participate is beyond me. This company just knows how to light shareholder wealth on fire.

Summary of the announcement -

 Appen provides FY23 trading update as at 31 October 2023

• Appen remains committed to return to profitability with additional $14

million of cost reduction, bringing total run-rate cost reduction initiatives

that have been or will be implemented over 2023 to $60 million

• Equity Raising is comprised of a ~A$23.6 million 1 for 3.65 pro rata

accelerated non-renounceable entitlement offer and a ~A$6.4 million

institutional placement

• Proceeds will be used to provide balance sheet flexibility and general

working capital to support Appen’s return to profitability, and transaction

costs

#CEO
Added 2 months ago

A new CEO has been announced today. Their announcement included the following for the outgoing CEO.

Mr Freudenstein acknowledged Mr Ahmad’s tenure at Appen:

“Armughanhas been CEO during a period of great change at Appen. Having overseen a new strategic direction and re-sizing of the business, Armughan has decided to pursue new challenges. We wish him well for the future.”

I like the marketing spin. "re-sizing" in reality meant complete destruction of shareholder value .


#ASX Announcements
Added 2 weeks ago

A pause in trading after a 30% ride in the first half of the session.

Not a leaky ship at all. Hope they announce that big telco contract they were touting/expecting.

#ASX Announcements
Added 2 weeks ago

News SummaryDJ Appen Suitor Withdraws $101M Proposal on Confidentiality BreachAPX$0.965$0.00 (0.0%)$1.00$0.95

14 Mar 2024 09:00:011 ViewBy Stuart Condie

SYDNEY--Appen said that Innodata withdrew its $101 million takeover proposal after the Australian data-annotation provider was forced by the local stock exchange to announce its existence.

"Innodata informed Appen that it was withdrawing the Indicative Proposal on the basis that it was intended to remain confidential," Appen said Thursday.

Trade in Appen shares was halted on Tuesday so that the Australian Securities Exchange could ask the company if it could explain a 30% jump in its share price. In response, Appen said that it had received an indicative, non-binding takeover proposal from Nasdaq-listed Innodata.

Write to Stuart Condie at stuart.condie@wsj.com

(END) Dow Jones Newswires

#Business Model/Strategy
Added a month ago

Just purely out of curiosity and for beer money, I signed up to be an Appen contractor ie be part of their 'Crowd'. Process was super easy - punch in your details and sign up to their Contractor payments platform and you're pretty much good to go and 'apply' to be part of a project, took less than 24 hrs. Appen has a reputation for being "legit" according to users of Reddit ( /r/beermoney ).

Appen Crowd jobs are split into 3 main categories

  • Surveys
  • Micro Tasks
  • Projects


Some examples of jobs available to the Crowd:

https://jobs.lever.co/appen

  • Survey: eg answer a questionnaire survey, get $0.01
  • Project: Be an online mystery shopper, get $8 to buy an item worth up to $500 (fully refunded by Appen)
  • Project: Drive around in an Appen car for 60mins while they record your facial expressions. $80 for session.
  • Project: Drive around in an Appen car, and record eye movements. $120 for session


Is Appen truly dead? Sure, they did lose a major Google contract. However this experience has shown me that Appen is much more than the Google contract. That being said, it's not stock I personally want to buy in - there are better opportunities elsewhere.

#Merger Proposal
Last edited 2 weeks ago

APX has responded to the ASX aware query, revealing that it "recently" received a highly indicative merger proposal from US-listed Innodata, in a stock for stock deal that was at a 100% premium to the prevailing share price.

Hopefully that is very recent, and not from the 52w lows. That may determine whether the next move is up or down when it comes out of the halt.

https://hotcopper.com.au/documentembed?id=uOMxKKzFkiWRTLKhOROKAxjvSDYL5g%2B9yhjzv%2FZp57FiGug%3D

#half-year ended 30 June 2023
stale
Added 7 months ago

Underlying EBITDA (before impact of FX) was ($15.7) million, compared to $9.6 million in 1H FY22. This is due to reduced revenue and gross margin, and a proportionally higher cost base coming out of FY22. 

APX well it's not a investment grade stock. Lets have look.

APPEN LIMITED (ASX:APX) - Ann: 2023 Half-Year Results and 2023 Outlook, page-1 - HotCopper | ASX Share Prices, Stock Market & Share Trading Forum

3ae73918fb2a358818a44a04d7ea7509d5799c.png

da9b3bbc979e7617fa60da251c470f49dc44b1.png

b05aaef728cde626c91cfc6e802d061976e0b6.png

b84ba9b0b6b6dce4251e2f124231a205f82cae.pngc650dd89bf3a2b4b5ee727d6ea904e20f69130.png1fa2b7f129b6535747ec343b11f87ceac2fbfd.pngc9b44813d3f4874236f1b356ef9a2e42816e06.png



5b0306687e57c1ea912701ff334a8a2606d2fc.png

#Change down subs holding
stale
Added 7 months ago

Previous: 12,070,052 7.62% / Present 10,188,473 6.45%

From 604: State street.

2332a2eb6ddc9fbbc8ef73df0de07a49c63112.png


How deep the price go? . Deeper than coal mine..lol

"Deeper than the deepest ocean ..wider than the sky" ...you know the song!!!


f903807173580a83a1c3d0e32fc92e3cfd2c3b.png




#Broker/Analyst Views
stale
Last edited 9 months ago

14-July-2023: Just revisiting this old straw from just over two years ago (May 2021). It's interesting to see how wrong those brokers were back then!


09-May-2021:  I do not hold Appen (APX) shares, as I believe their business model is being undermined and they are becoming less and less relevant now.  I also think they are much less of a "tech" company than most people realise.  They rely on cheap labour to constantly provide a serious flow of data into their systems, which is not a very automated system at all.  Once the data is in they can do plenty of stuff with it, but the data entry itself is very labour-intensive, and they pay peanuts to those people who are doing it.  I don't claim to know the business very well, but I know enough to know that I'm not interested on doing further research on them, as they face more headwinds than tailwinds - in my opinion.

That said, to add to the conversation here, as Appen (APX) appears to be a very polarising and popular company to discuss here, I thought I'd include a snapshot of the latest broker views on Appen - see image below.  Remember that this is only part of the data available - on FNArena.com - and it could be worth considering a subscription to their service if you want to stay up-to-date with this stuff, or read Rudi's summaries of those brokers' reports and client notes.  As a subscriber, you can create a watchlist and every time there is any news or updates on any company on your watchlist, you'll receive an email about it - usually immediately - or at the very least on the same day.  

It pays to note however that FNArena only cover 7 brokers:  

  1. Citi
  2. Credit Suisse
  3. Macquarie
  4. Morgan Stanley
  5. Morgans
  6. Ord Minnett
  7. UBS

...so there are limitations there - you have to remember that the consensus views are only a consensus of those 7 brokers, and usually not all 7 of them will cover the company you are interested in, so it's usually a consensus of less than 7.  For instance, only 5 of those 7 currently cover Appen.  Anyhow, for what it's worth, here is a snapshot - as of today - Sunday 09-May-2021 - of what Macquarie, Citi, Ord Minnett, UBS and Credit Suisse currently think of Appen:

758042b9c3a06a5e3088dd7578ce62bc038d1f.png

If that is too small to read, click on it and it should get bigger.

04-July-2023: The lowest target price (TP) for Appen there was from Macquarie, who reckoned Appen were worth $16.00/share, and the highest was Citi who thought $30.90 was a fair price. Appen closed at $2.38 today, and they are still in a long-term downtrend that started back in August 2020 when they were just below $40/share.

Today they're around -94% off those highs, or are being valued by the market now as being worth around 6% of what they were selling for back then (in August 2020).

Brokers are often behind the curve, or behind the play and trying to catch up, and they are rarely right it seems.

Appen was trading at $22.23/share and all five major broking firms had either a "Neutral" or "Buy" call on APX at that point. Appen are down 89% from there, and here's what the brokers' views are today:

36064e097cfe118475224a9d2a9840967b53bf.png

I note that three of those five brokers from two years ago have ceased coverage of Appen (Ord Minnett, UBS and Credit Suisse), however Bell Potter and Morgan Stanley have joined Citi and Macquarie in covering Appen, and only Bell Potter is neutral (with a "Hold" call made back on May 18th). The other three are negative, with 1x "Sell", 1 x "Underperform", and one "Underweight". The four price targets range from $1.35/share up to $2.40/share. Still too high. They're going lower than that!

Additional: Looks like FNArena cover 8 broking firms now, being the seven I've listed above (with links), plus Bell Potter as well.

#Perspective
stale
Added 9 months ago

03-July-2023: Things can look different depending on your point of view. For instance, this looks sort-of bullish:

786ae260b66fac3aeac082cc059d44224d1c8f.png

And then Appen released this: 10-May-2023: Trading-update,-cost-reduction-program-and-strategy-refresh.PDF

Which confirmed they were running at a loss - i.e. no longer profitable, but they had a plan. A plan to return themselves to profitability. But it would cost money and take time.

So, on that day (10-May-2023), the APX share price (SP) drops -90c (-28.2%).

Then we get these announcements:

16-May-2023: Appen-announces-fully-underwritten-A$60m-equity-raising.PDF

26-May-2023: 2023-Annual-General-Meeting---Chair's-Address.PDF

From the 26th May to the 2nd June, the APX SP rose from $2.42/share to $3.76/share, a rise of +55.37% in one week, so now their chart looks like this:

0bc0e525cee44ebf2c3e190234c1c134d8f788.png

VERY bullish - who wouldn't jump on that ride? Well, anyone who had followed the company for a few years would probably be a bit wary, but for those trend-followers who don't care about fundamentals or management, it might well look enticing.

And then this happens:

09-June-2023: Completion-of-Retail-Entitlement-Offer.PDF

And the underwriters, who were left with 45% of the retail entitlement offer started selling, and the usual shorter suspects began to lodge "Substantial Holder" notices, and Appens' CFO, appointed on May 1st (see here: Helen-Johnson-appointed-Chief-Financial-Officer.PDF) announces she is quitting that role ("for personal reasons") on June 26th:

Departure-of-CFO-and-appointment-of-Deputy-CFO.PDF

So their latest CFO lasted just 8 weeks.

And the 6 month graph, up until today, looks like this:

42e1982698c00b86aa424369357f13a5f9cb94.png

That's the thing about Appen. Every rally is followed by a fall back down. Have a look at their 3 year chart:

f6913446d37f54fb988de4b258905941fecd3d.png

Not pretty. Sometimes you need to zoom out and look at the bigger picture. This is a business in serious decline. Apart from short term trading, which just might be profitable if you time it right, Appen is a company I would completely avoid, no matter what they announce.

Here is the 3 year chart of WiseTech (WTC):

17cbf5b2593542aa6193a2c96d81d5b6cc49da.png

Now that's the sort of company you want to be invested in. Like Appen, WiseTech also have a volatile share price. The WTC SP has plenty of drawdowns. But the overall trend is up. So far, WTC have weathered every storm, including a public attack by a US shorting firm, and they just keep heading north east at a decent clip, over time.

Appen, not so much.

What have Wisetech and Appen got in common? Well, remember WAAAX? It was our almost pitiful version of the US' FAANG stocks. FAANG is now MAMAA, which is an acronym for the top five tech stocks listed in the US. Together, they have a total market capitalisation of around US$10 Trillion (or they did in January 2022) and carry an approximate 21% weight in the S&P 500 index (again, that was in Jan, 2022). MAMAA are Meta Platforms (Meta, formerly Facebook), Alphabet (formerly Google), Microsoft, Amazon, and Apple. This acronym was coined as a replacement for FAANG after Facebook changed its name to Meta Platforms, and Google had become Alphabet, and Netflix was thought to be ex-growth after their share price fell by over 70% from around $690 in mid-November 2021 down to around $190/share in late June 2022. Unlike Appen, Netflix did bounce, and it doesn't seem like a dead cat bounce...

bde406d5ab809fddae9dcc4d6134ea2370f831.png

So WAAAX was once Wisetech, Appen, Altium, Afterpay and Xero. Then Afterpay got swallowed up by Square and Square became Block, and it isn't an Aussie company now. So, we have WAAX with two As instead of three As. But there's a bloody good argument that it should be just the one A, which would be Altium, because Appen isn't really even a tech stock, they are more of a labour hire company for data input (such as tagging images to assist machine learning), and they're definitely not a growth stock. Here's the past 3 years, with the share prices of Appen, Wisetech, Altium and Xero from the same common starting point.

9084117776ba814f0495de14b4c21b21f97877.png

Big difference between the best and worst there. Of course they don't compare to the FAANGs/MAMAAs of the USA, as they are HEAPS smaller, and together they represent a very small percentage of our All Ords Index (our equivalent to the S&P500 over in the US). The USA's Tech (or "IT" sector) is their largest sector, and it's one of our smallest. Our largest sectors are Materials (Miners) and Financials (Banks).

I maintain that Appen has no place as a WAAX company, or any place in the portfolio of any serious investor who is prepared to do even a small amount of research before buying shares. They are going lower, or they are going broke, probably both, in that order.

They often have a nice bounce (such as that +55% rise in one week recently, as explained above), but because they're coming off SUCH a LOW BASE now, these percentages are almost meaningless, as the 3 year graph clearly shows.

It's all about proper perspective.

Unless you're in them for a short-term trade (and history would suggest the shorter the better), there wouldn't be a barge pole long enough.

#Change in substantial holding
stale
Added 9 months ago

Form 604: basically J.P. MORGAN SECURITIES PLC

Nature of Changes: (some headings of note below)

1/ Purchase and sales of securities in its capacity as Principal/Proprietary,

2/ Holder of securities subject to an obligation to return under a securities lending agreement

3/ Purchase and sales of securities in its capacity as Principal/Proprietary

4/ Holder of securities subject to an obligation to return under a securities lending agreement


Previous notice 'Present Notice'

Person’s votes Voting power (5) Person’s votes Voting power

Ordinary 9,994,515 8.04% 9,504,804 6.07% 

APPEN LIMITED (ASX:APX) - Ann: Change in substantial holding, page-1 - HotCopper | ASX Share Prices, Stock Market & Share Trading Forum

ff94e8d8fb8e56cca7c5e4e4d45399376197d6.png

58a85fd2bc1a82ac69c07bde5839872a0748f3.png

#Directors purchasing
stale
Added 10 months ago

Five Directors 3Y - Stuart Davis, Vanessa Liu, Stewart Hasker, Robin Low, Robert Freudenstein.

3Y for Robert Davis below: Trading for Directors at $1.85 during their allowable trade.

APPEN LIMITED (ASX:APX) - Ann: Change of Director's Interest Notice - Ms Vanessa Liu, page-1 - HotCopper | ASX Share Prices, Stock Market & Share Trading Forum

da33ff497c2851ce48b7e101ce060aea10c9df.png

#Management
stale
Added 11 months ago

....ah, yes. Because that's what long-suffering shareholders were looking forward to - more dilution near multi-year lows!

It's early days to judge new management, but this and the "strategy refresh" have the distinct clutching-at-straws feel.

#underwritten A$60m equity rais
stale
Added 11 months ago

Entitlement Offer Record Date (7.00pm Sydney time) Thursday, 18 May 

8eaae05385dbc0e8113d9de1ba0277b928458f.png

The strategy refresh will address four key focus areas:

1. Customer diversification – generative AI expected to create material demand beyond large tech customers

2. Margin improvement – greater reliance on technology to improve gross margins

3. Revenue visibility – new products to have a greater proportion of recurring revenue

4. Strong ROI – generative AI investments will leverage existing technology investments Further detail on Appen’s strategy refresh will be provided at the Appen Investor Technology Day which will take place after the AGM on 26 May 2023. 

Equity Raising The Equity Raising will consist of an offer of fully paid ordinary shares (“New Shares”) through: • A 1 for 6 pro rata accelerated non-renounceable entitlement offer (“Entitlement Offer”) to existing eligible shareholders to raise ~A$38 million; and

An institutional placement (“Placement”) to raise ~A$21 million. The Equity Raising price of A$1.85 per share represents a: • 16.2% discount to the theoretical ex-rights price of A$2.21 (“TERP”)5

• 19.6% discount to Appen’s last closing price of A$2.30 on 15 May 2023. Approximately 32.2 million New Shares will be issued under the Equity Raising, representing ~26% of Appen’s existing shares on issue.

3ef5b8d4b31d5e70e1c0c6be50581993a542aa.png46590280e2fe3427d96448bbbb1fa060d3ecc9.png

#Trading Update
stale
Added 11 months ago

Things not getting better for poor old Appen. Trading conditions have simply not improved, with YTD revenue (first 1/3 of their financial year) down 21.4% on last year.

Here too the plan is to cut their way to greatness, They had already announced $10m in annual cost savings in Feb, and now they reckon they can cut a further $36m in costs. They expect to exit FY23 (dec 31) with an annualised run-rate of positive underlying EBITDA and operating cash.

There's also a strategy refresh, with the business planning to focus more on generative AI (like ChatGPT), which require large amounts of human feedback.

We'll see, but I doubt shares will return to their 2020 high of $40 anytime soon.. At present, if you pro-rata the first 4 months, shares are on a P/S of 1.4x

Way too hard for me to handicap the odds of a successful turnaround. I wish them well.

Announcement here

#What ChatGPT thinks...
stale
Added one year ago

Do new AI systems like chatgpt use human annotated data?

Yes, new AI systems like ChatGPT use human-annotated data to train and improve their performance. This data is used to "teach" the AI model how to understand and respond to different inputs, and to help it learn the nuances of human language. This process is called "supervised learning", and it is one of the most common ways to train AI models.


Is it likely to become less necessary over time to use this data from humans?

It is possible that the need for human-annotated data may decrease over time as AI systems continue to improve. With advancements in unsupervised learning and self-supervised learning techniques, AI models may be able to learn from large amounts of unannotated data, which could reduce the need for human annotation.

However, it's important to note that even with these advancements, human-annotated data will continue to play an important role in training AI systems, as it can be used to verify and validate the results of unsupervised learning methods. Additionally, training on human-annotated data can also help to reduce bias and ensure that the AI system is fair and ethical.

So, the need for human annotated data may decrease over time but it will still be an important part of the training process for AI systems.


Does this data need to be constantly refreshed or can the same datasets be reused?

The need to refresh the training data depends on the specific use case of the AI system and how frequently the real-world data changes. In some cases, the same dataset can be reused multiple times to train different AI models or to fine-tune existing models. However, in other cases, the data may need to be constantly refreshed to ensure that the AI system stays up to date with the latest information.

For example, in natural language processing (NLP) tasks, such as language translation or text generation, a dataset of text can be used to train multiple models over time. However, as new words, phrases, and idioms emerge, the dataset will need to be updated to ensure that the AI system can understand and respond to them.

In other applications, such as computer vision, the training data needs to be constantly updated as the real world changes, for example, to add new classes of objects or to reflect changes in the way objects look.

In summary, it depends on the specific use case and how dynamic the real-world data is. In some cases, the same dataset can be reused multiple times, while in other cases, the data needs to be constantly refreshed to ensure that the AI system stays up-to-date.


#Bear Case
stale
Last edited one year ago

ARK FYI podcast gives a good explanation of why Appen's TAM is reducing due to the maturing of AI models and the automation of labelling.

Held in SM and RL should have believed the opinions of others rather than the company announcements. Tried to catch the falling knife and got badly cut! Painful lesson.

Conversation with Manu Sharma, founder and CEO of Labelbox

Key Points From This Episode:

How Labelbox tries to improve mission-critical AI systems across industries by building software products.

Manu’s experience working in satellite imaging at Planet Labs before starting Labelbox.

What it was like to see AI applications powering real-world solutions for the first time.

Why the Manu believes the AI paradigm is really all about data.

How the need to create a product suite to orchestrate AI activities motivated Manu to create Labelbox.

The rapid AI driven transformations that enterprises using Labelbox experience today.

How enterprises navigated solutions for data engines before Labelbox.

How Tesla has built a data engine to create a closed loop system.

What AI labeling actually is.

The impact of unsupervised learning on the need for labeling.

Three layers of AI capabilities.

Why AI is accessible to everyone today.

How AI powers John Deere’s tractors through See & Spray technology.

The biggest challenge that AI adopters are facing today.

Manu’s prediction for the rate of progress in AI technology.

#Update
stale
Added one year ago

"...there has been no improvement in trading conditions in August and September"

Management pointing out lower revenue and lower margins. And now expecting US$13-18m in EBITDA for FY22 (ends Dec31). Last year they did US$79m...

EV/EBITDA of 15x could seem cheap, but there's just way too much uncertainty for me. Potential for their business to be far less relevant due to rapid structural change to the industry. Or not.. it's just waaaay outside of my wheelhouse.

ASX announcement here

#Is it over for Appen?
stale
Added 2 years ago

It is for me!!! After all this time, I've decided to cut my losses and move forward ...... Lesson learnt.

Can say that I already feel better & can now focus on making better decisions into the future. Thank you Strawman ....... So glad I could try it here & not in my RL portfolio ...... here it's just pride that takes a hit!!!


#Post Mortem - Lessons Learnt
stale
Added 2 years ago

Why I sold now:


I sold all of my holding yesterday after the announcement of the downgrade expected in the 1HFY22 results and rest of FY outlook. Group revenue down 7%, with a weak global division, "underlying EBITDA" down to only $8.5 mil (69% down) and worst of all, NPAT loss of $9.4 mil. The company made it clear the outlook for the rest of FY22 is uncertain and are expecting lower revenue and profits than previously thought. The only glimmer of hope someone could take from the announcement is the continued growth of the China segment with first half revenue up 141% PCP to $18mil, however, if you actually compare this to H2FY21, the result is only up from $17.2 mil so half on half a terrible result considering this segment was looking to be a real growth engine. I get a strong feeling results will get worse again before they get better in the future. Note all $ figures in USD.

My thesis was based on a turnaround from the bump in the road that was COVID for Appen, with the potential for growth to be restarted after the initial COVID hit. This turned out to be incorrect with the opposite occurring, results are continuing to degrade with no positive move in sight. Assuming that the old results could be a baseline was incorrect. I would currently give a valuation/target price of 15x times a $25mil profit for FY23 + $50 mil cash. This gives a valuation of $3.44 a share. This valuation is optimistic at this point but is still below the current market price. After previous updates I could still justify holding (obviously wrongly now) with a lower personal valuation, but those new valuations were still above the market price at the time. Needing to lower my valuation should have been another warning sign. 


Post Mortem - Summary of mistakes and lessons learnt from owning Appen:


  • The first day you bought, you bought because they were up a few percent and a recent high. One day doesn't show any momentum. Over the next month the shares were down 35% at one point. There was no momentum. Always buy with some real momentum, otherwise wait.
  • You bought when you knew results were imminent. Always wait for results to confirm your expectations. It is all about risk adjusted returns. The risk of unexpected results is much higher at this point in time than the likely returns from jumping in early in the hope of a quick buck from better-than-expected results. Ie, I would rather miss the first 20% of a multi bagger potential company than jumping in early in the hope of a quick jump but turns out, results are poor. 
  • Compounding the point above, I bought a smaller batch again before results, this was after some management guidance was released because I thought the market was wrong and now there was great value because the shares were down 25%, I hadn't changed my view and management had confirmed my view. Don't catch a falling knife...
  • The momentum of expectations, results and the company in general always continue to get worse and worse than expected. Very rarely are bad results and expectations turned around quickly unless there is an obvious factor. There was a bit of hope in this thesis (I guess every thesis really requires some hope otherwise you can't invest). I did not appreciate how hard it is to change momentum, not share price momentum but the momentum of everything to do with a company including the time it takes for changes made by a company to take effect. As a result of the holding Appen I have appreciated having a watchlist and taking my time sitting on the sidelines waiting and watching. At some point the market might give you the opportunity you are looking for when the outlook and momentum becomes positive then is the time to buy. If this is at a higher price so be it, you will receive better returns due to reducing the risk of permanent capital loss from a poor decision. In many cases you could be picking up a company on the upswing from the lows, therefore, maximising returns. 
  • No clear buying plan was set out at the start. Potentially shows how important this step can be because it acts as a guide and limits the impulse buy due to changes/announcements. A strong justification would be required to change the original plan. I didn't write down any notes on the second parcel of shares bought, this purchase was just after the initial purchase in the same month and still before results! A buying plan is a must do in the process now.
  • Buying a full position must be done over a decent amount of time, generally at least 6 months for longer-term holds. You went to a full position very quickly. This was always viewed as a long-term buy not a shorter-term trade. Therefore, there was no rush to create a full position so quickly. If I were following the new rules I have implemented, the losses would have been much lower. The importance of buying over time is that you learn more about the company over the time you own and watch the company. What you originally thought you knew about company changes and your conviction should change accordingly. 
  • In my original thesis notes it was time to sell if revenue after the initial covid impacts didn't return to 20%. While it was maybe fair to say covid impacts lasted longer than expected, if this exit point was followed more closely, my capital could have been saved.
  • Hard and painful lessons learnt. Many of the points above have already been integrated into my processes and checklists to stop the same mistakes from occurring again.
  • Market sediment/opinion does matter. It is not just about what your convictions and belief of the fundamentals are. You need to consider the market and not think you are smarter than it, to a point of course. 
  • When there is negative momentum and deteriorating fundamentals, it is better to just get out early and sit on the side-lines and if positivity of the story or momentum changes you can get back in. Holding because you see the potential for change or the long-term story being different isn't enough because it is too late when you find out you are wrong and capital is lost permanently. I have found when I have exited other failing positions it often provides me with better clarity as it reduces some of the bias you have when you hold a position.  
  • I was too confident in the turnaround story that really had no basis besides management saying things should get better but in reality, it was disappointment after disappointment. 
  • Conviction did decrease. I should consider a rule that this means cutting or trimming a position as a result. My concept is for long term holds, that over time of holding I should be becoming more confident and have a better understanding of the business. If you don't want to buy more (if you could with no consideration for portfolio weighting or available capital) then should you be selling.
  • Just because you think a stock is cheap doesn't mean it won't get even cheaper! Appen is now an example of a stock where it was down 80% and halved from there! Ie down 90%! Luckily, I didn't get in at that point!
  • Don't believe management words but the undertones of the message. When a downgrade is given it tends to end up worse. This was a great example of the need to not listen to closely to the positive messages of management, about how they plan for things to get better. Rather read the underlying message and take a cynical view of management comments.
#Media Reporting
stale
Added 2 years ago

Why Appen’s big problem is that it’s not a tech company OR Why Appen's caught in an identity crisis

Interesting article in the AFR today – "it is still a services business, not a technology business"

https://www.afr.com/technology/why-appen-s-big-problem-is-that-it-s-not-a-tech-company-20220526-p5aoun


#Foundation models
stale
Added 2 years ago

Having just listened to this podcast it’s difficult to see the bull case for Appen any more. Others seemingly correctly pointed out that we have mostly tipped over the cusp where humans are required to teach AI I didn’t believe we had reached that point yet.

fascinating stuff

https://podcasts.apple.com/au/podcast/babbage-from-economist-radio/id508376907?i=1000565537282

#Revocation of non-binding prop
stale
Added 2 years ago

Oh dear.

In a late-afternoon announcement Appen said: "This afternoon, Telus informed us that they were revoking their Indicative Proposal. No reasons were given."

This doesn't look good, as everyone will be asking why Telus backed out so quickly. On the other hand, Appen also said "No confidential information was provided to Telus" so presumably Telus doesn't have any more information than they did when then made the proposal. I'm not sure what to make of it, but the share price tomorrow is surely (?) going to take a beating.

At any rate, that's the definition of "non-binding".

Disc: held. (Why didn't I sell earlier today...?)

#Thesis Review and Results Note
stale
Last edited 2 years ago

Lessons Learnt, Thesis Review and Comments on Appen


Some expensive lessons learned the hard way while holding Appen:

  • There is no need to jump on a company just before results. Unless it is clear they will be positive. There was a highly likely possibility when I entered APX that results for FY20 could be negative and they were...
  • So what did I do? Buy some more... If I liked it at $25, why wouldn't I like it at $18? Lesson learnt - don't catch the falling knife! Why enter a stock that has negative sediment and negative outlook on results even if I believe longer-term it is worth more than the current price? Things almost always normally get even worse before they get better. The negative momentum continues for much longer than you think. It makes it extremely hard to tell if you are wrong or it is just bad sediment is pushing the price down?
  • This report should have been the time when I added Appen to the watchlist ready to jump in after the next report when they have two positive half-year results that match with the thesis. Expectations would have been reined in after a bit more knowledge watching the company. I think it will be an awfully long time before I see my original valuation of $32 again.
  • It takes time for the turn around to happen... So why not wait for the actual turn around in case it doesn't come or takes too long?
  • If most of the brokers are downgrading then good luck fighting that sediment... Brokers prices tend to be optimistic as well, so you got to take a factor off their target price. These are normally 1-year targets, so you must take some short-term pain as a minimum.
  • One very strong positive day does not mean momentum has changed. Momentum changes over time, one day is just noise/reaction.


What has changed to my approach to investing as a result:

  • Need to have positive momentum/sediment to make a purchase. There is no point buying otherwise. The positivity needs to be in the company’s results and the market sediment. I have been interested in buying Magellan (MFG) but haven't seen any positive news to even think about deep dive researching it yet. This has paid off as MFG is down significantly since I did a quick review to put it on the watchlist.
  • In the book "Taming the Lion" by Richard Farleigh, he notes you should never buy unless the trend has begun, you may not get the lowest price but you have reduced the risk of loss as you are not fighting potential negative momentum. QAV's basic three-point trend-line is another example of this. I can't see a valid argument against this approach, yes, you may miss the maximum outcome but risk-to-reward ratio is swayed very strongly to the reward side comparatively. I am investing to make multi-bag returns. What's the issue with missing the first 10-20% to earn 200%+ and minimise potential losses on the way there?
  • You need to sell if all signs are negative but still within the thesis. You can always jump back in. There was no guarantee 6 months ago the recovery may be starting in 2H as it did. When I have done this before with AVA, DUG, RBL it has been the right decision.

 

Onto the future of Appen and my holding:

The thesis for purchasing was based on Appen having 1-2 years of pain before re-joining the previous growth trajectory, not incorrect at this point but points out in hindsight how stupid it was to jump in at the point I did. The 2H result was positive with the resumption of growth, additionally the YTD revenue and booked work well ahead of the PCP. This is what I should have waited for.

Problem is, as I have learnt the lessons above, I have been holding APX shares. Do I sell out now when I see some positive company results which are aligned with my original thesis because the market sediment is still negative? I wouldn't be buying at the current point in time but it seems too cheap to sell and my thesis hasn't been proved wrong yet (the thesis revolved around picking up a downtrodden stock and holding long-term). Therefore, I will continue to hold but on a serious watch, ready to dump if any company results aren't positive.

In terms of the company, I still think Appen as a significant role to play in the AI space. Appen admits the big 5 tech giant's revenues will reduce proportionally over time. Management has a plan to diversify the business. Non-tech-giant companies (Boeing, Adobe, Siemens and Home Depot are examples of companies that use Appen's services) have unique data that will need to be labelled for their own applications of AI/ML, data-labelling as a service is Appen's core business.

AI/ML needs a high-quality training dataset, human verification of datasets must be a part of this loop to ensure accuracy. Without high quality data, as with all algorithms, rubbish in = rubbish out. For example, look at this meme video of Elon Musk promising self-driving cars every year since 2014, even with all the data collected so far by Tesla, they haven't produced a publicly available autonomous vehicle. AI/ML is hard to perfect!

I think the world is yet to discovery how many ways AI/ML can be used to improve productivity/profitability of businesses, the big tech giants have been integrating these systems for a while now but AI/ML is becoming a focus area of other enterprises, as shown by the large increases in AI/ML spending predicted into the future.

The "China" business (which is expanding into Japan and Korea) is a new high growth segment of the business which is performing well. The recent capex investments in new products, improving automation/productivity and restructuring do need to start showing results through increased revenue. The lack of capex previously was something missed in the initial thesis as a flag. Upon noticing this, I am not surprised over the past couple of years that growth slowed, compounded by COVID. Appen is in the innovation space so needs to continue to change over time, just like it has previously, moving away from its origins as a company that developed linguistic technologies.

 

FY21 Results Notes


General Notes


  • Management aspirations for FY26:
  • Double FY21 revenue.
  • 1/3 Revenue from non-global customers.
  • EBITDA margin of 20%.
  • How management plans to meet above aspirations:
  • Customer aligned organisation structure.
  • Increasing investment in product and engineering to up to 10% of revenue.
  • Team of data scientists to build and deploy machine learning models to pre-labelled training data.
  • Quadrant unlocking point of interest market.
  • Key financials:
  • Revenue = $447.8m, up 8%.
  • Statutory EBITDA = $72.9m, down 2%.
  • Statutory NPAT = $28.5m, down 20%
  • "Underlying" NPAT = $40.6m, down 10%.
  • Dividend = 10c (AUD) - entire year. 50% franked
  • Investment in product development of $30.2m.
  • Use of underlying NPAT is roughly fair. Amortisation of acquisition-rated intangibles is a significant contributor to the difference between underlying and statutory results. $1.6m in restructure costs I would add back, companies are always restructuring.
  • Underlying diluted EPS = 32.53c (US).
  • Cash balance of $47.9m (no debt).
  • "Free cash flow" (Operating activities - payments for intangibles - plant - lease) = 53.9 - 21.8 - 1.3 - 4.9 = $25.9m. Noting receivables are up $38m which may be the reason for the low number here but also contract assets down $21m, moved to receivables, therefore net $19m. Working capital increased $17.6m. Should see a pickup in operating cash flows next half.
  • New customers included Salesforce, Boeing, Adobe and Bloomberg.
  • New senior managers in 2H21: Chief Transformation Officer, SVP and GM of Enterprise, SVP and GM of Quadrant (Quadrant founder) and Chief Product Officer (from Microsoft). Good time for some change.
  • Roadmap notes the expansion of the China business into Japan and Korea.
  • Looking back at financials, Appen appears to have not spent much money on internal capex prior to 2019. Acquisitions was the main "capex" prior to 2019. This takes a few years to start filtering through. Development spend is: "increasing the range of products with more pre-labelled data sets, automated data labelling and model evaluation products".
  • Product development is amortised over 3 years.

 

Positives


  • 2H revenues were very strong compared to previous halves at $250m. Previous largest half was $212m. Global services revenue up 32% on 1H. Higher proportion of non-ad related projects.
  • China revenue up 442% to $24.7m. This business is expanding into Japan and Korea.
  • Revenue order book YTD plus orders in hand approx $190m this was $165m in PCP.

 

Negatives


  • EBITDA guidance was missed and no guidance given. This doesn't provide any confidence to the market.
  • Most risks in the risk section of the report make note of an increase or equal level or risk going forward. Not a positive sign for the future.
  • Risks note increasing pressure from competitors.

 

Has the thesis been broken?


  • On serious watch. Not a buy but not a sell yet based on thesis expecting weakness during COVID. Revenues need to start a strong upwards trajectory from here. See overall notes above.
  • Note: there is no denying I might just by putting my head in the sand again...

 

Valuation


  • Ongoing NPAT = $55m, PE target = 20, Cash = $66m. Price target = $9.48. Conservative PE ratio used due to previously very poor market sediment. If APX grows valuation can be rerated. All calculations in AUD.

 

What are you expecting and what do you need to see over the next reporting season or generally into the future?


  • Revenues must continue to increase and beat previous PCP.
  • Cash flows increase to approximately match underlying NPAT (smoothing out over time required).
  • Capex investments must start to show some improvements in terms of revenue and/or margins.
  • Given Appen is capitalising the majority of the product development, EBITDA is not a fair measure of profitability going forward. Need to look at cash flows and profitability (NPAT/EBIT).
  • Management "promises":
  • Target of 35% growth from non-global customers.



Note all figures quoted in USD unless stated. Fiscal years are calendar years.

#Rise & Fall of a Darling
stale
Added 2 years ago

I ultimately held this too long, but the decision to exit was a wise one. There's a great saying which is that "sentimentality about an asset leads to a lack of discipline." I suffered from commitment bias and also suffered on Appen from straying outside of my circle of competence. It was a massive lesson for me. 

Macquarie has been dead right on this, unlike Citi. Unless Appen can dramatically pivot, their involvement in this industry (human led AI data labelling) is a dead end. This I why I think a safe entry would need to be on a single-digit PE and even then, the industry is moving so fast that such an investment would hold risks. 

To be honest, I think Appen are doing their best in a difficult situation (although they acted way too late to start shifting their business and thought that US tech would be a goldmine indefinitely). The growth from the Chinese market (whilst not secure/sticky long term) is showing a very impressive trajectory. But, it is likely to eventually end up following a similar fate to the US tech giants. 

It is still a hot industry right now, with US tech valuations of similar firms through the roof. A friend of mine was involved in launching a data labelling firm recently, called Encord (https://encord.com/). They raised a $12.5M USD Series A round last year. However, they are more like Scale AI than Appen: replacing manual processes (that use crowdsourced workforces) that make AI development expensive, time-consuming, and difficult to scale. 

Had Appen's management been ahead of its time, it should have acquired a firm like Scale AI in 2018 or 2019 before it was too late. In 2019, Appen was valued at over $2b AUD and in August 2019, Scale AI raised a series C financing round that put the company’s valuation at $1 billion USD. Today, Scale AI is worth north of $7b USD. Appen's situation could have been avoided. Sadly, this is a story of the rise and fall of a former market darling.

#FY21 results - Thoughts
stale
Added 2 years ago

Not a terrible result for Appen but never good to:

  • Miss the lower end of the guidance range
  • Drop near term guidance and start talking about investing for “the long term”


Share price has been punished and rightly so. 


Couple of highlights:

  • QoQ growth of China segment (I maintain that if this was a stand alone business on the ASX it would probably be worth as much as APX as a whole – This would be also be stupid but probably true)
  • 50mil in the bank no debt


Bit of commentary on competitors and I wonder if this is a more plausible narrative for the decrease in revenue growth and pressure on the business model that we are seeing.


I still think that the price provides a margin of safety if you believe in the future on human annotated data. Assuming underlying cashflow the business is spitting out of ~$50mil USD (this number is hard to tease out and you may come up with a different one) I still get a return of ~14% moving forwards. 


Assuming roughly a 10% return to be an acceptable number gets me to a fair value of $10.50 – I will update my valuation to reflect this.

#Industry
stale
Added 2 years ago

From the Q4 facebook earnings release:

Our planned capital expenditures are primarily driven by investments in data centers, servers, network infrastructure, and office facilities. As we discussed previously, this range reflects a significant increase in our artificial intelligence and machine learning investments, which will support a number of areas across our Family of Apps. 

Something to ponder as it drops today inline with Facebook.

#Framework For Selling
stale
Added 2 years ago

I've recently made the decision to cut my losses on APX, which was down 40%.

In a Kenny Rogers song, 'The Gambler', the American singer-songwriter highlights his encounter with a ‘gambler’ on a ‘train bound to nowhere’. If understood as counsel about life, the general advice of the song isn’t straightforward. However, it does highlight an important truth – that some of life’s most important decisions come down to using accumulated experiences and knowledge to make a judgement call based on probabilities.

Analogies with poker aside, Kenny is right. Indeed, “knowing” what to do and when with long-held positions is one of the most challenging and important aspects of successful investing. In the below note, I expand on my own investment framework for selling and put it into context with ASX:APX. It was a difficult decision to make, but on the balance of probabilities, I think it was the right decision to make, for me.

https://www.tepinvestments.com/blog/knowing-when-to-hold-em-and-knowing-when-to-fold-em-asxapx-amp-asxqpm

Wishing all $APX holders the best going forward. I'm not certain that Appen is "down and out" — rarely are positions that black and white in the markets. Yet, I’d prefer to be on the sidelines right now and put my capital to work in better opportunities. It is difficult to swim against the current (sentiment) and I have the optionality of returning if I think the situation is changing. In my eyes, that is prudent investing.

February 2022 (H2 CY21 results release) will provide us with some further insights into the situation. But, for the moment, there are too many red flags to stay invested.

#New Major Shareholder
stale
Added 2 years ago

Mondrian acquires an interest in Appen

The London-based international investment firm, Mondrian Investment Partners, purchased a sizeable stake in Appen last week.

The firm bought a 5.1% interest or 6,272,348 ordinary shares in the company. This puts Mondrian as Appen’s fifth- largest stakeholder, behind notable companies such as HSBC, JP Morgan, Citicorp and C & J Vonwiller (ex-Chair and Founder).

The date of the share acquisition (on-market) commenced back on 20 October and finalised on 19 November.

Mondrian manages over US$60 billion in both diversified equity and fixed income asset classes.

Appen completed its restructure in May, focusing on its core business interests.

While its half-year results were underwhelming, the company expects an improved second half. This is supported by a strong order book, higher confidence in its pipeline, and the expected second-half revenue skew. The latter is due to its customers’ delivery schedule for e-commerce, digital advertising, and search programs.

I'm curious as to how Facebook's developments of a metaverse may impact Appen, we already know that Facebook is Appen's number 1 customer by revenue...

#Musings
stale
Added 2 years ago

Understandably, many here are frustrated with management due to the share price decline and the manner with which they have allowed it to happen. But, my view is that Appen's management team have acted in the same neutral, low-key, understated manner all the way since 2015. This is a continuation of what we have come to expect from MB. That style works tremendously on the way up when things are going well (50c to $40) but horribly on the way down when things are not going well ($40 down to $8).

I'm continuing to hold because the original investment thesis of mine has not yet had the chance to play out over a full cycle (initiated by COVID where US big tech reprioritised work). Do structural issues concern me? Yes. What concerns me is Facebook's developments in SSL; this absolutely could be a structural issue for Appen. This is why the share price was at $8. But, what reassures me is the number of new projects for Appen (albeit small in value) that are springing up within the very same big tech companies. The number of new AI use cases is staggering. What also reassures me is the hundreds of millions of dollars of smart money being poured into industry players like Scale AI from some of the best investors in the world. Sure, they are a competitor, but my point is that Scale AI plays in the same arena as Appen. If the data annotation industry was going to 0 (i.e. be displaced) anytime soon, I don't think we would be seeing investment into new data labelling players from firms such as Dragoneer and Greenoaks Capital (both San Francisco-based investment firms), and Tiger Global, the prominent technology-focused investment company based in New York.

Most of Appen's revenue comes from relevance projects for Facebook and Microsoft. Revenue for these projects was down 9% YoY in H1CY2021 v H1CY2020. Appen claims that this is because H1CY2020 had no COVID impact (true at the time for big tech) and H1CY2021 experienced a major pivot of big tech away from ad-related revenue into new AI projects (which initially are less data-intensive). If revenue for content relevance with Facebook and Microsoft does not return by the end of CY2022, then we have a more evidence-based data point to suggest Facebook are removing their needs for data annotation in the relevance space (rather than re-prioritised temporarily). If this is the case, the management team of Appen need to face the public and explain why their explanation at the time deviated from the truth and whether they misled investors. This would be a serious event. But, we don't have to worry about that yet because that is purely a hypothetical at this point in time and Appen maintain that this revenue will return gradually. Management has been truthful along the journey since 50c and I trust that they are doing their best currently to maintain that reputation.

For the moment, Appen's guidance (for flat/increasing revenue) suggests that although there are some amazing breakthroughs taking place in SSL right now, even at Facebook and Microsoft, Appen's services are still needed. What gives me the confidence to continue to hold my major position here and not take the loss is that Appen remains working hand in hand with Microsoft and Facebook to this day. China/Govt/Enterprise are also important and are progressing well, but we want the core of this apple to not go rotten. Encouragingly, Appen has more projects live right now than at any point in their history (many of them are low in value but can grow in time). Appen is also doing increasing amounts of work with major auto companies. This is a competitive space, but great to have a foothold here. Time will be the true test. Solid growth and/or upgrades in CY2022 and the share price has a clear path back to $20+, where I will be in profit on my APX holding. There is of course the possibility of further downside if Appen's business deteriorates, but at this stage, I like where the company is at (making acquisitions, investing heavily, acquiring new talent, and with cash in the tank and no debt). I'm happy to wait another few years here to see how SSL evolves, it is definitely a threat, but I don't think it will displace Appen (or Scale AI/Samasource/Labelbox/Hive/Cloudfactory/DataLoop) any time soon. One of my favourite quotes is that "It is often never as good as it seems, but also not as bad as it seems. The truth lies somewhere in the middle." I think that is applicable to Appen today. The greed to fear to greed cycle continues, but I am staying the course...

P.S. I will update my sentiment to buy if Appen can meet their guidance for full-year CY21 and guide higher again in CY22 by at least 20%. For now, it remains a hold for me.

#MakeitAppen
stale
Added 2 years ago

Time to change your mind?

“Patient opportunism, buttressed by a contrarian attitude and strong balance sheet, can yield amazing profits during meltdowns” - Howard Marks

I struggle to find many others companies that have fallen so far out of favour with the market as Appen.

12 months ago, Appen was a $~4.5B company, today it’s a ~1.1B company. Certainly this isn’t completely unparalleled, especially in small caps, bute even with all the development that have unfolded in that period, it’s seems difficult to believe in the efficient-market hypothesis which such figures.

Perhaps a lot of investors decided the questions that need answering to hold Appen are a little too complex. Here are some I think are important:

  • Are we really at the point where machines will be teaching machines?
  • How easy or difficult is it to get a seat at the table with these giant tech companies and convince them you can help them develop their artificial intelligence models?
  • Are Appen telling the whole truth about Ad Revenue when these big tech firms appear to have growing ad spend?
  • Will Snorkel’s success rip the whole demand for assistance to shreds?

Or perhaps it’s even simpler, my perspective on Appen is that the very emotional ride of the share price in the past 2 years has put off those that held it; many have come to the conclusion the space is too difficult to study, it’s moving too fast and if you combine that with a 60% loss in your initial investment, well it makes sense to exit. So is this in with the new out with the old?

On one end of the spectrum, some believe Appen is nothing but an expensive labour hire firm. On the other, we have those that believe that AI projects are growing exponentially in numbers, and that human assistance will continue to grow exponentially in necessity as the scale and complexity of these projects continue to evolve (ie. interpreting video vs. interpreting images). I find myself leaning closer to the later.

It’s a very difficult debate to have an accurate point of view one, and more importantly, solving this debate will not even provide us that clear a picture on Appen’s future; good businesses evolve quickly, and the services they provide today may look very different to what they will provide in 5 years time.

Certainly, the recent news has been difficult to swallow; down 2% on overall group revenue, margins under pressure, fears of solutions like Snorkel that will make labeling unnecessary.

My belief is that in a market where the average PE is well in the 30s, Appen is trading at a reasonable price as it stands. 1 year ago, the valuation left little room for error, as things stand, trading at Enterprise value/EBITDA of 14, Appen don’t need to get absolutely everything right to win, If they continue to execute in growing markets, continue growing their new ARR model, continue to broaden the scope of AI projects they take on, well, the shares will perform above the benchmark.

Being the contrarian is one thing, being right is more important, and there’s never any certainty on that. Some of the smartest investors I follow are on the other side of the trade I’m making today. But I thought I would publish this here really to keep myself honest, and if things go sideways for Appen, well, I will have learned a lesson. To quote the same genius I quoted at the beginning, “Experience is what you got when you didn’t get what you wanted.” ? Howard Marks

#Thesis
stale
Added 2 years ago

A great summary of Appen and the investing thesis. By @galiciaInvestor on twitter.

Bit of scuttlebutt too signing up to be an annotator. 

#Musing on the thesis
stale
Added 3 years ago

Key to the discussion about Appen is whether or not large scale crowd annotation is required for the ongoing advancement of AI. Being the largest player in this space Appen will have scale advantages meaning It’s likely to be an effective competitor if the first statement is true. If you think that’s false probably Appen is a non-starter.

 

Certainly, you have to wonder whether less is needed when you look at the commentary surrounding the space. Lowered costs of AI training, automation and self labelling. Certainly these things exist. Do they displace crowd annotation or perhaps just push the margins the wrong direction?

 

My personal take and I could be very wrong is that human curation of large data sets still has a place. Listening to Tesla engineers describe the utter confusion of the AI on arriving at some routine roadworks or labelling unique situation of people and pet running down a highway is that really challenging final few percent of improvement to get to a FSD product. Recent exodus of senior staff from Waymo and delayed rollout schedules speak to the scale of the issue. One of the solutions is likely to be more data and some of that in my opinion will need to be human annotated data.

 

I think takeover is very unlikely unless there is a random SPAC that is looking for a home as Appen’s diversity of big tech companies as customers means that any one of them is unlikely to see it as a synergistic relationship. I think this is a negative.

 

Data is the new oil, Appen is a refinery it is a heck of a tailwind to have. Valuation is getting cheaper and cheaper if you believe they can grow moving forwards.

 

Assuming lower end of EBITDA guidance (~$109mil AUD) that places it on around a 12x Price to EBITDA multiple. Not bad at all if you believe there is some growth ahead. I would guess that fair value would be closer to 20x (but that’s just like my opinion man).

 

Recent reporting was a mixed bag, flat revenue, growthy bits of the business, better pipeline and a negative narrative regarding the ongoing value proposition of Appen which as I’ve said I’m not convinced is valid.

 

All that said I certainly don’t feel there is a rush to buy currently. 12 month momentum is extremely negative and sentiment is poor. I think it’s likely Appen falls more in price (I don’t make the rules). I actually welcome this and will have to have a really good think about what constitutes an attractive point for myself (Probably around $8.5 so it probably won’t quite get here). I do continue to hold a small position (getting smaller all the time in fact) with a longer term horizon.

#H1CY21 Results: Where to from
stale
Added 3 years ago

Firstly, H1 was always going to be a challenging period on a comparison basis because if we remember back to CY2020, Appen wasn't actually impacted at all by COVID in the first half of CY2020 (this is part of the reason why the share price raced to $40+ mid last year). It was only in the second half of CY2020 that Appen's customers' (US big tech) priorities starting changing (a shift away from traditional advertising-based revenue due to diversification efforts and legislative changes). Appen had already made it clear that CY2021 would have an earnings skew to the second half and so we shouldn't have been expecting much for H1.

Despite having a COVID impacted period (H1 CY2021) contrasted with a non-COVID impacted period (H1 CY2020), Appen managed to keep revenue flat (up 2% versus the pcp), that's not a bad effort, but could have been better. Profit (EBITDA and NPAT) however was significantly down because Appen is now deeply investing in new products, including the Quadrant acquisition. Of course, on the surface, the result looks horrible with margin compression and profits falling. Either Appen is in a structural decline (due to competitive threat and insourcing/SSL at US big tech) in which case margins will continue to be under pressure and the share price has much further to fall or this is a short term COVID induced blip and a transition point in the lifecycle of the company. To be fair, I think the truth lies somewhere in between but closer to the latter.

I think Appen does have a viable future (at least across the next 10 years) and importantly what I liked about the result is Appen is signalling to the market that it is up for a fight against players like Scale AI. Appen at this stage remains a "star business" (refer to the BCG growth-share matrix); it is in a fast-growing industry and is the leader in the industry. The acquisition, new executive appointments, increasing spend on employees to attract top talent, and increased spending on R&D/product (10% of total revenue) is Appen's way of saying, "we're in this for the long haul, we are the market leader and we aren't going down without a fight". Part of their competitive advantage is that they are a one-stop shop -- almost every data modality is covered by them (including geospatial via Quadrant). They have a size, scale, and breadth advantage compared to competitors and are increasing spend to stay the course as the leader. The industry is evolving fast and Appen needs to keep investing to stay current.

One of the risks from here is that Appen has once again signaled a skew; this time towards Q4. This again puts Appen on a tightrope. There is a chance that Appen will miss guidance again come the H2 results in Feb 2022, although Mark appeared more confident than previously on the investor conference call citing an increasing order book with a stronger proportion of late-stage deals. If Appen this time deliver on what they have guided, half 2 is going to be massive to make it to US$80m EBITDA (A$110m EBITDA) for the CY21 year, given H1 only reported underlying EBITDA of US$27.7m. It is also going to look really good if they achieve that because the prior corresponding period (H2 CY20) was a shocker. $110m AUD of EBITDA, if achieved, with guidance of c.20% growth in CY2022, probably puts Appen on a 15x CY22 EBITDA multiple for a market cap of $1,980 for a share price of $15.84 (SOI of 125M). If growth in CY22 is again achieved and again signaled for CY23, then we have a path back to $20-$30. So it is a long time frame that we are now looking at for those that hold with higher AEPs.

With every investment and every month that passes, I'm trying to become a better investor (and person) and Appen has certainly been part of that journey: I've made plenty of mistakes here. One of my key learnings from this experience has been to use stronger technical analysis filters alongside my investment thesis. For example, going forward I will be implementing a hard and fast rule to not buy a company in a technical share price downtrend, no matter how oversold or cheap one believes the valuation to be. I've caught a falling knife here, with an average entry point below $20 but still a position where I am significantly underwater. So far, I've taken 1 step back for every 3 steps forward with my investing journey... I'm ok with that, I think it is normal. Overall, investing has been a thoroughly rewarding journey for me and I expect that to continue; for those who keep learning and keep moving forward, this journey will work out well in the fullness of time. Everyone needs to be humbled by the market every once in a while to keep them honest. What matters most is what you learn from it.

The biggest question is probably -- has the investment thesis broken? One thing I have learned is to not fall in love with a stock and if the investment thesis breaks, it is time to say goodbye. I have no emotional attachment to Appen, I'm here to make money. Has Facebook, Google and Microsoft turned away from outsourced content relevance work completely? Will Appen need to rely solely on new markets revenue now, which may have a limited runway, despite growing at an amazing clip at the moment? Will China's revenue continue to ramp up at an unbelievable pace (up 5.5x YoY) or will China too eventually shift priorities and strategies to deal with outsourced data labeling?

The easiest way to tell the difference between an amateur and an experienced investor is that an amateur will tell you that an outcome is a "sure thing". For Appen, no one can proclaim to know what will happen next and how this situation will play out, not even Mark Brayan himself (for what it is worth I think he has been given a hard time and is working hard to keep APX as the market leader during a tough COVID induced transitory period). Whether this is the beginning of a structural decline or a short-term transition point as part of a much longer dynamic journey at the beginning of the AI uptake curve is yet to be seen. I think it is more likely to be the latter, but I'm far from certain. Lou Holtz — 'Nothing is as good as it seems, and nothing is as bad as it seems. Somewhere in between lies realty.'

I think Appen has a chance to evolve and continue to be at the forefront of the AI data labeling industry even as the industry may evolve to the detriment of historical business lines. There are plenty of green shoots: Indeed, Appen's China division is looking particularly interesting right now, if that run rate continues (60% per quarter), it will be on an annualised run-rate of $118m USD by this time next year. The number of new project wins is also very encouraging.

Perhaps the biggest risk of all is taking no risk: for the moment, I am going to stay invested. Switching my sentiment to HOLD until I see a reversal of fortune in the share price and in results (H2 CY21).

#Valuation
stale
Added 3 years ago

APX - Over and Out

First of all, a big shout out to my fellow members for the various notes and references which I have digested. As a long term investor, I am a reluctant seller, and resisted the desire to sell at the market opening yesterday after having listened to the investor call.

My valuation scenarios are $11.00 base with downside $9.00 and $17.00 upside, with none of the cases assuming a fundamental change to the business model and competitive positioning we are seeing now.

In all cases, I assume that automation of data-labelling grows progressively and over time captures the lion's share of the AI-data opportunity. However, I assume that a signficant and growing niche for manual labelling persists and that APX continues to develop its own limited automation capabilities. 

In terms of revenue growth scenarios, I settled on 10% as a central case: established markets are stable at best and new market growth starts out at 25% from a low base and also matures over the decade, due to competition. (Evidence: yesterday's call cited autonomous driving in China as a new market, but based on the recent Tesla AI day, it will not take long for automation capability to reduce the opportunity here too.)

In essence, I believe APX has a place in using manual labelling enhanced with productivity tools to take on emergent and niche customer opportunities, particularly where those customers cannot access advance data-labelling tech and rely on manual data-labelling at the early stage and for validation. However, the more material of these project will warrant development of automation, which over time will become ubiquitous.

Yesterday's Q&A was not a pretty sight. CEO Mark Barayan seemed almost weary in defending the guidance on 2H21. The pattern of a strong 2H is well-established, and it sounds like they have got close to their customers and are confident in the revenue. But guidance for 2H21 is well beyond what has been achieved in the past. Success gets APX towards 10% growth longer term, which is my starting point.  But it is unclear where the further upside and return to higher growth is coming from. I have no doubt that he has been beaten up a lot in the last 12 months from instos and Board. A final straw for me was the re-issuing of new guidance, and then in the same breath guiding towards the bottom of the new range. Surely, no-one can believe that the risk profile around H2 delivery is weighted so finely that you wouldn't put your target in the middle of the range? I consider there is too much pressure for another "miss" here.

A comment on my $9.00/$11.00/$17.00 scenarios- this doesn't mean the upside is asymmetric and that I should HOLD. These are more sensitivities in the modelling than true scenarios. I have not valued the scenario where the business model is broken (see some of the commentary from other Members) and we see lower growth and lower margins. You can create anything from $5-7 in that case, but I have chosen not to. I also did not seriously consider scenarios whereby APX invests significant capability in automated data labelling. It looks like that game is over and big tech has got their first.

I look forward to returning to this note in 12 months time, as I think we will learn a lot over that period. I am not sure I would have done much differently based on what I know today, but will review the lessons with time.

[DISC: Not Held.]

I exited APX this morning at $10.81. I first bought APX at  $2.75 on 9/12/2016. Enjoyed the ride up and took profits along the way and lost some of the returns on the way back down. Overall, a c.100% return over 4.5 years, which is better than my portfolio average. 

#Competitive threats
stale
Added 3 years ago

Margins like the share price are dropping right down

You might say this is just a one-off result,

But I'd say there is more competition in town,

So growth will be harder; it's not Appen's fault.

 

 

Here are some competitive threats taken from this article about Appen's business model.

 

-----

 

One trend to watch out for is the advent of projects like Snorkel, a Stanford University initiative started in just 2016, after Appen listed. It “set out to explore the radical idea that you could bring mathematical and systems structure to the messy and often entirely manual process of training data creation and management, starting by empowering users to programmatically label, build, and manage training data.”

Today, Snorkel, which explicitly seeks to reduce reliance on human contractor data labelling, is “used by many of the big names in the industry (Google, IBM, Intel),” according to this machine learning specialist. The 2019 version of Snorkel brought with it an improved capability to automate data labelling.

The point here is not that Appen is a bad company, but that the public narratives around Appen are inadequate to explain its recent results. We live in a world where market participants are variously incentivised not to dig too deeply into the weaknesses of the business models of high flying stocks. That is why you still see unquestioned claims that it is not possible to realistically automate the data labelling services that Appen provides.

And yet, if stock market researchers dared to delve beyond the confines of company presentations, they would see this is a problem that smart people are actively attacking. Appen is an expense for big tech; do you really think no-one will try to undercut them?

Data Labelling Can Be (Partially) Automated, At Appen’s Expense

The authors of this study state that “As machine learning models continue to increase in complexity, collecting large hand-labeled training sets has become one of the biggest roadblocks in practice. Instead, weaker forms of supervision that provide noisier but cheaper labels are often used…” Their goal is to improve the weaker, cheaper labelling techniques, and they conclude that “our approach leads to average gains of 20.2 points in accuracy over a traditional supervised approach, 6.8 points over a majority vote baseline, and 4.1 points over a previously proposed weak supervision method that models tasks separately.”

Oh, and by the way, those authors are the same people running Snorkel, you know, the data labelling tool used by Google and IBM.

But it gets worse than that for Appen. You see, when Facebook was just starting out with deep learning neural networks, every new project would have started from just about zero, in terms of labelled data. These days, “A procedure called ‘transfer learning’ takes a neural network trained on a vast data set and specializes it with a small supplement”, according to Alex Krizhevsky, one of the early proponents of neural networks.

Put simply, “Transfer learning allows us to deal with these scenarios by leveraging the already existing labeled data of some related task or domain”, and “Andrew Ng, chief scientist at Baidu and professor at Stanford, said during his widely popular NIPS 2016 tutorial that transfer learning will be — after supervised learning — the next driver of ML commercial success.”

Finally, we have the spectre of unsupervised learning. I’m not quite sure how this will impact need for fully supervised data labelling like Appen provides, but I’m sure it will reduce demand. Below, you can see Facebook’s CTO boasting about a recent advance in image segmentation, without data labelling. Clearly, here, the change is that Appen was not required, whereas its services (or a competitor’s) would previously have been needed to achieve the same result.

 

https://twitter.com/schrep/status/1388189398496202752

#Appen (ASX:APX) v Domain (ASX:
stale
Added 3 years ago

Below are the financial profiles of two (very different) ASX technology businesses: Appen and Domain. One is valued at circa $1.5B AUD (Appen) and the other is worth twice as much at circa $3B AUD (Domain). These companies are very different with different revenue models. But, for the sake of the exercise, bear with me. If you saw these financial profiles below, without the context of the business, you would be crazy to think Domain is the $3B business and Appen is the $1.5B business.

  • One has been consistently profitable since 2017, the other has not
  • One has been consistently growing the top line since 2017, the other has not
  • One has circa 2x the revenue and circa 1.5x the profit as the other

Does Appen deserve to be trading at $3B and Domain at $1.5B? Do both deserve to be trading at $3B? One is deemed to have a decades-long runway of growth ahead of it and one is deemed to be facing a structural decline. If you were looking from afar and were told one company was operating in the AI industry and the other in the property listings market, you would be crazy to think that it was the AI business that didn't have a runway ahead of it.

If you were told that one business was the market leader in its industry (Appen) and that the other business was the #2 in its industry (Domain), would you be crazy to think that Domain is the $3B business (trading on 11x revenue) and that Appen is the $1.5B business (trading on 2.5x revenue)? If you were looking from afar and were told that one was confident enough to release guidance on earnings growth of 18%-28% YoY and the other had no guidance, would you be crazy to guess it was Appen with the guidance and not Domain? One has a PE of 23x and the other has a PE of 83x.

Sometimes the market is crazy.

#Board Renewal
stale
Added 3 years ago

I think this is an excellent appointment; Richard Freudenstein should be ideally placed to help turn around some of Appen's perception issues that have arisen in the past 12 months. If Appen can win back the trust and support of the instos, a re-rate of APX's multiples alone (back to historical levels) will send the share price back to $25+ levels. It will take a concerted effort, strong underlying results, and some carefully positioned 'marketing' to the Street. Also curious as to how Mr Vonwiller will treat his shareholding once he retires from the board. He sold $58m worth (2m units) in June 2020, so hopefully, that is enough cash to fuel his lifestyle across the next decade and he won't need to dip his toes back into his remaining shareholding in a meaningful way (and hopefully not at these deflated levels).

The content relevance division should be growing at the moment given advertising spend figures by the big tech players in the US. The Content Relevance division was given a significant boost by the transformative acquisition of Leapforce in late 2017 for A$105M. This was funded primarily by debt but also a small ($30M) capital raising – the only time the company has raised additional capital since its IPO. Leapforce was a global leader in Content Relevance with a crowd-sourced workforce of >800,000 people – and the deal immediately established APX as the #1 global player.While Appen typically does not disclose the identity of its clients, it has revealed that it works with 8 of the top 10 global technology companies, plus we know that Facebook and Google generated the vast majority of Leapforce’s revenue, and that Microsoft was APX’s largest customer prior to the acquisition of Leapforce. Based on the customer relationships graphic from the most recent investor presentation, these would still seem to be large APX customers.

The upcoming earnings announcement will also be interesting. Prior to the last 12 months, Appen had an enviable track record of earnings upgrades. In Appen's short history of listing since 2015, the company has generated 13 earnings upgrades and just 1 earnings downgrade (2020). This included upgraded guidance at four of the company’s half-year result reporting dates (FY15, FY16, FY17 and FY18), two upgrades on the release of full-year results (FY17 and FY18) and the remainder during the normal trading year (including at the time of the material Leapforce acquisition). The company's forward P/E inflated from ~20x in 2016 to between 30x and 50x across 2017 to 2020 and then back down to ~20x in 2021. If we expect CY21 underlying NPAT of $70m, at a $1.44b market cap, Appen currently trades on a forward PE of 21x. With earnings (EBITDA) expected to grow between 18% and 28% in CY21, that equates to a desirable PEG ratio of less than 1.

#Business Model Analysis
stale
Added 3 years ago
#Moats
stale
Added 3 years ago

Xero (XRO) is priced for perfection (PE of ~500) and Appen (APX) is priced for a structural decline (11x FY21 EV/EBITDA).

Which is the better business? 99/100 analysts will tell you it is Xero due to their strong competitive moat, high gross margin, network effects, and pure-SaaS model. But, when faced with the choice of buying Xero at a $17.4 billion valuation or Appen at a $1.37 billion valuation, I choose the latter.

If you can see moats where others don't, you'll pay bargain prices for the great companies of tomorrow. Of equal importance: if you can recognize no-moat businesses that are being priced in the market as if they have durable competitive advantages, you'll avoid stocks with the potential to damage your portfolio.

I think Appen has more of a competitive moat than most analysts are willing to believe right now amid all of the uncertainty (rising competition, regulation of big tech, changing COVID priorities, the rise of self-supervised learning etc.). Appen's growth is volatile; it always has been.

Buying shares in a company means you own a tiny piece of the business. The value of that business is equal to all of the cash it will generate in the future. A business that can profitably generate cash for a long time is worth more today than a business that may be profitable for only a short time.

Return on capital is the best way to judge a company's profitability. It measures how good a company is at taking investor's money and generating a return on it. To see if a company has an economic moat, first check its historical track record of generating returns on capital. Strong returns indicate that the company may have a moat, while poor returns point to a lack of competitive advantage -- unless the company's business has changed substantially.

If historical returns on capital are strong, ask yourself how the company will maintain them. Buying stocks with low valuations (multiples) helps insulate you from the market's whims, because it ties your future investment returns more tightly to the financial performance of the company. If the return on capital is higher than the weighted average cost of capital (WACC), then the company will be profitable over the long term.

As physicist and philosopher Niels Bohr once said, "prediction is very difficult, especially if it is about the future". Yet, that's exactly what we need to do when assessing the durability of a company's competitive advantage. But, sometimes the future throws you a curveball, and that's when you need to reassess whether a company's moat is still intact or the unexpected turn of events has done permanent damage to the company's competitive advantage.

I will leave that up to all of you to decide.

T.E.P.

#Valuation
stale
Added 3 years ago

The broker price target figures I have attached below for you are from prior to Wednesday's business update (19th May). Even before this update, Appen was oversold. I expect upgrades from here, particularly post the August half-yearly results.

This is a major turning point. Appen has provided some detailed visibility into the business on a segment level, that they have never revealed before. Over time, this will highlight the transition of the business to being an AI product-led business with recurring revenue (SaaS).

Over the past half-year, fear, uncertainty, and concerns have been highly exaggerated and this has been accentuated (/been made possible) because of the historical lack of visibility into the business. This restructure and change to segment reporting lines changes the game.


Even very smart people who I have spoken to (who are leaders in the technology sector) have been unfortunately swept up in fear around Appen's competitive moat, considering Appen "a glorified labor-hire company". Today's update and revelation of the revenue split by product/service debunks this myth. But, this is what creates opportunity in the market. Fear creates opportunity. One needs to form a position grounded in deep due diligence and hold it unless the thesis changes.


Here is what the now revealed facts suggest: a) 30% of Appen's revenue is now committed (i.e. recurring). b) The New Markets division (AKA Appen's training data products) comprises 20% of the business (and rising). c) This AI product-led section of the business is at an FY20 run rate of $85M USD and growing at 34% YoY.

If the 'new markets' division (Appen's training data products) of Appen was spun out and listed on the NASDAQ, I would guess it would be valued at $1 billion USD or more, alone, on a circa 10x PSR. Scale AI (a similar sized business to APX's new markets division and similar in tech capability) suggests that it could go for a lot more than that (Scale is valued at $7 billion USD!). This is the tech-enabled component of APX, where the majority of the future growth of the business will stem from.

The global division of APX is also a valuable division of the company, producing consistent mid to high single-digit profitable growth. This part of Appen is producing all of the profit currently (the new markets division has been cash-flow negative but is now at breakeven as of H2CY2020). I'd conservatively value the global division component of APX (i.e. the global tech giants relevance work) at a 10x EBITDA multiple for a value of around [($42m USD H1 + $46m USD H2) x 10 EBITDA multiple] $880m USD = $1.135 billion AUD.

Adding the two components together, using this sum of the parts methodology, I arrive at a current fair valuation of Appen of circa $2.425 billion AUD ($1.29 billion AUD + $1.135 billion AUD). With 123 million shares on issue, this equates to a current fair value share price of circa $20 per share. If you are comfortable forecasting out one year into the future and assume that the global division grows at mid-single-digit figures and that the new markets division grows in line with the AI industry average, one arrives at a price target at least $4 higher than that (i.e. $24+).

high volume day (such as that we experienced) is highly likely to have been driven by institutional purchases. My own analysis for a 12-24 month view falls somewhere between Citi & Ord Minnett. I believe that achieving a share price in the $25 to $31 range within that timeframe is very achievable.

Lastly, let me say this. If Mark Brayan's understated style (measured, calm and trustyworthy) (whom I support FYI) leads to an upgrade over the next 12 months, then a return to $30+ is well and truly in sight. I'd much rather have a CEO like Mark at the helm, who has a history of under-promising and over-delivering, than a brash and bold CEO who will claim anything to move the share price higher in the short term at the expense of trust, longer-term.

As a part-owner of this business, I am not a trader and I am investing capital here for consistent profitable growth in future cash flows. In the short run, sentiment and storytelling are all-knowing. But, in the long run, cash flows are the only thing that truly matters for the share price.

#Media reporting - "ASX tech st
stale
Added 3 years ago

A report in the SMH today, a few hours old now - not great timing for Appen following a tough for days. 

_______________________________________________
 

"Australian artificial intelligence company Appen has been hit by claims of racism in its recruitment processes after it asked job candidates to take a “paper bag test” about their skin colour.

A recruiter for Appen contacted Houston based Charné Graham to apply for a role as a social media evaluator at Appen. But after selecting ‘Black or African American’ from a drop down box on the online application she was then asked to select her complexion as Light - pale white, White- fair, Median - white to light brown, Olive - moderate brown, Brown - dark brown or Very dark brown to black."


https://www.smh.com.au/business/companies/paper-bag-test-artificial-intelligence-firm-appen-criticised-for-skin-colour-test-20210512-p57r5r.html

#Valuation
stale
Added 3 years ago

APX Multiples -- Are They 'Fair'?

Let's start by understanding exactly how Appen is being valued right now versus how it has been treated historically.

Computed below are the key multiples for understanding Appen's valuation over Jun 2017 to April 2021, reported quarterly.

These are: TEV/LTM total revenue, TEV/NTM total revenue, TEV/LTM EBITDA, TEV/NTM EBITDA, TEV/LTM EBIT, TEV/NTM EBIT, P/LTM EPS, P/NTM EPS, P/LTM Normalised EPS, P/BV, P/Tangible BV, P/BV, P/Tangible BV, P/NTM CFPS, TEV/LTM Unlevered FCF and Market Cap/LTM Levered FCF.

Across 2017 to 2021, Appen has traded across a range of:

  • TEV/LTM Total Revenue: 2.67x to 8.44x (3.3x currently)
  • TEV/LTM EBITDA: 17.33x to 48.82x (25.61x currently)
  • P/BV: 4.15x to 19.35x (4.15x currently)


What does this tell us?
Firstly, Appen currently trades at the bottom end of these historical valuation-multiple ranges. In other words, sentiment towards the stock is very low relative to historical levels.

Secondly, anything that affects the (perceived) timinglikelihood or duration of future cash flows will affect these valuation multiples. Thus, I don't think the situation we find ourselves in is as simple as classifying Appen as a cyclical v growth v high-growth stock.

Ultimately, there are a large set of factors such as competitive dynamics, pricing power, the nature of revenue (% recurring revenue), management, etc. that are all influencing broker estimates of future growth rates, margins and subsequently cash flow. This is reflected in the valuation multiples.

But, what valuation multiple is 'fair'?
I consider Altium & Wisetech the closest comparators to Appen on the ASX, albeit they are very different businesses. (The best comparator to Appen globally is Lionbridge AI).

These two businesses trade at enormously higher valuation multiples. Currently, they trade 340% (ALU) to 540% (WTC) higher on a revenue multiple basis and 55% (ALU) to 194% (WTC) higher on an EBITDA multiple basis.

There a few factors that dictate why Altium and Wisetech are being rewarded with higher multiples. The multiple premium afforded to Altium and Wisetech is significantly higher than that of Appen's primarily because of two main factors. 1) Earnings quality and 2) earnings reliability.

1) Earnings quality is reflected below in the operating statistics of ALU v WTC v APX, across gross margin (%) and EBITDA margin.

ALU has a gross margin approximately 1.9x higher than APX. WTC's gross margin is 3.3x higher than APX's. The EBITDA margin premium over Appen is between 2.2x (WTC) and 2.9x% (ALU).

2) On the other hand, earnings reliability can be reflected in the percentage of revenue that is recurring:

  • 65% of Altium's revenue is recurring
  • 91% of Wisetech's revenue is recurring


What could cause a re-rate in Appen's valuation multiples?
As discussed previously, analyst growth rate expectations are currently rock bottom and well below Appen's guidance. Confirmation from Appen that their long term earnings growth trajectory is sound (probably towards the end of this year with CY2022 earnings guidance) will lead to a normalisation of future growth rate expectations by analysts -- this will lead to broker upgrades and a rising share price. This alone should lead to a 50%-100% increase in share price if the valuation multiples return to APX's average historical levels across 2017 to 2021.

Long term, could Appen reach valuations as lofty as Altium's or Wisetech's?
Possibly. They might not be able to reach 15-20x revenue (which is extreme), but they are making important steps towards transitioning to a higher quality SaaS-based business model. There is one key chart to watch. The percentage of Appen's revenue that is recurring.

In 2H20, Appen reported a 343% increase in committed revenue versus 2H2019. This $92M of committed revenue in 2H20 is 31% of the total, up from $36M in 1H20 (12% of the total). In my opinion, this has been underestimated by the investment community.

Appen's acquisition of Figure8 was a game-changer for the company strategically. Figure Eight materially increases the quality of Appen's revenues and the breadth of its customer base via high growth, high-gross margin recurring revenue from annual platform subscription fees (SaaS model) earned from its ~200 customers.

The acquisition combined the scale, quality and language expertise of Appen's leading global crowd, supported by its efficient crowd management platform, with Figure Eight's innovative data annotation platform, to create a unique end to end solution.

We are only beginning to see the fruits of this acquisition. Accounting for differences in gross marginEBITDA margin and recurring revenue, it is my view that Appen deserves to trade on at least half of Altium's revenue multiple -- which would be a revenue multiple of ~7x (versus ALU at 14.6x). On 2020 revenue of $600m that suggests Appen currently deserves a valuation of circa $3.5 billion AUD -- for a share price of $28.

If Appen could reach ALU's 65% recurring revenue threshold, continue growth at a materially higher pace compared to ALU and increase EBITDA margin to close the gap towards ALU's 34% margin, it would be reasonable to expect that Appen too could trade on 10x+ revenue for a market capitalisation north of $6 billion AUD ($50+ share price).

Appen remains the largest holding in my portfolio -- I am grateful that Mr Market has provided me with a chance to enter at this level.

Time will tell if I am right.

T.E.P.

#Full year results summary
stale
Added 3 years ago

General Notes/Neutral outcome:

  • Revenue up 12% to $600 mil. Relevance up 15% while speech & image down 10%.
  • Underlying EBITDA $108.6m (+8%)
  • 136 new customers.
  • Guidance is positive with 18-28% growth but I don't think this is reliable.
  • China and government are focus growth areas.
  • 34% increase in projects with existing major customers. However, this is a result of a greater number of smaller projects.
  • Company noted face-to face sales and customer engagement was down due to COVID restrictions. This is potentially critical to COVID recovery for Appen. They will be able to personally meet and sell their product again over the next year. Customers will be able to sell their product which uses Appen's datasets. To me this point is a strong reason as to why revenue has not matched previous expectations. The need to be physically present to make sales is underestimated in my opinion. Engagement will need to improve, I think this will happen naturally as companies can begin to reduce their focus on core business and look for opportunities.

Positive:

  • Profit up 21.4% to $50.5mil
  • Customer wins in the Q4 was strong after declining Q1-Q3.
  • China growth.
  • Around US$100m of ACV at the end of CY20. However, as of 1 Feb 2021 this had risen to $124.4mil. Is this customers moving to committed revenue over projects or a bullish sign for H1CY21?
  • Relevance is the main driver of the business.
  • Strong employee engagement.
  • Overall cash flow positive with $78.4 mil cash on hand and no debt. Important to make it through the current downturn.
  • Cash flow from operating activities up 39% to $93.5mil

Negatives:

  • Revenue growth below long-term requirement for thesis.
  • Speech & image is going backwards and growth isn't as spectacular as relevance. Still producing positive EBITDA.
  • Appen now quoting annual growth rate of AI industry at 24%, I think this figure was previously 28%.
  • Brokers downgrading due to the poor result causing downward price action.
  • Current figures for revenue so far might be a bit weak. Purposefully hazy on year-to-date revenue whether its better or worse I can’t tell?

Has the thesis been broken?

  • No, thesis was based on purchasing Appen at a weak point. The thesis requires growth to restart over the next 1-2 years. Will need to see signs of improvement over the next year. 
  • Thesis is based on this point in time being a temporary stall rather than a negative inflection point. If a negative inflection point (lower growth in revenue/profitability) becomes evident = sell.
#FY20 results - Thoughts
stale
Added 3 years ago

Appen has grown into a fairly complex company over the last few years and the results take a bit of time to wade through, digest and contextualise. This is exacerbated by the extremities presented in 2020 making extrapolation of results in that year nigh impossible.

 

Some points are raised that are worth considering…

 

Appen have said that online advertising spend softened in 2020. Are we supposed to believe this given the record shift to online and a US election thrown in? While some are rightfully sceptical I think that it is possible as uncertainty leads companies to preserve cash and even if customers were spending more on advertising online APX is several steps removed from this direct spend and it is entirely possible that their customers delayed or reduced R&D and non-essential spending in their AI projects that require these data sets.

 

Currency had a wild year with the AUD swinging between mid 50 cents to mid 70 cents USD. Appen have given projections with the rough average of the exchange rate last year to allow them to “contextualise” the numbers. While that sounds reasonable unfortunately the AUD has rocketed up to almost 80 cents now so is going to be a significant headwind unless there is a reversal back down. Of course it could even move higher. That said the important thing is being aware of this. I try to construct my portfolio in a way to diversify across large currency movements. If you are like me and earn AUD it can also be worth remembering that although this hurts Appen your global buying power is rising so I don’t hate this kind of exposure. I certainly wasn’t complaining when the FX provided a free kick in the other direction.

 

When you look at the revenue by customer of the five largest 1 had good growth two reduced spending and two stayed roughly the same. Something to watch.

 

China growth is currently +60% quarter on quarter from a low base while it won’t continue at this rate it implies it could have revenue from $15 – 90million in just two years time (probably lower end). While speculative and currently immaterial if this was a separate listed entity on the ASX it would probably trade for $200+ mil valuation.

 

New customer acquisition is accelerating as they learn how to sell to smaller entities. This will help to mitigate the significant customer concentration risk.

 

Competition still not a major issue with essentially a competitive duopoly in place between Appen and Lionbridge.

 

No concerns raised invalidate my thesis for Appen and my expectation is medium to strong sustainable growth for at least the next five years. No view on the AUD.

 

I would recommend listening to the call to get some extra explanation of the presented numbers from the company that can be found here.

#Personal Investment Case
stale
Last edited 3 years ago

Appen at current prices appears to be a great opportunity with strong tailwinds behind it for at least the next 10 years. AI is one of Ark Invest's 5 innovative disruptive technologies. However, the investment case requires continual growth at 25%+ which will taper down to 20% by 2030. These are large numbers for a company already creating $500+ million in revenue.

Appen has a nice segment of the market. I found a figure that projects AI data will be 10% of all AI spending. Given Appen only has one other major competitor that I can find this gives Appen the opportunity to realise the revenue figures quoted above.

Customer value proposition:

Appen's value proposition to it's customers is the removal of project risks and provides price certainty. AI requires large and accurate datasets to train AI. For the customer to collect, process and use the data this expands the internal scope of the project. Questions customers have to ask themselves is: how many people to hire, who are the experts and how to hire them short time, what to do with them after collecting the data if it is a short project, how many working hours are required, do we have the correct systems to create and store the data, will  we do this right? By purchasing the AI training data from Appen, all of these risks are removed and the cost is known at the start. The time saving alone could be well worth it in the fast moving tech world.  To use the popular jargon I see Appen as an "AI data/training as a service or AI data/training on demand" company.

Positives:

  • Appen is a growth company that is strong cashflow positive and profitable.
  • Net cash
  • Strong momentum with growing revenues and profitability. 5 year ROE = 21% CAGR
  • "Picks and shovels of AI"
  • Management has significant skin in the game:
    • Chairman (founder) owns 7.61%
    • CEO and Bill Pulver have high 7 figures of wealth in the company (at current prices)
    • All other directors have at least $1m invested
  • MD pay in comparison to other companies:
    • Base salary is 8th percentile
    • STI is 33rd percentile
    • LIT is 80th percentile
    • Show me the incentive I'll show you the outcome... MD is paid lower for short term and higher for long term outcomes when compared to other similar companies.
  • Unless the case was for a strong bear case. I am yet to see a price estimate or valuation under $20. No sell analyst ratings only buy and hold.
  • Strong network effect having built up over 1 million workers to assist in the processing of data. This would take time to reproduce.
  • China expansion with strong protections of Appen IP ensured. This part of the business is only just getting started. China doesn't appear far of the US in terms of AI tech. A potential area for even more growth.
  • Long term chart - bottom left to top right. Any graph of revenue, profits, cash flows is the same. A great indictor of a company that exceeds in my view. Winners keep winning.
  • AI datasets need continued training. Over time the dataset is outdated or degrades.
  • Price appears to have a strong floor at around $20-22 since Feb 19. Dipped well below a long term 3 point trend line (on log scale).
  • Industry growth expected to be around 28% a year.

Negatives:

  • Concentration of customers - Top 5 clients provide 88% of revenues.
  • Increasing AUD/USD will reduce profitability
  • Recent announcements of weak figures. Is this a one off?

Risks:

  • Big tech giants take AI data work in house due to the amount of data they require it may become more economical or this puts pressure on margins.
  • Growth stops and is not as strong as predicted.
  • I can't find many negative reports on Appen therefore research and thesis could be based on confirmation bias.
  • Current figures are weak. Company says this is COVID related. What if this is not a one off as widely believed.
  • My figures are way to optimisitic.
  • Losses to other competitors.

When to get out:

  • When growth stops or significantly reduced.
  • Share prices in significant gains for a long time and doesn't discount any risk.
  • Margins are reduced causing a substantial change in valuation that no longer justifies the risk. Appen has had margins in a tight range historically.

Expected outcomes:

  • 30% Worst case - growth stops and Appen can only maintain profitability at current levels. No future growth from here. I use this as a base case given the expected growth in field. PE of 15 + cash = $8.6 per share
  • 60% Expectated outcome - 2030 PE of 30, Revenue growth 25% from 2021 to 2025 then taper to 20%. NPAT = 11% and discounted back at 15% = $32.44 per share.
  • 10% Best case: Same as above but 30% p.a revenue growth for every year to 2030. $82 per share.
  • Overall approximately a 60% downside risk for a 10 year return in the order of 20% p.a. compounding. Target price based on probabilities = $30.22

I see Appen as a strong "value" growth buy. I have been sitting on the fence due to the weak EBITDA expectation. Why only release the expected EBITDA figure? Are the revenue and profit figures worse?  I understand the companies explanation. At a granular level my guess is teams are all working from home in the US and its probably getting to the point where teamwork is dropping off and new projects are less important than keeping to your known strengths.

I will be looking to buy in small chucks to build a position given the current outlook but don't won't hold off if others start to realise the value I see here.

I would be very interested in a forum conversation with anyone who would like to point out what I have got wrong with this thesis! As mentioned I couldn't find many negatives...

 

 

#Conference Call Reaction
stale
Added 3 years ago

https://www.tepinvestments.com/blog/appen-apx-entropy-dcf-models-amp-investor-behaviour

“The trick is not to learn to trust your gut feelings, but rather to discipline yourself to ignore them. Stand by your stocks as long as the fundamental story of the company hasn’t changed.”
– Peter Lynch

 

Appen: An Aussie Star on the World Stage

From the 5 golden Aussie technology stocks (the ‘WAAAX’), at current prices, we like the look of Appen most. Given our investing style and Appen’s recent fall from grace, the smallest member of the 5 WAAAX giants is looking particularly alluring right now. In this research note we will evaluate why, but first, let us lay out the context:

Appen collects and labels images, text, speech, audio, video, and other data used to build and continuously improve the world’s most innovative artificial intelligence systems.

Appen’s competitive moat includes having a global crowd of over 1 million skilled contractors who speak over 180 languages and dialects, in over 70,000 locations and 130 countries, and the industry’s most advanced AI-assisted data annotation platform.

It is this reliable and cost-effective training data that gives leaders in technology, automotive, financial services, retail, healthcare, and governments the confidence to deploy world-class AI products.

The companies utilising Appen to deploy AI products are the real deal. We are talking about the BIG end of town. Although Appen does not disclose their customer’s identity, they do reveal that they work with 8 of the 10 largest Western AI technology companies on Planet Earth.

We believe those customers to be Microsoft (Azure), Google (Google Cloud), Facebook, Twitter, Mozilla, IBM (Watson), VMware and American Express, in addition to smaller AI application developers. Not bad for a somewhat little Aussie company that was founded in 1996.

Working with the giants of the tech world has propelled Appen’s growth. Since 2015, the share price is up an astonishing 1368%. Indeed, Afterpay is the only member of the WAAAX that has outperformed Appen across the past half-decade.

The top line is up 546% across 2015-19, from $83M to $536M. Moreover, with the underlying EBITDA margin holding in a range between 16% and 20%, EBITDA is up 622% over the same 5-year period from $14M to $101M AUD. Over this 5-year period, the PE multiple has ranged from 44 to 114, reflecting its status as a high growth firm.

 

Appen’s sell-off: sizing the opportunity

On the 10th of December 2020, Appen downgraded its FY2020 earnings guidance on the back of its heavyweight US-technology customers confronting new lockdowns in California and shifting their resources to new projects away from data-intensive mature projects in the wake of COVID-19.

Appen is still projecting overall YoY growth in both revenue and earnings, but this growth is now signalled to be slower than was previously indicated – the company noted that it was not experiencing the usual ramp-up in sales that has been experienced historically at this time of year.

Consequently, the EBITDA range for FY20 was downgraded from $125M-$130M to $106-$109M AUD, which includes an FX adjustment (headwind) from US$0.70c to US$0.74c.

The key piece of information for investors to understand is that the earnings update relates to the re-allocation of work by Appen’s customers. Some of Appen’s US tech clients have temporarily shifted resources (engineers) away from major existing projects, which are data-intensive, to focus on new project opportunities (that enhance their long-term resilience and value), which are less data-intensive. The mature projects have not been abandoned completely.

The share price is down circa 43% from the all-time high of $43.50 to $24.66 at the time of writing, for a market capitalisation of circa $3 billion AUD. We have taken this opportunity to add Appen to the TEP Investments portfolio and it is now our largest holding.

 

“Whether we're talking about stocks or socks, I like buying quality merchandise when it is marked down.” – Warren Buffett

 

We take a long-term view on value creation, seeking companies that have a disciplined growth strategy, a laser-like focus on their core market and are the leader in their industry. This process gives one the opportunity to look past the short-term valuation metrics and short-term performance if we can have confidence a business has the platform and management team to create a more valuable business on a medium and long-term basis.

What we are looking to identify, is a business that might look expensive on short term valuation metrics (i.e., one year forward PE multiple) or look ‘down and out’ because of a temporary earnings downgrade but offer value in 3 to 5 years on the back of strong compound revenue and profit growth.

 

Will this earnings downgrade be short-lived or is it the beginning of a structural decline?

For earnings downgrades, if the information released to the market causing the downgrade does not impact your original investment thesis, then your margin of safety has improved, potentially dramatically. For any earnings downgrade with a high-quality company, we consider if the change is a result of cyclical or structural changes.

Our view is that this is not a structural (long term) change in demand for Appen’s products and services. The largest western technology firms who are Appen’s customers (e.g., Microsoft, Google, Amazon) continue to grow at pace. Moreover, Appen has an opportunity to secure blue-chip Asian technology clients in the future, such as Tencent or Alibaba, and we believe this opportunity is not priced into the share price. Appen also has an opportunity to expand into other verticals such as finance and healthcare.

On the Appen earnings update investor call, CEO Mark Brayan highlighted that the company believes this COVID-related development could be positive longer-term in terms of presenting new revenue avenues that could complement a return to growth on their historical programs of work. However, currently, Appen has a lack of visibility on this and their near-term work orders and this is something we are vigilant of as a risk. This is the first time we have seen evidence of Appen’s customers struggling to cope with multiple R&D programs of work. Our view is that ramp ups in engineering, product and software hiring at the US tech giants may indicate that this is a challenge that will be managed through over the next 12 months and beyond and is temporary.

The long-term trends for Appen remain exceptionally favourable. Spending on artificial intelligence is growing rapidly at 28% annually and AI adoption should accelerate in a post pandemic environment according to market observers such as the Boston Consulting Group (BCG). Further, online advertising, a major source of revenue for Appen’s key customers and a reasonable indicator of their spend, is forecast to rebound strongly in 2021 according to analyst forecasts. In the Q&A section of the trading update conference call, Mark Brayan declared that he expects Appen to resume a growth trajectory in 2021 in line with market growth. The structural tailwinds, as well as the strength of the existing pipeline for 2021, support a return to strong growth rates in 2021 in line with industry trends.

Our conclusion is that this is a short-term cyclical earnings impact not a structural headwinds earnings downgrade – AI is here to stay.

 

How much is Appen worth?

Valuing Appen is notoriously difficult.

The challenge of this task is evidenced by the fact that broker fair-value estimates for Appen i) swing wildly and ii) vary wildly among the sample set. When a single-year earnings downgrade of circa 15% shifts a broker estimate by more than 25% despite the value of the business being the present value of all future cashflows across the lifetime of the business – we have an overreaction.

It implies that buy-side research firms have no real indication as to the length, likelihood, and size of Appen’s future cashflows and are tinkering not just with short term earnings but modifying key long term inputs to their Appen valuation models. Changes to the long-term growth rate or the terminal value of Appen leads to enormous variation in the fair value of the business.

With pessimism and uncertainly clouding investors’ judgement right now, short term fluctuations appear to have crept into long term assumptions. This forms part of our investment thesis and is part of what we aim to take advantage of over the next 12-24 months with the Appen share price as long-term growth assumptions normalise again once Appen proves this current set back is temporary.

We have tested 3 scenarios across the TEP Investments APX discounted cash flow valuation model: i) the bear case, ii) the base case and iii) the bull case and determined a fair value target price using a blended valuation across the 3 scenarios.

Across all 3 scenarios, the following has been held constant:

  • A corporate tax rate of 30%

  • A weighted average cost of capital (WACC) of 9.9%.

    • This is based upon a cost of debt calculation that reflects i) the risk-free rate, ii) the country risk premium and iii) the sector’s (technology) specific cost of borrowing

    • Annual inflation rate of 2.40%

  • An EBITDA multiple method for calculating the terminal value

  • Assumed total shares on issue remains constant at 122.35M

  • Assumed the underlying EBITDA margin is 17% in 2020F and rises gradually (linearly) to 21% by 2030F (across 2015-2019, the EBITDA margin has ranged from 16% to 20%)

  • Assumed the EBIT margin is 11% in 2020F and rises gradually (linearly) to 16% by 2030F (across 2015-2019, the EBIT margin has ranged from 12% to 16%)

 

The Bear, The Bull & The Human

In the bear case, we assume that Appen is unable to meet its promise of returning to an industry standard growth rate (28% p.a.). We assume Appen’s top-line grows at 20% in 2021F and then gradually declines (linearly) to 12% growth YoY in 2030F. This is a low-growth scenario in which Appen would be underperforming the industry growth rate by a significant margin. We consider it a highly unlikely scenario but find it a useful exercise to determine a likely floor in the share price. In this scenario, we assume a terminal value multiple of 6x 2030F EBITDA to match the assumed low growth trajectory of the business. This scenario leads to a fair value share price estimate of $18.81 per share.

In the base case, we assume that Appen can meet its promise of returning to an industry standard growth rate (28% p.a.). We assume that Appen’s top line grows at 28% in 2021F and then gradually declines (linearly) to a growth rate of 20% YoY in 2030F. This is a moderate growth scenario that tapers off, such that Appen is likely to have underperformed the industry growth rate overall across the forecast period (2020-2030F). We consider this a viable scenario, but, there is a fair chance that the business outperforms this scenario if Appen can match and maintain the industry growth rate.  In this scenario, we assume a terminal value multiple of 7x 2030F EBITDA to match the moderate growth trajectory of the business. This scenario leads to a fair value share price estimate of $36.71 per share.

In the bull case, we assume that Appen beats the projected industry growth rate (28% p.a.). We assume Appen’s top line grows at 28% in 2021F and then rises to 36% YoY growth in 2022F buoyed by a bullish post-COVID environment and maturation of new customer projects and/or additional growth from one or more new blue-chip clients (tech giants – Alibaba, Tencent etc.) in China. We then assume that the growth rate gradually declines (linearly) back to a growth rate of 28% by 2030F. This is a high growth scenario that beats the projected industry growth rate and then tapers off in line with the industry growth rate. We consider this a possible scenario. In this scenario, we assume a terminal value multiple of 8x 2030F EBITDA to match the high growth trajectory of the business. This scenario leads to a fair value share price estimate of $66.98 per share.

Finally, reverse engineering the model to arrive at the current share price (circa $25 per share) reveals insights into what the investor community currently collectively believe the growth rate of Appen will be going forward.  Using the same margin, WACC, and terminal value assumptions as per the above scenarios, reverse engineering the model reveals that the investor community are collectively pricing in a revenue CAGR of 19% across 2020-2030F for a share price of $25 per share, well below the expected industry growth rate (28% p.a.). This contrasts with the Appen track record of high growth; APX achieved a 54% revenue CAGR across 1H FY2015 to 1H FY2020.

Ultimately, using a blended valuation approach and applying a likelihood of 15% to the base case, 50% to the base case and 35% to the bull case, we arrive at a TEP Investments target price for Appen of $44.62 per share.

The law of entropy & investor psychology

However, unless you have a crystal ball (we do not even get one here at Oxford University, unfortunately), projecting the future growth rate of this high-quality business is a little bit like throwing darts at a dartboard. We can refine our throw with practice, industry insights and objective research. Yet, the law of entropy states that all things in this universe trend towards disorder – there is no guarantee where our dart will land.

Moreover, left unchecked, disorder increases over time. Energy disperses, and systems dissolve into chaos. The more disordered something is, the more entropic we consider it. The Greek root of the word translates to “a turning towards transformation” — with that transformation being chaos.

Entropy is fundamentally a probabilistic idea: For every possible “usefully ordered” state of molecules, there are many, many more possible “disordered” states. Just as energy tends towards a less useful, more disordered state, so do businesses and organizations in general. Rearranging the molecules — or business systems and people — into an “ordered” state and maintaining it requires a continual injection of outside energy.

So, although we cannot hope to predict the world and future business outcomes with high levels of precision, can we still win on the roulette table of life that is the investing world?

I believe so.

There is something more predictable than the future ever could be and this is what the best investors manage to understand and take advantage of – human behaviour.  In short, we can predictably assume that human behaviour is unpredictable. Humans are not rational market participants. Humans are irrational market participants.

Humans emotions and investment markets will always continue to swing back and forth along the investment pendulum. Charlie Munger’s ‘Psychology of Human Misjudgment’ speech given at the Harvard Law School in the mid-1990s is in my eyes the finest investment speech ever given. The speech does not directly touch on investments but that tells you something – the most enduring advantages are psychological.

We do not need to predict the future of Appen with certainty. What we do need to know is that investors are currently viewing Appen with a bearish view of its future growth trajectory – this has been highlighted via the DCF analysis above. The pendulum of investing has swung out towards one of its two endpoints – it is much closer to fear than it is to greed. We also know that a pendulum rarely spends considerable amounts of time at either end of its arc and the further it swings out to an extreme the higher the likelihood that the pendulum will reverse towards the other direction.

With a more positive growth outlook from Appen at the February 2021 full year FY2020 update or with a more positive update at the H1FY2021 update in August 2021, analysts and investors will begin to normalise their view of long term Appen growth rates towards the base case and potentially to towards the bull case. Fair value of this company swings extraordinarily with relatively small shifts in the long-term growth rate.

With the earnings downgrade, the market pendulum has swung to the bears – but just like the inescapable tug of gravity, the reversal of the ‘sentiment pendulum’ is inevitable.

It is almost impossible to predict the future of Appen’s business performance flawlessly, but it is almost a certainty that investor sentiment will swing once more… and with it… the share price.

T.E.P.

 

“We can all observe that stock prices, set in an auction market, are more volatile than business values. Several studies and casual observation reveal that individual prices oscillate widely around a central price year in year out, and for no apparent reason. Certainly, business values do not do this. Over time, this offers the prospect that any business, indeed all businesses, will be meaningfully mispriced.” – Nicholas Sleep

#Financials
stale
Added 3 years ago

Re APX my read is that anyone who listened to the company's last call would not be too surprised at the downgrade. IMO the last call had quite a few caveats, MD was quite cautious, APX do not have significant visability on sales and although the US stock market is booming C19 is still impacting normal activity. i sold APX a little while ago with the strategy to see if we get a pre xmas downgrade then reass for potential re-entry. i think APX still has a growth pathway, a coupe of brokers still o/w, one upgdraed to o/w on this call. Likely Relevance will be irreleavnt (excuse the pun) one day, but not yet. my best guess at this stage is buy around $24-5. DYOR this is not advice.

#FY19 Results
stale
Added 4 years ago

Appen released its full year results today and there was a lot to like. Highlights for me include the following:

Core business revenue of 536 million a 47% increase on FY18. They further break this down into: Speech and image 67.7M (+32%) Content relevance 430M (+37%).

Figure 8 ARR of 33.7M (56% CAGR over last 4 years) – Acquisition now performing strongly and expected to positively contribute to EBITDA from second half 2020 but possibly even in current half.

Underlying EBITDA growth of 42% to $101M excludes figure 8 contribution.

EBITDA margin slightly lower from 19.6% to 18.8%. On call stated one large customer had agreed to fixed pricing for next five years which management were happy with stating that it relieved margin pressure although said they would be lower in first half due to investment in sales and marketing before returning to mid to high teens in second half. Interesting according to CEO business efficiencies will be reinvested in the business rather than allowing significant margin expansion.

Very positive commentary regarding growth avenues with two US facilities opening up allowing work with more sensitive US data. China office sounds well set up but low expectations being set for growth there. US government work and LIDAR 3d data set annotation also mentioned as areas for new contracts (lookout Pointerra).

Regarding corona virus seemingly little expected impact so far...

The Company’s full year underlying EBITDA for the year ending Dec 31st 2020 is expected to be in the range $125M - $130M (at A$1 = US$0.70, Feb-Dec 2020)