Machine Learning For Stock Trading Strategies
We spend a lot of time talking with startups that are trying to solve problems using “machine learning.” In order to understand if they’re actually using machine learning to achieve a competitive advantage, we need to know if they have access to any proprietary datasets. Without some delicious big data to feed your algorithms with, they won’t learn anything. Without some big data, you will only be able to accomplish what traditional software will accomplish. Without proprietary big data sets, you will not be able to retain a competitive advantage now that half the world is using AI.
Berlin-based AI incubator Merantix has somewhere around 700 ideas they’re trying to tackle using machine learning. Not all ideas can add exponential value. In order to create exponential returns, you need to add exponential value. When many people hear about the power of machine learning, they wonder if it can be applied to stock trading. If Google’s deep learning algorithms can now beat a game that has more possible moves than atoms in the known universe, then what’s stopping us from unleashing it upon the stock market and making millions?
Using Machine Learning for Stock Trading
The idea of using computers to trade stocks is hardly new. Algorithmic trading (also known as algo trading or black box trading which is a subset of algo trading) has been around for well over a decade and rapidly gaining in popularity. Here’s a look at algorithmic trading as a percentage of market volume:
If that trend continues, then this means that today upwards of 90% of trading is being conducted by computer programs. One thing to notice about algorithmic trading is that it has been moving in the direction of shorter and shorter holding times. High-frequency trading (HFT) is a subset of algorithmic trading in which stocks are bought and then sold in fractions of a second. This strategy is a form of arbitrage in which the HFT algorithm spots a price discrepancy and then quickly capitalizes on it. As you would expect, HFT trading profits are becoming smaller and smaller but the volume of trades are still dominating the overall market:
Now that we know about algorithmic trading and HFT, just how does machine learning or deep learning come into play? To answer this question, the important variable to take into account is duration. While HFT and algo trading perform trades of a short duration, it becomes much more difficult to “capture alpha” when you start increasing the time frame. The reality is that some of the world’s biggest hedge funds are already all over this space and have been capturing alpha across many durations for a long time now using machine learning.
Hedge Funds and AI For Stock Trading
In 2015, Bridgewater Associates which has $150 billion in assets under management (AUM) started a new artificial intelligence unit led by David Ferrucci who led the development of IBM’s Watson. After working at IBM for 17 years, he was poached by Bridgewater in 2012.
Another firm called Renaissance Technologies has $65 billion in AUM and is said to have “the best physics and mathematics department in the world”. The Medallion Fund at Renaissance, run mostly for employees of the company, has one of the best records in investing history having returned +35% annualized over 20 years. The two co-CEOs of Renaissance were both hired from IBM Research in 1993 where they were working on language-recognition programs.
With $32 billion under management, Two Sigma Investments is known for using AI and machine learning as a key part of their strategy. One co-founder did his PhD in artificial intelligence at MIT and the other was an International Mathematical Olympiad Silver Medalist. Being a finance professional is not a requirement to work at this firm.
While hedge funds such as these three are pioneers of using machine learning for stock trading strategies, there are some startups playing in this space as well. Binatix is a deep learning trading firm that came out of stealth mode in 2014 and claims to be nicely profitable having used their strategy for well over three years. Aidyia is a Hong Kong-based hedge fund launched in 2015 that trades in U.S. equities and makes all stock trades using artificial intelligence with no human intervention required. Sentient, another deep learning company we discussed before, has developed an artificial intelligence trader that was successful enough that they are considering spinning it out as a prop trading company or asset management firm.
If there’s a startup that shows promise in this space, you can bet that the three well-established hedge funds we discussed know about it. If you had a machine learning algorithm that generated alpha, would you tell the world about it? Most likely not. But then how would you raise the capital needed to make some serious money off of your strategy? Firms like Bridgewater can be as nimble as any startup and at the same time have $150 billion in capital to play with. It’s hard to compete if you’re a startup that’s trying to get funded. If you’re looking for investors, you have to disclose what you’re doing. Word travels fast. It’s not hard to see hedge funds like Bridgewater poaching talent from AI startups that are trying to play in this space and quickly finding out what they’re up to.
Next we come to retail investors – your average mom and pop investor. If you have a PhD in some specialized area of machine learning and you want to build a trading program, that’s one thing. As for your average Joe retail investor, forget about it. Any company out there trying to peddle you some platform claiming to use machine learning that will make you a better trader does not have your best interests in mind.
AI Stock Trading for Retail Investors
We’re going to tell you what every investment professional knows but nobody selling trading programs will. If you are a professional trader, you cannot generate alpha for very long without someone else stepping in and eroding whatever information advantage you had. Trading is an exceptionally difficult way to make money, and the vast majority who go down that path lose all their capital. There is no such thing as some magical AI trading program that’s been developed for decades which will give you some advantage over the market. As soon as someone tells you that, walk away. Unfortunately, not everyone understands this. Here’s a real-world example of what pitfalls await those who think that an AI-enabled trading strategy sold to anyone with a credit card is the missing link to financial independence.
VantagePoint AI Trading Software
There’s a newsletter we subscribe to called “The Hustle,” and over 1 million readers subscribe to it for “bold business and tech news” which filters out all the noise and gives you the most impactful headlines. They’ve since become less interesting with their “what our staff likes to eat at Taco Bell” discussions where Gwyneth from HR chimes in about how she prefers two tacos hold the lettuce and everyone has a good chuckle. Riveting stuff, and clearly more entertaining for the staff than the readers. Gwyneth’s Taco Bell preferences aside, what we found most disturbing in The Hustle was the below ad they recently featured:
We understand the need to sell ad space, but you have a responsibility to vet what you advertise before choosing to represent firms that may not have the best interest of your readers in mind. Sure, you can’t control what Google ads display, but you can choose not to advertise something in your newsletter that is not good for your readers. On the surface, VantagePoint appears interesting enough. They’re using AI to interpret market data and produce technical indicators that can provide a trading signal. (Technical analysis has been around for decades. An algorithmic trading strategy based on historical data is nothing new.)
We could smell the cow manure emanating from this ad, so we went to the VantagePoint website and signed up for a “free demo.” The cacophony of unorganized sales emails that followed wasn’t what concerned us most, nor was it their incessant attempt at touting their use of “AI.” (The company refers to itself as “VantagePoint AI,” and the fellow we spoke with was a “Senior AI Expert.”) What concerned us most was the business model they’ve adopted to sell their trading software.
The first sales call we received was an attempt to qualify us as a lead by finding out what investment strategy we preferred and how much capital we had to use with their trading program. Fair enough. We asked some questions about proprietary data which they don’t have. (They’re using market data they source from a sole provider and you will only pay $35 a month to access that data.) In other words, they’re using data that everyone else on this planet has access to. The biggest problem we had was with their business model which involves “lifetime subscriptions” with ludicrous price points.
Remember, we told the VantagePoint Senior AI Expert that we had $10,000 in capital. At these price points, we’d have exhausted one-fifth of our money just to get access to a single sector’s worth of access on this platform. In their mind, they saw nothing wrong with that. “You’ll make it back to cover the costs,” says the AI expert who just got done telling us that 90% of traders go broke, and who acknowledged on the call that our undercover MBA had no experience in trading. Anyone with a modicum of common sense would have a huge problem with paying for a “lifetime license” which doesn’t give the provider any incentive to give you excellent support or provide upgrades to the software once you’ve paid. (You do need to pay for upgrades as well. What world do these people live in exactly?)
The people over at The Hustle who subjected one million readers to this tripe should be
taken out back and shot forced to sit through one of VantagePoint’s free demos and then deal with the barrage of sales pitches that follow. Do not go down this path people. Some of the most intelligent people on this planet, educated at the world’s top financial institutions, can’t become successful traders. Don’t think you’ll fare any better with a lifetime subscription to VantagePoint’s AI trading software.
For retail investors to take advantage of machine learning for stock trading, you have a couple of directions to take. For ultra-high net worth retail investors, you can invest your money in a hedge fund that uses AI like Bridgewater or Renaissance. For those of us who don’t have such large amounts of capital laying around, we can wait for deep learning companies like Sentient to go public or be acquired and then invest in those vehicles. Whatever you do, don’t be drawn in by any purveyors of “AI stock trading programs” who want you to spend thousands of dollars on lifetime licenses to become financially independent.
Here at Nanalyze, we complement our tech investments with a portfolio of 30 dividend growth stocks that pay us increasing income every year. Find out which ones in the Quantigence report freely available to Nanalyze subscribers.