The Shortcomings of Neural Networks for Trading Predictions

As someone who is devoting a large-portion of their senior year (and very likely time beyond that) to researching potential applications of deep learning in trading, I wasn’t thrilled to learn about the recent shortcomings of quantitative traders. Let’s begin with Marcos López de Prado, a frequently cited algorithmic trader who recently  published Advances in Financial Machine Learning. One thing that De Prado talks about is the idea of ‘red-herring patterns’ that are extrapolated by machine learning algorithms. These types of algorithms are, by design, created to analyze large bodies of data and identify patterns within this data. In fact, this idea of noticing patterns is one of the main assumptions I am basing my work on (using Word2Vec embeddings to identify past financial patterns and apply them to real-time data for more accurate predictions). But, what happens when these algorithms identify patterns that aren’t real? An aggressive neural network (In my case: One which adjusts vector weights heavily while learning from data) is prone to make these types of mistakes. Think of this example: A stock happens to go up a couple percent points every Thursday for three weeks in a row. A (poorly written) neural network would deduce that every Thursday in the future, this stock would go up by at least a percent point or two. Now, this is easily avoidable by training a trading algorithm on larger sets of data, but even large data sets are prone to these types of red-herrings. Once a trading algorithm clings on to a pattern, it could backfire horribly when that pattern eventually breaks.
This brings the idea of Black Swans into light. The theory of Black Swans was popularized by Nasim Taleb in his accurately-titled book The Black Swan: The Impact of the Highly Improbable. The general gist of this theory is that the most profoundly impactful events oftentimes are the ones we least expect, due to our fallacious tendencies in analyzing statistics (I will go into more detail on these topics and more in a future blog post, once I am done reading the whole book). Taleb argues that one of our biggest shortcomings in analyzing data is creating ‘false narratives’, which are more convenient and easier to sell to clients. These false narratives oftentimes omit crucial data (silent data), which backfires once the narrative breaks.
But, on the other end, a more passive neural network (one which more slightly adjusts vector weights) can sometimes come to no meaningful conclusions, which means wasted time and computational energy. I want to create a Word2Vec model which can detect patterns, but I also don’t want it to actively follow patterns with no longevity.
So, what does one do? How aggressive/passive should I make my Word2Vec neural network? 

Another theory which I encountered over the weekend is the idea of survivorship bias. In training neural networks, how do we treat data from companies which have failed? If we are analyzing the stock price data for various important stocks over time, what do we with data from once-important stocks which are now defunct, such as Lehman Brothers? I initially thought it would be best to throw this data out, since it is no longer applicable, but it turns out this strategy can have negative consequences. If we only train our network on stocks which have survived, then we will miss out on crucial data about when stocks go bankrupt. So, how do we properly treat this type of data?


All of these seemingly insignificant flaws in trading algorithms can evoke catastrophic mistakes. This concept is synthesized by quantitative investment officer Nigol Koulajian, saying: “You can have one little pindrop that can basically make you lose over 20 years of returns.” This ‘little pindrop’ which Koulajian mentions is the eventual divergence from the false patterns identified by neural networks. I personally think it would take more than a little pindrop to erase 20 years of returns, but the idea still stands. So, this warrants the question, how do we avoid the little pindrop? My (far-fetched?) theory is that you can use neural networks to estimate worst-case scenarios int the same way they are designed to estimate best-case scenarios, and then work to avoid this.
In broader terms, Bloomberg reports that the Eureka Hedge Fund Index, which tracks the returns of hedge funds which are known for using machine learning, has under performed yearly compared to the S&P 500. The harsh truth (right now) is that simply investing in the S&P500 will return ~13% yearly, while machine-learning based hedge funds return ~9% yearly.
Eureka Hedge Fund Index
(The keen observer will notice that despite all the noise, the index has been steadily going up over the past 7 years)
These are some of the questions I ask those few who read what I am writing, and are the types of questions I will ask through my personal research interviews (Good News! I have my first interview scheduled this upcoming Tuesday, and, interviewee permitting, I will post a summary of our talk later in the week).
In my personal opinion, the recent under performance of trading algorithms in general is not a bad sign. This is still a relatively new field, meaning that more research needs to be done and new discoveries need to be made. I think of it this way: If trading algorithms are working perfectly, then what’s the point of a newcomer (like me) coming in and doing research on them? If it ain’t broke, don’t fix it.

The Falling of the Giants: Why McDonald’s Death is Inevitable

For almost the entirety of its long lived reign over the makers of cheap food, McDonald’s has lived on the premise that it is a friendly place where you can stop by to grab some tasty, inexpensive food all while losing no more than five minutes of your time. It may not seem like the most innovative or groundbreaking idea of all time, but through relentless advertising and shameless lying, the company managed to make itself the most recognized brand in the entire world for half of a century.
However, as the times began to change and the number of vegetarians, vegans, and animal activists began to skyrocket, McDonald’s began to face a new obstacle. By the year 2000, most people were aware of the negative health-effects of consuming glorious items such as the McRib, Shamrock Shake, and other fine concoctions served up under the golden arches. This wave of hate towards the company only got worse after the Blockbuster movie “Supersize Me” was released and was shown to children in schools all around the nation.
At this point in time, McDonald’s realized that it was basically futile to give any attempt to restore their image, so they gravitated towards a different approach. It had now become obvious to the firm that the only positive aspect of their “food” products was their inexpensive price. So, logically, the advertising team at the fast food chain decided to start targeting low-income families. This tactic proved to be effective, especially in the years following the crash of 2008.
Effective, but not abiding:

That’s a dismal chart, and the impacts have been severe. 
Yes, McDonald’s is still a giant by all means. With over 14,000 stores in the U.S alone, the fast food chain is one of the largest in the world. But, in a time where Wall Street bankers are greedier than ever, size is no longer a factor if your profits aren’t increasing every single quarter. If McDonald’s doesn’t think of something ingenious soon, then they will start to feel the impact of their stagnating profits.
In my opinion, the company really is stuck. Think about it for a minute: If they try to conform to the rest of the healthy-eating society, they won’t last because nobody would go to McDonald’s to eat a salad. If they continue with their old ways, then they will keep customers who only go there for a cheap bite to eat, but then will gradually begin to lose these loyal clients following the same trend that is currently taking place.
However, it seems like Wall Street doesn’t agree with my opinion, as the McDonalds stock hasn’t really taken notice of the persisting downward trend in the company’s same-store sales.

The Land of Distractions

“The oppression of the poor must establish the monopoly of the rich. Profit or income inequality are always highest in countries which are going fastest to ruin.”
-Adam Smith

This quote, which was spoken over 200 years ago, still seems oddly relevant today. With wealth disparity increasing and labor force participation rates dropping, it becomes evident that we are currently riding on a one-way trip towards calamity. Or we should be.
One would expect that in such a time, a time of historical injustice and senselessness, the streets of rich neighborhoods would be flooded with angry mobs of mistreated lower-class workers fighting for closure. But it appears that this isn’t the case. In fact, the past few years have not only been devoid of uprising and aspiration to change, but it seems as if nobody thinks that something is wrong.
This begs the obvious question of “Why?” Why are we so oblivious to what is clearly happening right in front of our eyes? It would be reasonable to think that those who live in a country that only cares about money would also be inclined to be well-informed about the occurrences in the world of finance. In addition, the information is accessible to everyone, on finance blogs, statistics charts, and online news headlines.
But, the more time you spend on the internet trying to find new, helpful information, the more evident the problem becomes.
It is basically impossible to go on the internet nowadays without getting hit by a barrage of ads and seemingly interesting links. Want to check the latest stock news? Well, you’ll have to wade through all of the grilled cheese tutorial videos and Kylie Jenner life-updates first. So, we have all the information in the world at our disposal, but all of this information is hidden behind a wall of carefully placed distractions.
This is yet another one of the many remarkable aspects about America that makes it such a fascinating country; It provides its citizens with an abundance of information from which enough knowledge can be acquired to get a graduate degree in any field, but strongly supports systems whose sole purpose is to divert the user’s attention away from this information. It’s shocking, but not necessarily aimless. To me, this all seems like a clever way to distinguish the future 1% and the other 99%. The few who understand this will strive to benefit as much as possible from the plethora of free information that is provided to them, while ignoring the common distractions and frivolous topics that are so highly praised in mainstream media. On the other end of the spectrum lay those who avoid experimenting with obscure subjects, such as investing and macroeconomics, because it is unpopular with the crowd.