Entering text into the input field will update the search result below

How Systematic, Algorithmic Trading Impacts Stocks, And How To Benefit From This Understanding

Aug. 22, 2017 3:37 PM ET9 Comments
Mark H. Melin profile picture
Mark H. Melin


  • Systematic and algorithmic strategies are increasingly moving markets and individual stocks.
  • Investors can benefit from recognizing how algorithms might be looking at individual named issues.
  • The "beta market environment" method of analysis considers how technical price conditions impact markets and individual stocks by looking at price persistence, volatility , and mean divergence/convergence.

Algorithms and rule-based systematic trading systems have gone from representing near 30% of the market to now dominating where only 10% of those influencing the supply and demand balance decisions are “fundamental discretionary traders,” JPMorgan (JPM) head of quantitative and derivatives research Marko Kolanovic pronounced recently. In a June 2017 research note to clients, he said such trading is undoubtedly influencing the price of given securities. In fact, he attributed the June 9 and 12 sell-off in technology stocks to computer-based algorithms receiving sell signals.

How a computer algorithm views stocks is perhaps one of the most important factors driving a stock price today, but few people have any clue how it works, what algorithms think about their stocks, and why a stock may be moving up or down in price absent fundamental news.

That is about to change.

The goal of this series of articles is to illuminate to various degrees how certain algorithms might view individually named equities. We not only consider technical market factors but also connect dots with fundamental economic forces that influence algorithms more than is generally recognized.

Accomplishing the goal of providing a concise analysis of how literally billions of lines of code might think is no easy task to be sure. An argument can be made that each algorithm has its own set of characteristics, market proclivities, and idiosyncratic execution triggers that make condensing an outlook more than challenging, some might say impossible.

While the argument that each algorithm is unique in its own right has significant merit, I tend to disagree that a general consensus view cannot be developed. While it is a difficult task, it is not impossible.

As someone who has studied various systematic trading strategies, developed professional trading programs for use in a hedge fund setting, written or contributed to four

This article was written by

Mark H. Melin profile picture
Mark Melin is a leading expert at NonCorrelated investing. He has taught managed futures at Northwestern University executive education program and has written, edited or contributed to four books, including High Performance Managed Futures (Wiley 2010) and The Chicago Board of Trade’s Handbook of Futures and Options (McGraw-Hill 2008) Mark is a journalist covering hedge funds for ValueWalk.com. Follow him on Twitter @MarkMelin

Analyst’s Disclosure: I/we have no positions in any stocks mentioned, and no plans to initiate any positions within the next 72 hours. I wrote this article myself, and it expresses my own opinions. I am not receiving compensation for it. I have no business relationship with any company whose stock is mentioned in this article.

Seeking Alpha's Disclosure: Past performance is no guarantee of future results. No recommendation or advice is being given as to whether any investment is suitable for a particular investor. Any views or opinions expressed above may not reflect those of Seeking Alpha as a whole. Seeking Alpha is not a licensed securities dealer, broker or US investment adviser or investment bank. Our analysts are third party authors that include both professional investors and individual investors who may not be licensed or certified by any institute or regulatory body.

Recommended For You

Comments (9)

Curious1955 profile picture
Thank you for a very interesting article. Will enjoy going through your references too.
Thomas Hoffman, CFA profile picture
Thanks for the article and all the references which will keep me busy for awhile. Look forward to the next.
Edmond Overbey profile picture
@Professor Mellin- Thanks for a thoughtful, well researched article. Forgive me if I am oversimplifying. 1. Seems this information is most helpful to traders. Thus the buy and hold crowd will pay more attention to fundamentals and beat the technical analysis by basing their decisions on value. 2. Aren't these strategies, or derivatives of strategies, that have been employed for years, and what's new is a few algorithms are applying these strategies now rather than thousands of technical analysts applying them in days of yore? I.e., what has changed is that these strategies are being applied in nanoseconds rather than minutes.

Please don't misunderstand. Getting up to date explanations of these strategies from such a knowledgeable source is of tremendous value to all of your readers.
Mark H. Melin profile picture
These are good points. I primarily look at the impact on a mid-term time horizon. With the predominance of algos moving markets, this is a factor that all investors should at least be aware of. I'm writing an analysis of Disney stock right now and you will see some of your questions are addressed. Essentially, the valuation metrics used in fundamental analysis apply with algos, but they do so with a twist. For instance, they look at the trend of Price / Earnings and Free Cash flow as an indicator in some cases. In the case of Disney, P/E trend gave a sell signal before the announcement, just as did relative value analysis.

Thank you for your well thought out comments.
The more they computerize their Trading Systems, the more chances they will benefit long-only traders and investors.

Some of the expert and master traders I've undergone training in the previous decade were the early pioneers in computerizing their Trading Systems now called Computerized Trading Systems or Platforms.

Mostly for intraday scalps and short-term trading such as daytrades that can last a few to several days of hold, and a few swing strategies that usually hold positions for several weeks. Including a few who dabbled writing rudimentary arbitrage routines that the big-boy HFTs now dominate. Of course they were no match to previous generations of mainframes and minis programed to trade the markets automatically.

Most of the trading systems are designed for Trend Trading we fondly call BTFD these days. Few would program for shorts since it is far too easy to wipe out capital with just few mistakes going that route.

And that's where long only medium-term and long-term traders, where using a computerized trading system is an overkill; benefits from short-term Computerized Trading Systems who kept trend trading the markets.

Including buy and hold investors of course.


For myself, the more I use even the very basic type of short-term bottom fishing strategies; the more my trades become less whipsawy in recent years. I don't know if it's my skills getting better in identifying which methods have higher probability or not. But more likely because more and more short-term bottom fishing setups are being computerized resulting in more synchronized and better precision bottom entries now hard-coded into those CTS'es.

- Forget about Highfalutin Machine Learning and AI.

There are already several dozens, if not hundreds, of High-Probability Trade Setups learned by highly intelligent expert and master traders through the decades, including the ones developed before computers were invented.

For us mere mortals with limited capital; better to just utilize most efficiently those setups and strategies that just keep on working most effectively for decades and decades and decades. Rather than experiment with the exotic (aka toxic) unknowns that may take decades more before artificial intelligence has the chance to become highly profitable.

- They are profitable for Science Fiction Journalists.

Kasparov, by studying the routine moves of computerized chess, was finally able to beat Deep Blue --> simply because computerized intelligence is not as good as the human brain.

Good luck.
@Mark, thank you for your Herculean effort to write such a well contained article with excellent references.

Could you give us a quantitative estimate of how much these algos can possibly more the market in % terms in any one day?

This may tell us more about their true impact. I would be surprised if it was more than 2% but if you have any evidence to that I will be happily and impartially read it.

And another question. Which asset classes are the most common fishing grounds for those algos and why is that? Perhaps since we cannot beat them, we can avoid them maybe?

Thanks and keep up the good work!
Mark H. Melin profile picture
The first question you ask is the topic of much debate. I was attending a CFA luncheon where a Vanguard representative claimed that passive represents no than 10% of average daily stock volume, while JPMorgan says near 80%. I've spoken to HFT & CTA practioners who say it is somewhere inbetween, but near the high end.

It is difficult to discern regarding markets traded, as HFT are not required to register and report their positions. Traditionally commodity and derivatives markets were the breeding ground, but over the past year, in my estimation, stocks have become fertile breeding ground.

I would say don't avoid the markets because of algos because you can't. Understand them is better. I'm finishing up my first analysis of Disney, you will see that algos in many cases consider some of the same variables as a value investor, but do so with a systematic overlay.

Hope that helps.
Mark H. Melin profile picture
Good questions.
First, don't let those involved in creating algo strategies intimidate you. It is not uncommon for me to see intentional obfuscation in public so they cannot be understood but then talk in private in a language that fundamental portfolio managers understand. This is the language I will use. I am a mortal and speak to fellow mortals.
In regards to your second question, it is not an exact science determining which factors are most significant and which are not for two reasons: the study of beta market environments is in a very early stage and there are too many variables to give a simple answer. As a broad generalization, when certain algorithmic signals align it has much more significant meaning than when they are independent.
Algos can update logic in real time, this is the "promise" of machine learning. I've communicated to many of the top funds in this regard, including Two Sigma, who tell me that concept is not entirely operational. While they haven't generated positive returns yet, they are learning quite a bit. You might find this interesting:

The next article is going to be an analysis of Disney stock. It looks to me like the algo signals were moving in advance of the Netflix announcement.

Thx for your comments.
cyrano13 profile picture
Thank you for trying to educate us mortals who trade with limited resources.
At the risk of being naive, a couple of questions:
is it really possible to determine which factors are always significant,and which are not

Do algo's update logic in real time from data feeds that monitor, volume, social media,
dark pools, ETF's, short interest geo-political news, etc.

Looking forward to your next post
Disagree with this article? Submit your own. To report a factual error in this article, . Your feedback matters to us!

Related Analysis

To ensure this doesn’t happen in the future, please enable Javascript and cookies in your browser.
Is this happening to you frequently? Please report it on our feedback forum.
If you have an ad-blocker enabled you may be blocked from proceeding. Please disable your ad-blocker and refresh.