I am a staunch advocate of systematic or rule-based strategies and humans excel at pattern recognition, which would seem to give us an advantage in developing these types of strategies. Unfortunately, we might be a little too proficient. We tend to see patters that are not really there. Psychologists have a name for this affliction; they call it pareidolia. It turns out that rats and pigeons do not suffer from pareidolia, which allowed them to beat us handily in a recent decision-making study. This flaw has significant implications for trading.
Rats and Pigeons
I heard about this issue in one of the Great Courses lecture series titled "Big Data: How Data Analytics is Transforming the World" by professor Tim Chartier of Davidson College. I am not affiliated with the Great Courses, but I highly recommend them to anyone looking to expand their knowledge. I watch one of the lectures every morning during my workout and they cover a wide range of subjects: math, history, science, psychology, religion, etc. The courses are taught by some of the top university professors in the country and I always look for insights that can be applied to trading.
In his lecture on pattern recognition, Professor Chartier explained how rats and pigeons were able to get the best of us. The researchers designed a simple experiment where the roll of a single six-sided die was used to determine one of two outcomes. A roll of one resulted in a red light signal and a roll of 2-6 resulted in a green light signal. The resulting rolls were random, but in a large sample, 83% of the light signals would be green and 17% would be red.
The rats and pigeons were rewarded with food for every correct guess. In other words, if they pushed a green button and a green light appeared, the received a food reward. If they pushed the green button and a red light appeared, they received no reward. The methodology (including the random sampling technique) was explained to the human participants (and presumably to the rats and pigeons in the interest of fairness) and the experiment was conducted.
The rats and pigeons pushed their buttons and observed the light signals and correctly deduced that the green light came on more frequently than the red light. So what did they do? They pushed the green button every time and they were correct 83% of the time, which meant they also received the food reward 83% of the time.
What about the human participants? We scored a dismal 68% and were soundly defeated by the rats and the pigeons. Even though the human subjects were told the signals were randomly generated, they could not help themselves. When the green light came on 12 times in a row, they were convinced the next light had to be red. Unfortunately, a random process has no memory. The probability of the next green light was still 83%. Assigning memory to a random process is called the gamblers fallacy and it built the cities of Las Vegas and Atlantic City.
Fortunately, unlike random dice rolls, there are identifiable and repeatable patterns in the market. However, identifying patterns is not enough. Those patterns must be tested using historical data AND there must be a premise or reason the pattern exists and will persist in the future. Many researchers ignore this requirement.
Data mining will uncover countless instances of correlation, but we are looking for causation: a reason behind the pattern that will cause it to be repeated in the future. Often these reasons exploit behavioral deficiencies in human reasoning and adverse psychological influences like fear and greed. The next time you see a pattern in market data, make sure you can identify the cause of the pattern and make sure to test it with historical data.
Print and Kindle Versions of Brian Johnson's New Book are Now Both Available on Amazon (Nineteen 5-Star Reviews)
Trader Edge Strategy E-Subscription Now Available: 20% ROR
The Trader Edge Asset Allocation Rotational (AAR) Strategy is a conservative, long-only, asset allocation strategy that rotates monthly among five large asset classes. The AAR strategy has generated approximately 20% annual returns over the combined back and forward test period (1/1/1990 to 7/29/2013). Please use the above link to learn more about the AAR strategy.
Your comments, feedback, and questions are always welcome and appreciated. Please use the comment section at the bottom of this page or send me an email.
If you found the information on www.TraderEdge.Net helpful, please pass along the link to your friends and colleagues or share the link with your social network.
The "Share / Save" button below contains links to all major social networks. If you do not see your social network listed, use the down-arrow to access the entire list of social networking sites.
Thank you for your support.
Copyright 2014 - Trading Insights, LLC - All Rights Reserved.