Practical Applications of Be Wary of Black-Box Trading Algorithms

Practical Applications Summary

In Be Wary of Black-Box Trading Algorithms, from the August 2019 issue of The Journal of Investing, Gary Smith of Pomona College argues that investors should not blindly trust trading algorithms, especially those that are totally opaque. The growing trend of relying on artificial intelligence to conduct trading activities is ill advised, he warns, because computer “intelligence” is very different from human intelligence. Although computers are excellent at detecting statistical relationships, they are terrible at evaluating the merit of those relationships.

Smith urges investors to continue to rely on human judgment to evaluate correlations discovered by trading algorithms. Those judgments must be based on sound theory, Smith says, since even the most highly correlated trading models will fail to predict future performance without a solid theoretical basis. He provides an example of a simple model discovered by a multiple regression algorithm that correlated strongly with 2016 data but diverged sharply from 2017 data. This example provides evidence for the dangers of pursuing trading models based purely on data rather than logic or reliable theory.