How to Choose the Best Machine Learning Technique Posted on : Nov 23 - 2022

While the comparison table in this article applies to a specific problem in FinTech, the conclusions are consistent with findings in other frameworks. There is no single method that outperforms all the other ones, for obvious reasons. To be the global winner means winning on all potential datasets. The immense majority of datasets are pure noise, for which performance is meaningless, and the winner randomly changes from one dataset to another. Yet, in real-life applications, each dataset comes with patterns or meaningful signal. There are strategies that on average, do better. The purpose of this article is to explore what works best. However the winning methods depend to a large extent on the type of problem being studied. It is easier to to rule out methods that are consistently underperforming.

The conclusions here are based on the book “Big Data and AI Strategies: Machine Learning and Alternative Data”, published by JP Morgan Chase and available (for free) here. In particular, Table 1 is a re-organized version of the one shown page 117 in that book.

Overview

The 22 methods listed in Table 1 were used in daily trading of energy stocks (more precisely, indexes combining many stocks) over a long period of time. The methods are ranked according to the Sharpe ratio. This metric measures the performance of an investment portfolio compared to a risk-free asset, after adjusting for its risk. It is defined as the difference between the returns of the investment and the risk-free return, divided by the standard deviation of the investment returns. View More