The Promises and Pitfalls of Machine Learning for Predicting Stock Returns

Abstract

Recent research suggests that machine learning models dominate traditional linear models in predicting cross-sectional stock returns. We confirm this finding when predicting one-month forward-looking returns based on a set of common stock characteristics, including predictors such as short-term reversal. Despite the statistical advantage of machine learning model predictions, we demonstrate that the economic gains tend to be more limited, and critically dependent on the ability to take risk and implement trades efficiently. Unlike traditional models, machine learning models have been somewhat more effective over the past decade at discerning valuable predictions from cross-sectional equity characteristics.

Keywords: Machine Learning, Data Science, Interpretable Machine Learning, Return Prediction, Cross-Section of Stock Returns, Gradient Boosting, Factor Investing

JEL Classification: G11, G12, G14, G15, G17