TY - JOUR

T1 - The Promises and Pitfalls of Machine Learning for Predicting Stock Returns

AU - Leung, Edward

AU - Lohre, Harald

AU - Mischlich, David

AU - Shea, Yifei

AU - Stroh, Maximilian

PY - 2021/5/3

Y1 - 2021/5/3

N2 - Recent research suggests that machine learning models dominate traditional linear models in predicting cross-sectional stock returns. The authors 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, the authors 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.

AB - Recent research suggests that machine learning models dominate traditional linear models in predicting cross-sectional stock returns. The authors 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, the authors 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.

KW - Security analysis and valuation

KW - machine learning

KW - big data

KW - factor investing

U2 - 10.3905/jfds.2021.1.062

DO - 10.3905/jfds.2021.1.062

M3 - Journal article

VL - 3

SP - 21

EP - 50

JO - Journal of Financial Data Science

JF - Journal of Financial Data Science

SN - 2640-3943

IS - 2

ER -