Home > Research > Publications & Outputs > The Promises and Pitfalls of Machine Learning f...


Text available via DOI:

View graph of relations

The Promises and Pitfalls of Machine Learning for Predicting Stock Returns

Research output: Contribution to Journal/MagazineJournal articlepeer-review

  • Edward Leung
  • Harald Lohre
  • David Mischlich
  • Yifei Shea
  • Maximilian Stroh
<mark>Journal publication date</mark>3/05/2021
<mark>Journal</mark>Journal of Financial Data Science
Issue number2
Number of pages30
Pages (from-to)21-50
Publication StatusPublished
<mark>Original language</mark>English


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.