Predicting Returns with Machine Learning Across Horizons, Firms Size, and Time

Journal of Financial Data Science, Forthcoming

29 Pages Posted: 28 Aug 2023

See all articles by Nusret Cakici

Nusret Cakici

Fordham university

Christian Fieberg

City University of Applied Sciences

Daniel Metko

University of Bremen

Adam Zaremba

Montpellier Business School; Poznan University of Economics and Business

Date Written: August 18, 2023

Abstract

Researchers and practitioners hope that machine learning strategies will deliver better performance than traditional methods. But do they? This study documents that stock return predictability with machine learning depends critically on three dimensions: forecast horizon, firm size, and time. It works well for short-term returns, small firms, and early historical data; however, it disappoints in opposite cases. Consequently, annual return forecasts have failed to produce substantial economic gains within most of the U.S. market in the last two decades. These findings challenge the practical utility of predicting returns with machine learning models.

Keywords: machine learning, return predictability, the cross-section of stock returns, asset pricing, firm size, equity anomalies, long-short portfolios, long-run returns

JEL Classification: C52, G10, G12, G15

Suggested Citation

Cakici, Nusret and Fieberg, Christian and Metko, Daniel and Zaremba, Adam, Predicting Returns with Machine Learning Across Horizons, Firms Size, and Time (August 18, 2023). Journal of Financial Data Science, Forthcoming, Available at SSRN: https://ssrn.com/abstract=4552395

Nusret Cakici

Fordham university ( email )

113 West 60th Street
New York, NY 10023
United States
2017473227 (Phone)
07446 (Fax)

Christian Fieberg

City University of Applied Sciences ( email )

Werderstr. 73
Bremen, DE Bremen 28199
Germany

Daniel Metko

University of Bremen ( email )

Max-von-Laue-Straße 1
Bremen, DE 28359
Germany

HOME PAGE: http://www.fiwi.uni-bremen.de

Adam Zaremba (Contact Author)

Montpellier Business School ( email )

2300 Avenue des Moulins
Montpellier, Occitanie 34000
France

HOME PAGE: http://sites.google.com/view/adamzaremba

Poznan University of Economics and Business ( email )

al. Niepodległości 10
Poznań, 61-875
Poland

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
205
Abstract Views
574
Rank
247,763
PlumX Metrics