Machine Learning Goes Global: Cross-Sectional Return Predictability in International Stock Markets

54 Pages Posted: 28 Jun 2022 Last revised: 16 Mar 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; University of Cape Town

Date Written: June 20, 2022

Abstract

We examine return predictability with machine learning in 46 stock markets around the world. We calculate 148 firm characteristics and use them to feed a repertoire of different models. The algorithms extract predictability mainly from simple yet popular factor types—such as momentum, reversal, value, and size. All individual models generate substantial economic gains; however, combining them proves particularly effective. Despite the overall robustness, the machine learning performance depends heavily on firm size and availability of recent information. Furthermore, it varies internationally along two critical dimensions: the number of listed firms in the market and the average idiosyncratic risk limiting arbitrage.

Keywords: machine learning, return predictability, international stock markets, the cross-section of stock returns, forecast combination, asset pricing, firm size

JEL Classification: C52, G10, G12, G15

Suggested Citation

Cakici, Nusret and Fieberg, Christian and Metko, Daniel and Zaremba, Adam, Machine Learning Goes Global: Cross-Sectional Return Predictability in International Stock Markets (June 20, 2022). Available at SSRN: https://ssrn.com/abstract=4141663 or http://dx.doi.org/10.2139/ssrn.4141663

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

University of Cape Town

Cape Town
South Africa

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
1,426
Abstract Views
3,924
Rank
25,182
PlumX Metrics