Machine Learning and The Cross-Section of Emerging Market Stock Returns

93 Pages Posted: 29 Nov 2022 Last revised: 15 Mar 2023

See all articles by Matthias X. Hanauer

Matthias X. Hanauer

Technische Universität München (TUM); Robeco Asset Management

Tobias Kalsbach

Technische Universität München (TUM)

Date Written: March 13, 2023


This paper compares various machine learning models to predict the cross-section of emerging market stock returns. We document that allowing for non-linearities and interactions leads to economically and statistically superior out-of-sample returns compared to traditional linear models. Although we find that both linear and machine learning models show higher predictability for stocks associated with higher limits to arbitrage, we also show that this effect is less pronounced for non-linear models. Furthermore, significant net returns can be achieved when accounting for transaction costs, short-selling constraints, and limiting our investment universe to big stocks only.

Keywords: Machine Learning, Return Prediction, Cross-Section of Stock Returns, Emerging Markets, Random Forest, Gradient Boosting, Neural Networks

JEL Classification: C14, C52, C58, G11, G12, G14, G15, G17

Suggested Citation

Hanauer, Matthias Xaver and Kalsbach, Tobias, Machine Learning and The Cross-Section of Emerging Market Stock Returns (March 13, 2023). Emerging Markets Review, Forthcoming, Available at SSRN: or

Matthias Xaver Hanauer (Contact Author)

Technische Universität München (TUM) ( email )

Arcisstr. 21
Munich, D-80290


Robeco Asset Management ( email )

Weena 850
Rotterdam, 3014 DA


Tobias Kalsbach

Technische Universität München (TUM) ( email )

Arcisstrasse 21
Munich, DE 80333

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

Paper statistics

Abstract Views
PlumX Metrics