Uncovering Sparsity and Heterogeneity in Firm-Level Return Predictability Using Machine Learning

Journal of Financial and Quantitative Analysis, forthcoming

71 Pages Posted: 25 May 2020 Last revised: 21 Feb 2023

Date Written: April 26, 2022

Abstract

We develop an approach that combines the estimation of monthly firm-level expected returns with an assignment of firms to (possibly) latent groups, both based upon observable characteristics, using machine learning principles with linear models. The best performing methods are flexible two-stage sparse models that capture group-membership predictive relationships. Portfolios formed to exploit such group-varying predictions based on a parsimonious set of characteristics deliver economically meaningful returns with low turnover. We propose statistical tests based on nonparametric bootstrapping for our results, and detail how different characteristics may matter for different groups of firms, making comparisons to the existing literature.

Keywords: Characteristics, Sparsity, Heterogeneity, Industries, Lasso, Clustering, Return Prediction, Big Data

JEL Classification: G1, G17, C55, C58

Suggested Citation

Evgeniou, Theodoros and Guecioueur, Ahmed and Prieto, Rodolfo, Uncovering Sparsity and Heterogeneity in Firm-Level Return Predictability Using Machine Learning (April 26, 2022). Journal of Financial and Quantitative Analysis, forthcoming, Available at SSRN: https://ssrn.com/abstract=3604921 or http://dx.doi.org/10.2139/ssrn.3604921

Theodoros Evgeniou (Contact Author)

INSEAD ( email )

Boulevard de Constance
77305 Fontainebleau Cedex
France

Ahmed Guecioueur

INSEAD ( email )

Boulevard de Constance
Fontainebleau, 77300
France

Rodolfo Prieto

INSEAD ( email )

Boulevard de Constance
77305 Fontainebleau Cedex
France

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

Paper statistics

Downloads
377
Abstract Views
1,759
Rank
145,975
PlumX Metrics