Estimating Security Betas via Machine Learning

63 Pages Posted: 1 Oct 2021

See all articles by Wolfgang Drobetz

Wolfgang Drobetz

University of Hamburg

Fabian Hollstein

Leibniz University Hannover - School of Economics and Management

Tizian Otto

University of Hamburg

Marcel Prokopczuk

University of Reading - ICMA Centre; Leibniz Universität Hannover - Faculty of Economics and Management

Date Written: September 29, 2021

Abstract

This paper evaluates the predictive performance of machine learning techniques in estimating time-varying betas of US stocks. Compared to established estimators, tree-based models and neural networks outperform from both a statistical and an economic perspective. Random forests perform the best overall. Machine learning-based estimators provide the lowest fore-cast errors. Moreover, unlike traditional approaches, they lead to truly ex-post market-neutral portfolios. The inherent model complexity is strongly time-varying. The most important predictors are various historical betas as well as fundamental turnover and size signals. Compared to linear regressions, interactions and nonlinear effects enhance the predictive performance substantially.

Keywords: Beta estimation, machine learning

JEL Classification: G11, G12, C58, G17

Suggested Citation

Drobetz, Wolfgang and Hollstein, Fabian and Otto, Tizian and Prokopczuk, Marcel and Prokopczuk, Marcel, Estimating Security Betas via Machine Learning (September 29, 2021). Available at SSRN: https://ssrn.com/abstract=3933048 or http://dx.doi.org/10.2139/ssrn.3933048

Wolfgang Drobetz

University of Hamburg ( email )

Moorweidenstrasse 18
Hamburg, 20148
Germany

Fabian Hollstein

Leibniz University Hannover - School of Economics and Management ( email )

Koenigsworther Platz 1
Hannover, 30167
Germany

HOME PAGE: http://sites.google.com/view/fabianhollstein/home

Tizian Otto (Contact Author)

University of Hamburg ( email )

Moorweidenstraße 18
Hamburg, 20148
Germany

Marcel Prokopczuk

Leibniz Universität Hannover - Faculty of Economics and Management ( email )

Koenigsworther Platz 1
Hannover, 30167
Germany

University of Reading - ICMA Centre ( email )

Whiteknights Park
P.O. Box 242
Reading RG6 6BA
United Kingdom

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

Paper statistics

Downloads
406
Abstract Views
1,048
rank
93,862
PlumX Metrics