Machine Learning and Return Predictability Across Firms, Time and Portfolios

73 Pages Posted: 2 Dec 2020 Last revised: 7 Jan 2021

See all articles by Fahiz Baba Yara

Fahiz Baba Yara

New University of Lisbon - Nova School of Business and Economics

Date Written: March 25, 2020

Abstract

Previous research finds that machine learning methods predict short-term return variation in the cross-section of stocks, even when these methods do not impose strict economic restrictions. However, without such restrictions, the models' predictions fail to generalize in a number of important ways, such as predicting time-series variation in returns to the market portfolio and long-short characteristic sorted portfolios. I show that this shortfall can be remedied by imposing restrictions, that reflect findings in the financial economics literature, in the architectural design of a neural network model and provide recommendations for using machine learning methods in asset pricing. Additionally, I study return predictability over multiple future horizons, thus shedding light on the dynamics of intermediate and long-run conditional expected returns.

Keywords: Return Predictability, Long-run Returns, Machine Learning, Neural Networks, Long-short portfolios

JEL Classification: E44, G10, G11, G12, G17

Suggested Citation

Baba Yara, Fahiz, Machine Learning and Return Predictability Across Firms, Time and Portfolios (March 25, 2020). Available at SSRN: https://ssrn.com/abstract=3696533 or http://dx.doi.org/10.2139/ssrn.3696533

Fahiz Baba Yara (Contact Author)

New University of Lisbon - Nova School of Business and Economics ( email )

Campus de Campolide
Lisbon, 1099-032
Portugal

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
56
Abstract Views
295
rank
420,134
PlumX Metrics