Deep Learning and the Cross-Section of Expected Returns

56 Pages Posted: 6 Dec 2017 Last revised: 11 Dec 2017

Date Written: December 2, 2017

Abstract

Deep learning is an active area of research in machine learning. I train deep feedforward neural networks (DFN) based on a set of 68 firm characteristics (FC) to predict the US cross-section of stock returns. After applying a network optimization strategy, I find that DFN long-short portfolios can generate attractive risk-adjusted returns compared to a linear benchmark. These findings underscore the importance of non-linear relationships among FC and expected returns. The results are robust to size, weighting schemes and portfolio cutoff points. Moreover, I show that price related FC, namely, short-term reversal and the twelve-months momentum, are among the main drivers of the return predictions. The majority of FC play a minor role in the variation of these predictions.

Keywords: Cross Section of Returns, Deep Learning, Asset Pricing, Factor Models, Machine Learning

JEL Classification: G11, G12, G17

Suggested Citation

Messmer, Marcial, Deep Learning and the Cross-Section of Expected Returns (December 2, 2017). Available at SSRN: https://ssrn.com/abstract=3081555 or http://dx.doi.org/10.2139/ssrn.3081555

Marcial Messmer (Contact Author)

University of St. Gallen ( email )

Langgasse 1
St. Gallen, 9008
Switzerland

Register to save articles to
your library

Register

Paper statistics

Downloads
2,249
Abstract Views
5,509
rank
5,812
PlumX Metrics