Factor Investing with Reinforcement Learning

41 Pages Posted: 7 May 2022

See all articles by Guillaume Coqueret

Guillaume Coqueret

EMLYON Business School

Eric André

EMLYON Business School

Multiple version iconThere are 3 versions of this paper

Abstract

This article aims to enhance factor investing with reinforcement learning (RL) techniques. The agent learns through sequential random allocations which rely on firms' characteristics. Using Dirichlet distributions as the driving policy, we derive closed forms for the policy gradients and analytical properties of the performance measure. This enables the implementation of REINFORCE methods, which we test on a large dataset of US equities. Across a large range of parametric choices, our result indicates that RL-based portfolios are very close to the equally-weighted (1/N) allocation. This implies that the agent learns to be agnostic with regard to factors, which can partly be explained by cross-sectional regressions showing a strong time variation in the relationship between returns and firm characteristics. All in all, our results contribute to a nascent stream of literature that relativizes the usefulness of mainstream characteristics in asset pricing models.

Keywords: Reinforcement learning, Factor investing, Equally-weighted portfolio, Asset pricing. JEL classifications: C38, G11, G12

Suggested Citation

Coqueret, Guillaume and André, Eric, Factor Investing with Reinforcement Learning. Available at SSRN: https://ssrn.com/abstract=4103046 or http://dx.doi.org/10.2139/ssrn.4103046

Guillaume Coqueret (Contact Author)

EMLYON Business School ( email )

23 Avenue Guy de Collongue
Ecully, 69132
France

Eric André

EMLYON Business School ( email )

23 Avenue Guy de Collongue
Ecully, 69132
France

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

Paper statistics

Downloads
141
Abstract Views
523
Rank
76,717
PlumX Metrics