Interactions in Asset Pricing

35 Pages Posted: 17 Jul 2023 Last revised: 6 Nov 2023

See all articles by Guillaume Chevalier

Guillaume Chevalier

AXA Investment Managers

Guillaume Coqueret

EMLYON Business School

Martial Laguerre

EMLYON Business School

Thomas Raffinot

AXA-IM

Date Written: November 3, 2023

Abstract

We propose a linearization of rule-based algorithms that reveals the most important interactions between characteristics and macroeconomic variables when explaining future stock returns. Our results suggest that the two types of predictors are intertwined in predictive models, which implies that the relationships between returns and standard asset pricing characteristics are not only non-linear but also strongly dependent on the state of the economy. From an investment standpoint, our interpretable machine learning approach also produces portfolios that outperform benchmarks out-of-sample.

Keywords: asset pricing, firm characteristics, marcoeconomic variables, machine learning, rulefit, interpretability

JEL Classification: C14, C23, C45, C58, G11, G12, G17

Suggested Citation

CHEVALIER, Guillaume and Coqueret, Guillaume and Laguerre, Martial and Raffinot, Thomas, Interactions in Asset Pricing (November 3, 2023). Available at SSRN: https://ssrn.com/abstract=4500944 or http://dx.doi.org/10.2139/ssrn.4500944

Guillaume CHEVALIER

AXA Investment Managers ( email )

Tour Majunga
6 Place de la Pyramide
La Défense, Paris 92908
France

Guillaume Coqueret (Contact Author)

EMLYON Business School ( email )

23 Avenue Guy de Collongue
Ecully, 69132
France

Martial Laguerre

EMLYON Business School ( email )

23 Avenue Guy de Collongue
Ecully, 69132
France

Thomas Raffinot

AXA-IM ( email )

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

Paper statistics

Downloads
639
Abstract Views
2,549
Rank
78,499
PlumX Metrics