Identifying Signals of the Cross Section of Stock Returns

97 Pages Posted: 4 Aug 2021 Last revised: 1 Mar 2023

See all articles by Tengjia Shu

Tengjia Shu

University of Illinois at Chicago

Ashish Tiwari

University of Iowa

Date Written: August 2, 2021


The proliferation of anomalies and the resulting “factor zoo” has challenged finance researchers to identify firm characteristics that are genuinely related to the cross-sectional variation in expected stock returns. We address this challenge using a Bayesian ensemble-of-trees approach which combines the advantages of machine learning with a Bayesian inference framework. Applying the methodology to U.S. stock returns we find that a firm’s market value is the sole consistently relevant
characteristic. We further confirm that the stochastic discount factor based on a sparse set of factors can successfully explain most of the variation in expected returns.

Keywords: Factor Zoo, Anomalies, Stochastic Discount Factor, Bayesian Inference, Machine Learning, Ensemble-of-Trees

JEL Classification: G11, G12, C11, C53, C58

Suggested Citation

Shu, Tengjia and Tiwari, Ashish, Identifying Signals of the Cross Section of Stock Returns (August 2, 2021). Available at SSRN: or

Tengjia Shu

University of Illinois at Chicago ( email )

601 S. Morgan St
Chicago, IL 60607
United States

Ashish Tiwari (Contact Author)

University of Iowa ( email )

Finance Department
Henry B. Tippie College of Business, 108 PBB
Iowa City, IA 52242
United States
(319) 353-2185 (Phone)
(319) 335-3690 (Fax)


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

Paper statistics

Abstract Views
PlumX Metrics