Exploring the Factor Zoo With a Machine-Learning Portfolio

Abstract

Over the years, top journals have published hundreds of characteristics to explain stock return, but many have lost significance. What fundamentally affects the time-varying significance of characteristics? We combine machine-learning (ML) and portfolio analysis to uncover patterns in significant characteristics. We train ML models on 106 characteristics to predict stock returns. From out-of-sample ML portfolio analysis, we reverse-engineer important characteristics that ML models uncover, which are unobservable. The ML portfolio’s dominant characteristics rotate between proxies for investor arbitrage constraint and firm financial constraint. We show that the credit cycle could fundamentally explain cross-sectional stock return over time.

Keywords: Machine Learning, Characteristics, Return Predictability, Portfolio Evaluation

JEL Classification: G12, G32