Deep Learning in Characteristics-Sorted Factor Models

Abstract

Many view deep learning as a "black box" used only for forecasting. However, this paper provides an alternative application by constructing a structural deep neural network to generate latent factors in asset pricing. The conventional approach of sorting firm characteristics to generate long-short factor portfolio weights is underappreciated nonlinear modeling. First, we describe the complete mechanism for fitting cross-sectional returns by firm characteristics through risk factors. Second, unlike statistical models, our model has an economic-guided objective function that minimizes pricing errors. Empirically, we find asset pricing and investment improvements using individual stocks and test portfolios for in-sample and out-of-sample analysis.

Keywords: Cross-sectional Returns, Deep Learning, Latent Factors, Pricing Errors, Security Sorting.

JEL Classification: C1, G1