Macroeconomic Content of Characteristics-Based Asset Pricing Models: A Machine Learning Analysis

Abstract

We explore whether the empirical success of nine characteristics-based asset pricing models is explained by their ability to identify macroeconomic risks.  Although the stochastic discount factors (SDFs) of some models are weakly related to macroeconomic shocks, we find no evidence that such a relation exists for the SDFs' non-market components. The result also holds for short-term macroeconomic news, real-time macroeconomic shocks, and changes in macroeconomic forecasts. Our analysis involves more than 100 macroeconomic indicators and uses machine learning to combine them. Our paper illustrates how machine learning can be used for analyzing the explainability of one variable by many others.

Keywords: asset pricing, stochastic discount factor, machine learning, elastic net, macroeconomic shocks

JEL Classification: G12, C58