The Best of Both Worlds: Forecasting US Equity Market Returns using a Hybrid Machine Learning – Time Series Approach
28 Pages Posted: 11 Dec 2019 Last revised: 28 Sep 2021
Date Written: December 2, 2019
Predicting long-term equity market returns is of great importance for investors to strategically allocate their assets. We apply machine learning methods to forecast 10-year-ahead U.S. stock returns and compare the results to traditional Shiller regression-based forecasts more commonly used in the asset-management industry. Machine-learning forecasts have similar forecast errors to a traditional return forecast model based on lagged CAPE ratios. However, machine-learning forecasts have higher forecast errors than the regression-based, two-step approach of Davis et al  that forecasts the CAPE ratio based on macroeconomic variables and then imputes stock returns. When we combine our two-step approach with machine learning to forecast CAPE ratios (a hybrid ML-VAR approach), U.S. stock return forecasts are statistically and economically more accurate than all other approaches. We discuss why and conclude with some best practices for both data scientists and economists in making real-world investment return forecasts.
A more updated paper with a clearer description of methodology and longer time series can be found here: https://jfds.pm-research.com/content/3/2/9
Keywords: machine learning, stock return forecasting, return predictability, CAPE ratio
JEL Classification: G10, C58, E37
Suggested Citation: Suggested Citation