The Best of Both Worlds: Forecasting US Equity Market Returns using a Hybrid Machine Learning – Time Series Approach

28 Pages Posted: 11 Dec 2019

See all articles by Haifeng Wang

Haifeng Wang

The Vanguard Group, Inc.

Harshdeep Ahluwalia

The Vanguard Group, Inc.

Roger A Aliaga-Diaz

The Vanguard Group, Inc.

Joseph H. Davis

The Vanguard Group

Date Written: December 2, 2019

Abstract

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 [2018] 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.

Keywords: machine learning, stock return forecasting, return predictability, CAPE ratio

JEL Classification: G10, C58, E37

Suggested Citation

Wang, Haifeng and Ahluwalia, Harshdeep and Aliaga-Diaz, Roger A and Davis, Joseph H., The Best of Both Worlds: Forecasting US Equity Market Returns using a Hybrid Machine Learning – Time Series Approach (December 2, 2019). Available at SSRN: https://ssrn.com/abstract=3497170 or http://dx.doi.org/10.2139/ssrn.3497170

Haifeng Wang (Contact Author)

The Vanguard Group, Inc. ( email )

100 Vanguard Blvd
Malvern, PA 19355
United States

Harshdeep Ahluwalia

The Vanguard Group, Inc. ( email )

100 Vanguard Blvd
Malvern, PA 19355
United States

Roger A Aliaga-Diaz

The Vanguard Group, Inc. ( email )

100 Vanguard Blvd
Malvern, PA 19355
United States

Joseph H. Davis

The Vanguard Group ( email )

100 Vanguard Blvd
Malvern, PA 19355
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
599
Abstract Views
1,964
rank
49,214
PlumX Metrics