Ensemble Machine Learning and Stock Return Predictability

AFA 2020

AsianFA 2019, AMES 2019, FMND 2019

50 Pages Posted: 8 Jan 2019 Last revised: 17 Sep 2019

See all articles by Ben Jacobsen

Ben Jacobsen

Tilburg University - TIAS School for Business and Society; Massey University

Fuwei Jiang

Central University of Finance and Economics (CUFE)

Hongwei Zhang

Tilburg University - TIAS School for Business and Society; Central University of Finance and Economics (CUFE)

Date Written: March 1, 2019

Abstract

Many, even sophisticated, models cannot beat a simple mean combination of univariate stock market return forecasts. We introduce an ensemble machine learning method, which averages forecasts from sophisticated models (like BMA, WALS and LASSO) based on random subsamples and which learns from its mistakes by adaptively changing sampling distributions. Empirically, our novel method improves the simple mean forecast with statistically significant monthly out-of-sample R2 of around 2-3% and annual utility gains around 3%. Our approach benefits from predicting well in volatile periods and especially from extreme market drops. The forecasting gains of our new method stem from improved diversity among individual forecasts. We obtain similar gains in forecasting accuracy when we use our method to predict factor portfolios and other macro economic variables.

Keywords: Equity Premium Prediction, Machine Learning, Forecast Combination, Parameter Uncertainty, Diversification

JEL Classification: G17, G12, G02, C58

Suggested Citation

Jacobsen, Ben and Jiang, Fuwei and Zhang, Hongwei, Ensemble Machine Learning and Stock Return Predictability (March 1, 2019). AFA 2020, AsianFA 2019, AMES 2019, FMND 2019 , Available at SSRN: https://ssrn.com/abstract=3310289 or http://dx.doi.org/10.2139/ssrn.3310289

Ben Jacobsen

Tilburg University - TIAS School for Business and Society ( email )

Warandelaan 2
TIAS Building
Tilburg, Noord Brabant 5037 AB
Netherlands

Massey University ( email )

Auckland
New Zealand

Fuwei Jiang

Central University of Finance and Economics (CUFE) ( email )

39 South College Road
Haidian District
Beijing, Beijing 100081
China

Hongwei Zhang (Contact Author)

Tilburg University - TIAS School for Business and Society ( email )

Warandelaan 2
TIAS Building
Tilburg, Noord Brabant 5037 AB
Netherlands

Central University of Finance and Economics (CUFE)

39 South College Road
Haidian District
Beijing, 100081
China

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
416
Abstract Views
1,664
rank
76,634
PlumX Metrics