Tree-Based Machine Learning Approaches for Equity Market Predictions

Journal of Asset Management

36 Pages Posted: 28 Nov 2018 Last revised: 12 Jun 2019

See all articles by Dominik Wolff

Dominik Wolff

Darmstadt University of Technology; Institute for quantitative Capital Market research at Deka Bank (IQ-KAP); Deka Investment GmbH; Frankfurt University of Applied Sciences

Dr. Ulrich Neugebauer

Deka Investment GmbH

Date Written: June 11, 2018

Abstract

We empirically analyze equity premium predictions with ‘traditional’ linear regression models and tree-based machine learning approaches. Based on a commonly used dataset of equity market predictors extended by additional fundamental, macroeconomic, sentiment and risk indicators, we find mixed results for machine learning algorithms for equity market predictions. In contrast to sophisticated linear regression models such as penalized least squares or principal component regressions (PCR), the analyzed machine learning algorithms fail to significantly out-perform the historical average benchmark forecast. However, an investment strategy that uses machine learning predictions in a market-timing strategy outperforms a passive buy-and-hold investment. Compared to sophisticated linear prediction models machine learning algorithms do not improve forecast accuracy in our problem set.

Keywords: Machine Learning, Equity Return Forecasts, Predictive Regression, Three-Pass Regression Filter, Random Forest, Boosting

JEL Classification: G17, G11, C53

Suggested Citation

Wolff, Dominik and Neugebauer, Ulrich, Tree-Based Machine Learning Approaches for Equity Market Predictions (June 11, 2018). Journal of Asset Management, Available at SSRN: https://ssrn.com/abstract=3265107 or http://dx.doi.org/10.2139/ssrn.3265107

Dominik Wolff (Contact Author)

Darmstadt University of Technology

Hochschulstraße 1
S1|02 40
Darmstadt, Hessen D-64289
Germany

Institute for quantitative Capital Market research at Deka Bank (IQ-KAP) ( email )

Mainzer Landstrasse 16
Frankfurt am Main, 60325
Germany

HOME PAGE: http://www.iq-kap.de/en

Deka Investment GmbH ( email )

Mainzer Landstrasse 16
Frankfurt am Main, 60325
Germany

Frankfurt University of Applied Sciences ( email )

Nibelungenplatz 1
Frankfurt / Main, 60318
Germany

Ulrich Neugebauer

Deka Investment GmbH ( email )

Mainzer Landstrasse 16
Frankfurt am Main, 60325
Germany

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
299
Abstract Views
1,698
rank
111,125
PlumX Metrics