Predicting Equity Returns with Forecast Combinations of Deep Learning and Ensemble Methods

74 Pages Posted: 7 Jul 2023 Last revised: 29 Mar 2024

See all articles by Eike-Christian Brinkop

Eike-Christian Brinkop

University of Reading - ICMA Centre

Emese Lazar

University of Reading - ICMA Centre

Marcel Prokopczuk

Leibniz Universität Hannover - Faculty of Economics and Management; University of Reading - ICMA Centre

Abstract

We analyse forecast combination methods in the context of machine learning to predict equity returns. Whilst individual models lack robustness, forecast combinations over two levels display stability and Sharpe ratios of up to 3.06. We use decision trees in genetic algorithms to analyse the structure of variable influence. The impact of these variables displays inconsistencies and shows variations across different models and data. We propose a new performance measure for risk premium forecasts which leads to more robust evaluations than existing performance measures such as R2, whilst providing economic interpretability. This measure can be linked to the advantages models offer for portfolio choice.

Keywords: Equity Return Prediction, Forecast Combination, Deep Learning

JEL Classification: C51, C52, C53, C55, G12, G17

Suggested Citation

Brinkop, Eike-Christian and Lazar, Emese and Prokopczuk, Marcel, Predicting Equity Returns with Forecast Combinations of Deep Learning and Ensemble Methods. Available at SSRN: https://ssrn.com/abstract=4503472 or http://dx.doi.org/10.2139/ssrn.4503472

Eike-Christian Brinkop

University of Reading - ICMA Centre ( email )

Whiteknights
Henley, RG9 3AU
United Kingdom

Emese Lazar (Contact Author)

University of Reading - ICMA Centre ( email )

Whiteknights Park
P.O. Box 242
Reading RG6 6BA
United Kingdom
+44 (0)1183 786675 (Phone)
+44 (0)1189 314741 (Fax)

Marcel Prokopczuk

Leibniz Universität Hannover - Faculty of Economics and Management ( email )

Koenigsworther Platz 1
Hannover, 30167
Germany

University of Reading - ICMA Centre ( email )

Whiteknights Park
P.O. Box 242
Reading RG6 6BA
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
280
Abstract Views
2,140
Rank
206,702
PlumX Metrics