Deep Parametric Portfolio Policies

65 Pages Posted: 12 Jul 2022 Last revised: 6 Sep 2022

See all articles by Frederik Simon

Frederik Simon

University of Cologne

Sebastian Weibels

University of Cologne

Tom Zimmermann

University of Cologne

Date Written: June 30, 2022

Abstract

We directly optimize portfolio weights via deep neural networks by generalizing the parametric portfolio policy framework. Our results show that network-based portfolio policies result in an increase of investor utility of between 30 and 100 percent over a comparable linear portfolio policy, depending on whether portfolio restrictions on individual stock weights, short-selling or transaction costs are imposed, and depending on an investor's utility function. We provide extensive model interpretation and trace improvements over linear policies to the relevance of predictor interactions. Both approaches agree on the same dominant predictors, namely past return-based firm characteristics.

Keywords: Portfolio Choice, Machine Learning, Expected Utility

JEL Classification: G11, G12, C58, C45

Suggested Citation

Simon, Frederik and Weibels, Sebastian and Zimmermann, Tom, Deep Parametric Portfolio Policies (June 30, 2022). Available at SSRN: https://ssrn.com/abstract=4150292 or http://dx.doi.org/10.2139/ssrn.4150292

Frederik Simon

University of Cologne ( email )

Albertus-Magnus-Platz
Cologne, 50923
Germany

Sebastian Weibels (Contact Author)

University of Cologne ( email )

Albertus-Magnus-Platz
Cologne, 50923
Germany

Tom Zimmermann

University of Cologne ( email )

Albertus-Magnus-Platz
Cologne, 50923
Germany

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

Paper statistics

Downloads
210
Abstract Views
768
rank
213,198
PlumX Metrics