Deep Parametric Portfolio Policies

64 Pages Posted: 12 Jul 2022 Last revised: 10 Feb 2023

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 as a function of firm characteristics 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 show that network-based policies better capture the non-linear relationship between investor utility and firm characteristics. Improvements can be traced to both variable interactions and non-linearity in functional form. Both the linear and the network-based approach 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
523
Abstract Views
2,032
Rank
89,916
PlumX Metrics