Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/270745.2 
Erscheinungsjahr: 
2025
Schriftenreihe/Nr.: 
CFR Working Paper No. 23-01
Versionsangabe: 
This Version: February 2025
Verlag: 
University of Cologne, Centre for Financial Research (CFR), Cologne
Zusammenfassung: 
We consider parametric portfolio policies of any complexity using deep neural networks to optimize investor utility. Risk aversion acts as an economic regularization mechanism, with higher risk aversion constraining model complexity. Empirically, Deep Parametric Portfolio Policies (DPPP) generate 43-102 basis points higher monthly certainty equivalent returns compared to linear policies. Looking beyond expected returns, non-linear portfolio policies better capture the complex relationship between investor preferences and firm characteristics but the benefits of using complex models vary with investor preferences. Results hold across different utility functions and remain robust to transaction costs and short-selling restrictions.
Schlagwörter: 
Portfolio Choice
Machine Learning
Expected Utility
JEL: 
G11
G12
C58
C45
Dokumentart: 
Working Paper

Datei(en):
Datei
Größe
915.66 kB




Versionsverlauf
Version Dokument Versionsbeschreibung
2 10419/270745.2 This Version: February 2025
1 10419/270745 This Version: February 2023

Publikationen in EconStor sind urheberrechtlich geschützt.