Robust Portfolio Selection Under Model Ambiguity Using Deep Learning

In this study, we address the ambiguity in portfolio optimization, particularly focusing on the uncertainty related to the statistical parameters governing asset returns. We propose a novel method that combines robust optimization with artificial neural networks (ANNs). Our approach effectively hand...

Full description

Saved in:
Bibliographic Details
Main Authors: Sadegh Miri, Erfan Salavati, Mostafa Shamsi
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:International Journal of Financial Studies
Subjects:
Online Access:https://www.mdpi.com/2227-7072/13/1/38
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204766300274688
author Sadegh Miri
Erfan Salavati
Mostafa Shamsi
author_facet Sadegh Miri
Erfan Salavati
Mostafa Shamsi
author_sort Sadegh Miri
collection DOAJ
description In this study, we address the ambiguity in portfolio optimization, particularly focusing on the uncertainty related to the statistical parameters governing asset returns. We propose a novel method that combines robust optimization with artificial neural networks (ANNs). Our approach effectively handles both the randomness inherent in asset prices and the ambiguity in their governing parameters. Through our method, we consider both simulated data, using the Exponential Ornstein–Uhlenbeck process, and real-world stock price data. The results showcase that our ANN-based method outperforms traditional benchmark methods such as equally weighted portfolio and adaptive mean–variance portfolio selection.
format Article
id doaj-art-3662b3bfcd6d4da39267ef8cecc3b4fc
institution OA Journals
issn 2227-7072
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series International Journal of Financial Studies
spelling doaj-art-3662b3bfcd6d4da39267ef8cecc3b4fc2025-08-20T02:11:14ZengMDPI AGInternational Journal of Financial Studies2227-70722025-03-011313810.3390/ijfs13010038Robust Portfolio Selection Under Model Ambiguity Using Deep LearningSadegh Miri0Erfan Salavati1Mostafa Shamsi2Department of Mathematics and Computer Science, Amirkabir University of Technology (Tehran Polytechnic), Tehran 15916-34311, IranDepartment of Mathematics and Computer Science, Amirkabir University of Technology (Tehran Polytechnic), Tehran 15916-34311, IranDepartment of Mathematics and Computer Science, Amirkabir University of Technology (Tehran Polytechnic), Tehran 15916-34311, IranIn this study, we address the ambiguity in portfolio optimization, particularly focusing on the uncertainty related to the statistical parameters governing asset returns. We propose a novel method that combines robust optimization with artificial neural networks (ANNs). Our approach effectively handles both the randomness inherent in asset prices and the ambiguity in their governing parameters. Through our method, we consider both simulated data, using the Exponential Ornstein–Uhlenbeck process, and real-world stock price data. The results showcase that our ANN-based method outperforms traditional benchmark methods such as equally weighted portfolio and adaptive mean–variance portfolio selection.https://www.mdpi.com/2227-7072/13/1/38portfolio optimizationrobust optimizationartificial neural networksambiguity
spellingShingle Sadegh Miri
Erfan Salavati
Mostafa Shamsi
Robust Portfolio Selection Under Model Ambiguity Using Deep Learning
International Journal of Financial Studies
portfolio optimization
robust optimization
artificial neural networks
ambiguity
title Robust Portfolio Selection Under Model Ambiguity Using Deep Learning
title_full Robust Portfolio Selection Under Model Ambiguity Using Deep Learning
title_fullStr Robust Portfolio Selection Under Model Ambiguity Using Deep Learning
title_full_unstemmed Robust Portfolio Selection Under Model Ambiguity Using Deep Learning
title_short Robust Portfolio Selection Under Model Ambiguity Using Deep Learning
title_sort robust portfolio selection under model ambiguity using deep learning
topic portfolio optimization
robust optimization
artificial neural networks
ambiguity
url https://www.mdpi.com/2227-7072/13/1/38
work_keys_str_mv AT sadeghmiri robustportfolioselectionundermodelambiguityusingdeeplearning
AT erfansalavati robustportfolioselectionundermodelambiguityusingdeeplearning
AT mostafashamsi robustportfolioselectionundermodelambiguityusingdeeplearning