Comparing Deep RL and Traditional Financial Portfolio Methods

Eric Benhamou; Jean Jacques Ohana; Beatrice Guez; David Saltiel; Rida Laraki; Jamal Atif

doi:10.1007/978-3-031-74643-7_24

Comparing Deep RL and Traditional Financial Portfolio Methods

Eric Benhamou
, Jean Jacques Ohana
, Beatrice Guez
, David Saltiel
, Rida Laraki
, Jamal Atif

Univ. Paris-Dauphine
Ai for Alpha

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Portfolio allocation aims to optimize the risk/return ratio in investment management. Traditional methods based on modern portfolio theory have been widely used for this purpose. However, the emergence of deep reinforcement learning (DRL) offers an alternative approach. This article conducts a comprehensive comparative analysis of traditional portfolio allocation methods and DRL, examining their principles, methodologies, and performance in maximizing risk-return profiles. It demonstrates that a basic version of DRL converges to traditional methods, while a myopic agent driven by immediate rewards represents the dynamic version of traditional methods. Experimental results indicate some improvement of DRL over traditional methods.

Original language	English
Title of host publication	Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers
Editors	Rosa Meo, Fabrizio Silvestri
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	323-338
Number of pages	16
ISBN (Print)	9783031746420
DOIs	https://doi.org/10.1007/978-3-031-74643-7_24
Publication status	Published - 1 Jan 2025
Externally published	Yes
Event	23rd Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023 - Turin, Italy Duration: 18 Sept 2023 → 22 Sept 2023

Publication series

Name	Communications in Computer and Information Science
Volume	2137 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	23rd Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023
Country/Territory	Italy
City	Turin
Period	18/09/23 → 22/09/23

Keywords

Deep RL
Portfolio allocation

Access to Document

10.1007/978-3-031-74643-7_24

Cite this

Benhamou, E., Ohana, J. J., Guez, B., Saltiel, D., Laraki, R., & Atif, J. (2025). Comparing Deep RL and Traditional Financial Portfolio Methods. In R. Meo, & F. Silvestri (Eds.), Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers (pp. 323-338). (Communications in Computer and Information Science; Vol. 2137 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-74643-7_24

Benhamou, Eric ; Ohana, Jean Jacques ; Guez, Beatrice et al. / Comparing Deep RL and Traditional Financial Portfolio Methods. Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers. editor / Rosa Meo ; Fabrizio Silvestri. Springer Science and Business Media Deutschland GmbH, 2025. pp. 323-338 (Communications in Computer and Information Science).

@inproceedings{76b5515c05c140e880d417c86e6f7b28,

title = "Comparing Deep RL and Traditional Financial Portfolio Methods",

abstract = "Portfolio allocation aims to optimize the risk/return ratio in investment management. Traditional methods based on modern portfolio theory have been widely used for this purpose. However, the emergence of deep reinforcement learning (DRL) offers an alternative approach. This article conducts a comprehensive comparative analysis of traditional portfolio allocation methods and DRL, examining their principles, methodologies, and performance in maximizing risk-return profiles. It demonstrates that a basic version of DRL converges to traditional methods, while a myopic agent driven by immediate rewards represents the dynamic version of traditional methods. Experimental results indicate some improvement of DRL over traditional methods.",

keywords = "Deep RL, Portfolio allocation",

author = "Eric Benhamou and Ohana, \{Jean Jacques\} and Beatrice Guez and David Saltiel and Rida Laraki and Jamal Atif",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; 23rd Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023 ; Conference date: 18-09-2023 Through 22-09-2023",

year = "2025",

month = jan,

day = "1",

doi = "10.1007/978-3-031-74643-7\_24",

language = "English",

isbn = "9783031746420",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "323--338",

editor = "Rosa Meo and Fabrizio Silvestri",

booktitle = "Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers",

}

Benhamou, E, Ohana, JJ, Guez, B, Saltiel, D, Laraki, R & Atif, J 2025, Comparing Deep RL and Traditional Financial Portfolio Methods. in R Meo & F Silvestri (eds), Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers. Communications in Computer and Information Science, vol. 2137 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 323-338, 23rd Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023, Turin, Italy, 18/09/23. https://doi.org/10.1007/978-3-031-74643-7_24

Comparing Deep RL and Traditional Financial Portfolio Methods. / Benhamou, Eric; Ohana, Jean Jacques; Guez, Beatrice et al.
Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers. ed. / Rosa Meo; Fabrizio Silvestri. Springer Science and Business Media Deutschland GmbH, 2025. p. 323-338 (Communications in Computer and Information Science; Vol. 2137 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Comparing Deep RL and Traditional Financial Portfolio Methods

AU - Benhamou, Eric

AU - Ohana, Jean Jacques

AU - Guez, Beatrice

AU - Saltiel, David

AU - Laraki, Rida

AU - Atif, Jamal

PY - 2025/1/1

Y1 - 2025/1/1

N2 - Portfolio allocation aims to optimize the risk/return ratio in investment management. Traditional methods based on modern portfolio theory have been widely used for this purpose. However, the emergence of deep reinforcement learning (DRL) offers an alternative approach. This article conducts a comprehensive comparative analysis of traditional portfolio allocation methods and DRL, examining their principles, methodologies, and performance in maximizing risk-return profiles. It demonstrates that a basic version of DRL converges to traditional methods, while a myopic agent driven by immediate rewards represents the dynamic version of traditional methods. Experimental results indicate some improvement of DRL over traditional methods.

AB - Portfolio allocation aims to optimize the risk/return ratio in investment management. Traditional methods based on modern portfolio theory have been widely used for this purpose. However, the emergence of deep reinforcement learning (DRL) offers an alternative approach. This article conducts a comprehensive comparative analysis of traditional portfolio allocation methods and DRL, examining their principles, methodologies, and performance in maximizing risk-return profiles. It demonstrates that a basic version of DRL converges to traditional methods, while a myopic agent driven by immediate rewards represents the dynamic version of traditional methods. Experimental results indicate some improvement of DRL over traditional methods.

KW - Deep RL

KW - Portfolio allocation

UR - https://www.scopus.com/pages/publications/85215971858

U2 - 10.1007/978-3-031-74643-7_24

DO - 10.1007/978-3-031-74643-7_24

M3 - Conference contribution

AN - SCOPUS:85215971858

SN - 9783031746420

T3 - Communications in Computer and Information Science

SP - 323

EP - 338

BT - Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers

A2 - Meo, Rosa

A2 - Silvestri, Fabrizio

PB - Springer Science and Business Media Deutschland GmbH

T2 - 23rd Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2023

Y2 - 18 September 2023 through 22 September 2023

ER -

Benhamou E, Ohana JJ, Guez B, Saltiel D, Laraki R, Atif J. Comparing Deep RL and Traditional Financial Portfolio Methods. In Meo R, Silvestri F, editors, Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2023, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2025. p. 323-338. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-74643-7_24