Deep Reinforcement Learning (DRL) for Portfolio Allocation



Benhamou, Eric, Saltiel, David, Ohana, Jean Jacques, Atif, Jamal and Laraki, Rida ORCID: 0000-0002-4898-2424
(2021) Deep Reinforcement Learning (DRL) for Portfolio Allocation. .

[img] Text
ecml2020.pdf - Author Accepted Manuscript

Download (257kB) | Preview

Abstract

Deep reinforcement learning (DRL) has reached an unprecedent level on complex tasks like game solving (Go [6], StarCraft II [7]), and autonomous driving. However, applications to real financial assets are still largely unexplored and it remains an open question whether DRL can reach super human level. In this demo, we showcase state-of-the-art DRL methods for selecting portfolios according to financial environment, with a final network concatenating three individual networks using layers of convolutions to reduce network’s complexity. The multi entries of our network enables capturing dependencies from common financial indicators features like risk aversion, citigroup index surprise, portfolio specific features and previous portfolio allocations. Results on test set show this approach can overperform traditional portfolio optimization methods with results available at our demo website.

Item Type: Conference or Workshop Item (Unspecified)
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 22 Jun 2021 08:02
Last Modified: 18 Jan 2023 22:33
DOI: 10.1007/978-3-030-67670-4_32
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3127162