Detecting and Adapting to Crisis Pattern with Context Based Deep Reinforcement Learning

9 Pages Posted: 10 Sep 2020 Last revised: 16 Jun 2021

See all articles by Eric Benhamou

Eric Benhamou

Université Paris Dauphine; EB AI Advisory; AI For Alpha

David Saltiel

Université Paris Dauphine; A.I. Square Connect; AI For Alpha

Jean-Jacques Ohana

AI For Alpha

Jamal Atif

Université Paris Dauphine

Date Written: September 7, 2020

Abstract

Deep reinforcement learning (DRL) has reached super human levels in complex tasks like game solving (Go, StarCraft II, Atari Games), and autonomous driving. However, it remains an open question whether DRL can reach human level in applications to financial problems and in particular in detecting pattern crisis and consequently dis-investing. In this paper, we present an innovative DRL framework consisting in two subnetworks fed respectively with portfolio strategies past performances and standard deviations as well as additional contextual features. The second sub network plays an important role as it captures dependencies with common financial indicators features like risk aversion, economic surprise index and correlations between assets that allows taking into account context based information. We compare different network architectures either using layers of convolutions to reduce network’s complexity or LSTM block to capture time dependency and whether previous allocations is important in the modeling. We also use adversarial training to make the final model more robust. Results on test set show this approach substantially over-performs traditional portfolio optimization methods like Markovitz and is able to detect and anticipate crisis like the current COVID one.

Keywords: Deep Reinforcement Learning, Portfolio selection

JEL Classification: G11

Suggested Citation

Benhamou, Eric and Saltiel, David and Ohana, Jean-Jacques and Atif, Jamal, Detecting and Adapting to Crisis Pattern with Context Based Deep Reinforcement Learning (September 7, 2020). Université Paris-Dauphine Research Paper No. 3688353, Available at SSRN: https://ssrn.com/abstract=3688353 or http://dx.doi.org/10.2139/ssrn.3688353

Eric Benhamou (Contact Author)

Université Paris Dauphine ( email )

Place du Maréchal de Tassigny
Paris, Cedex 16 75775
France

EB AI Advisory ( email )

35 Boulevard d'Inkermann
Neuilly sur Seine, 92200
France

AI For Alpha ( email )

35 boulevard d'Inkermann
Neuilly sur Seine, 92200
France

David Saltiel

Université Paris Dauphine ( email )

Place du Maréchal de Tassigny
Paris, Cedex 16 75775
France

A.I. Square Connect ( email )

35 Boulevard d'Inkermann
Neuilly sur Seine, 92200
France

AI For Alpha ( email )

35 boulevard d'Inkermann
Neuilly sur Seine, 92200
France

Jean-Jacques Ohana

AI For Alpha ( email )

35 boulevard d'Inkermann
Neuilly sur Seine, 92200
France

Jamal Atif

Université Paris Dauphine ( email )

Place du Maréchal de Tassigny
Paris, Cedex 16 75775
France

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
6,747
Abstract Views
75,501
rank
1,480
PlumX Metrics