Option Hedging with Risk Averse Reinforcement Learning

2020 ACM International Conference on AI in Finance

8 Pages Posted: 4 Nov 2020

See all articles by Edoardo Vittori

Edoardo Vittori

Polytechnic University of Milan; Intesa SanPaolo SpA

Michele Trapletti

Intesa SanPaolo SpA

Marcello Restelli

Polytechnic University of Milan

Date Written: May 29, 2020

Abstract

In this paper we show how risk-averse reinforcement learning can be used to hedge options. We apply a state-of-the-art risk-averse algorithm: Trust Region Volatility Optimization (TRVO) to a vanilla option hedging environment, considering realistic factors such as discrete time and transaction costs.

Realism makes the problem twofold: the agent must both minimize volatility and contain transaction costs, these tasks usually being in competition.

We use the algorithm to train a sheaf of agents each characterized by a different risk aversion, so to be able to span an efficient frontier on the volatility-p&l space.

The results show that the derived hedging strategy not only outperforms the Black & Scholes delta hedge, but is also extremely robust and flexible, as it can efficiently hedge options with different characteristics and work on markets with different behaviors than what was used in training.

Keywords: Financial Options, Portfolio Optimization, Transaction Costs, Machine Learning, Reinforcement Learning, Deep Hedging

JEL Classification: C02, C15, C45, C61, G11

Suggested Citation

Vittori, Edoardo and Trapletti, Michele and Restelli, Marcello, Option Hedging with Risk Averse Reinforcement Learning (May 29, 2020). 2020 ACM International Conference on AI in Finance, Available at SSRN: https://ssrn.com/abstract=3693133

Edoardo Vittori (Contact Author)

Polytechnic University of Milan ( email )

Piazza Leonardo da Vinci
Milan, Milano 20100
Italy

Intesa SanPaolo SpA ( email )

Piazza P. Ferrari 10
P.O. BOX 8319
Milan, 20121
Italy

Michele Trapletti

Intesa SanPaolo SpA ( email )

Piazza P. Ferrari 10
P.O. BOX 8319
Milan, 20121
Italy

Marcello Restelli

Polytechnic University of Milan ( email )

Piazza Leonardo da Vinci
Milan, Milano 20100
Italy

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

Paper statistics

Downloads
89
Abstract Views
354
rank
406,204
PlumX Metrics