Deep equal risk pricing of financial derivatives with non-translation invariant risk measures

TL;DR

This paper explores the use of non-translation invariant risk measures in equal risk pricing for financial derivatives, utilizing deep reinforcement learning to improve pricing flexibility and reduce price inflation.

Contribution

It introduces a novel approach combining non-translation invariant risk measures with deep reinforcement learning for derivative pricing, extending beyond traditional convex risk measures.

Findings

Semi-mean-square-error reduces price inflation

Deep reinforcement learning enables single-run pricing

Training accuracy remains stable with modifications

Abstract

The use of non-translation invariant risk measures within the equal risk pricing (ERP) methodology for the valuation of financial derivatives is investigated. The ability to move beyond the class of convex risk measures considered in several prior studies provides more flexibility within the pricing scheme. In particular, suitable choices for the risk measure embedded in the ERP framework such as the semi-mean-square-error (SMSE) are shown herein to alleviate the price inflation phenomenon observed under Tail Value-at-Risk based ERP as documented for instance in Carbonneau and Godin (2021b). The numerical implementation of non-translation invariant ERP is performed through deep reinforcement learning, where a slight modification is applied to the conventional deep hedging training algorithm (see Buehler et al., 2019) so as to enable obtaining a price through a single training run for the two neural networks associated with the respective long and short hedging strategies. The accuracy of the neural network training procedure is shown in simulation experiments not to be materially impacted by such modification of the training algorithm.