Deep learning for CVA computations of large portfolios of financial derivatives

TL;DR

This paper introduces a neural network approach for calculating Credit Valuation Adjustment (CVA) for complex portfolios of derivatives, revealing significant overestimations in traditional methods and improving accuracy in risk assessment.

Contribution

The paper presents a novel neural network-based method for CVA computation that accounts for portfolio complexity and counterparty risk factors, enhancing accuracy over standard procedures.

Findings

CVA can be overestimated by up to 25% without exercise strategy adjustment.

Expected Shortfall of CVA can be overestimated by more than 100%.

Neural network method improves CVA accuracy for portfolios with optionality.

Abstract

In this paper, we propose a neural network-based method for CVA computations of a portfolio of derivatives. In particular, we focus on portfolios consisting of a combination of derivatives, with and without true optionality, \textit{e.g.,} a portfolio of a mix of European- and Bermudan-type derivatives. CVA is computed, with and without netting, for different levels of WWR and for different levels of credit quality of the counterparty. We show that the CVA is overestimated with up to 25\% by using the standard procedure of not adjusting the exercise strategy for the default-risk of the counterparty. For the Expected Shortfall of the CVA dynamics, the overestimation was found to be more than 100\% in some non-extreme cases.