CVA Sensitivities, Hedging and Risk

Stéphane Crépey (1) , Botao Li (2) , Hoang Nguyen (3, 2) , Bouazza Saadeddine

1 UFR Mathématiques UPCité - UFR Mathématiques [Sciences] - Université Paris Cité
2 LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation
3 IES - Institut d’Electronique et des Systèmes

We present a unified framework for computing CVA sensitivities, hedging the CVA, and assessing CVA risk, using probabilistic machine learning meant as refined regression tools on simulated data, validatable by low-cost companion Monte Carlo procedures. Various notions of sensitivities are introduced and benchmarked numerically. We identify the sensitivities representing the best practical trade-offs in downstream tasks including CVA hedging and risk assessment.

Keywords: CVA; sensitivities; neural networks; model risk

Domains: Computational Finance [q-fin.CP]

Stéphane Crépey, Botao Li, Hoang Nguyen, Bouazza Saadeddine. CVA Sensitivities, Hedging and Risk. 2024. ⟨hal-04661959⟩