Library
local_library Home Repository

Deep learning for CVA computations of large portfolios of financial derivatives

Journal Article (2021)
Authors

K.H. Andersson (Centrum Wiskunde & Informatica (CWI))

Cornelis W. Oosterlee (TU Delft - Numerical Analysis, Centrum Wiskunde & Informatica (CWI))

Research Group
Numerical Analysis
Copyright
© 2021 K.H. Andersson, C.W. Oosterlee
To reference this document use:
https://doi.org/10.1016/j.amc.2021.126399
More Info
expand_more
Publication Year
2021
Language
English
Copyright
© 2021 K.H. Andersson, C.W. Oosterlee
Research Group
Numerical Analysis
Volume number
409
Pages (from-to)
1-21
DOI:
https://doi.org/10.1016/j.amc.2021.126399
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

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, 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.