Assessing Asset-Liability Risk With Neural Networks

Risks 2020, 8, 16.

Posted: 13 Jan 2020 Last revised: 10 Feb 2020

Date Written: December 23, 2019

Abstract

We introduce a neural network approach for assessing the risk of a portfolio of assets and liabilities over a given time period. This requires a conditional valuation of the portfolio given the state of the world at a later time, a problem that is particularly challenging if the portfolio contains structured products or complex insurance contracts which do not admit closed form valuation formulas. We illustrate the method on different examples from banking and insurance. We focus on value-at-risk and expected shortfall, but the approach also works for other risk measures.

Keywords: Asset-asset liability risk, risk capital, solvency calculation, value-at-risk, expected shortfall, neural networks, importance sampling

Suggested Citation

Cheridito, Patrick and Ery, John and Wuthrich, Mario V., Assessing Asset-Liability Risk With Neural Networks (December 23, 2019). Risks 2020, 8, 16., Available at SSRN: https://ssrn.com/abstract=3508862 or http://dx.doi.org/10.2139/ssrn.3508862

Patrick Cheridito (Contact Author)

ETH Zurich ( email )

Department of Mathematics
8092 Zurich
Switzerland

John Ery

ETH Zürich ( email )

Rämistrasse 101
ZUE F7
Zürich, 8092
Switzerland

Mario V. Wuthrich

RiskLab, ETH Zurich ( email )

Department of Mathematics
Ramistrasse 101
Zurich, 8092
Switzerland

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
885
PlumX Metrics