Assessing asset-liability risk with neural networks

TL;DR

This paper presents a neural network method for evaluating asset-liability risk in portfolios, especially with complex products, focusing on risk measures like value-at-risk and expected shortfall.

Contribution

It introduces a novel neural network framework for conditional valuation of portfolios with complex instruments, addressing a key challenge in risk assessment.

Findings

Effective in banking and insurance examples

Handles structured products without closed-form valuation

Applicable to various risk measures

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.