Explaining Risks: Axiomatic Risk Attributions for Financial Models

TL;DR

This paper introduces an axiomatic approach to fairly attribute risk in financial models using an extension of the Shapley value, enhancing interpretability of complex machine learning models in high-stakes sectors.

Contribution

It proposes a novel axiomatic risk attribution method based on Shapley values, specifically tailored for financial models, improving risk interpretability.

Findings

Risk can be effectively allocated using the extended Shapley value framework.

The method provides fair and interpretable risk attributions in complex models.

Empirical examples demonstrate the approach's practical effectiveness.

Abstract

In recent years, machine learning models have achieved great success at the expense of highly complex black-box structures. By using axiomatic attribution methods, we can fairly allocate the contributions of each feature, thus allowing us to interpret the model predictions. In high-risk sectors such as finance, risk is just as important as mean predictions. Throughout this work, we address the following risk attribution problem: how to fairly allocate the risk given a model with data? We demonstrate with analysis and empirical examples that risk can be well allocated by extending the Shapley value framework.