English

Explaining Risks: Axiomatic Risk Attributions for Financial Models

Computational Finance 2025-06-10 v1 Machine Learning Machine Learning

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.

Keywords

Cite

@article{arxiv.2506.06653,
  title  = {Explaining Risks: Axiomatic Risk Attributions for Financial Models},
  author = {Dangxing Chen},
  journal= {arXiv preprint arXiv:2506.06653},
  year   = {2025}
}

Comments

This article has been accepted for publication in Quantitative Finance, published by Taylor & Francis

R2 v1 2026-07-01T03:04:41.777Z