# Explaining Risks: Axiomatic Risk Attributions for Financial Models

arXiv: https://arxiv.org/abs/2506.06653 · HTML: https://mlsanity.com/paper/2506.06653/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 7 Jun 2025.

## Builds on (most cited first, 11 of 11)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions](https://mlsanity.com/paper/2202.11912/) (2022)
- [Monotonic Neural Additive Models: Pursuing Regulated Machine Learning Models for Credit Scoring](https://mlsanity.com/paper/2209.10070/) (2022)
- [Multicriteria interpretability driven Deep Learning](https://mlsanity.com/paper/2111.14088/) (2021)
- [Four Axiomatic Characterizations of the Integrated Gradients Attribution Method](https://mlsanity.com/paper/2306.13753/) (2023)
- [Variance Allocation and Shapley Value](https://mlsanity.com/paper/1606.09424/) (2016)
- [How to address monotonicity for model risk management?](https://mlsanity.com/paper/2305.00799/) (2023)
- [Portfolio risk allocation through Shapley value](https://mlsanity.com/paper/2103.05453/) (2021)
- [Attribution Methods in Asset Pricing: Do They Account for Risk?](https://mlsanity.com/paper/2407.08953/) (2024)

## Abstract (arXiv)

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.