# On Using the Shapley Value for Anomaly Localization: A Statistical Investigation

arXiv: https://arxiv.org/abs/2507.21023 · HTML: https://mlsanity.com/paper/2507.21023/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 28 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [Deep Learning for Anomaly Detection: A Survey](https://mlsanity.com/paper/1901.03407/) (2019)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Deep Learning for Anomaly Detection: A Review](https://mlsanity.com/paper/2007.02500/) (2020)
- [Explaining Predictive Uncertainty with Information Theoretic Shapley Values](https://mlsanity.com/paper/2306.05724/) (2023)
- [Shapley Values of Reconstruction Errors of PCA for Explaining Anomaly Detection](https://mlsanity.com/paper/1909.03495/) (2019)
- [Using Kernel SHAP XAI Method to optimize the Network Anomaly Detection Model](https://mlsanity.com/paper/2308.00074/) (2023)
- [A Characteristic Function for Shapley-Value-Based Attribution of Anomaly Scores](https://mlsanity.com/paper/2004.04464/) (2020)

## Built on by (most cited first, 1 of 1)

- [Statistical Analysis of using the Shapley Value for Sensor Anomaly Localization with Accurate Classifiers](https://mlsanity.com/paper/2606.00867/) (2026)

## Abstract (arXiv)

Recent publications have suggested using the Shapley value for anomaly localization for sensor data systems. Using a reasonable mathematical anomaly model for full control, experiments indicate that using a single fixed term in the Shapley value calculation achieves a lower complexity anomaly localization test, with the same probability of error, as a test using the Shapley value for all cases tested. A proof demonstrates these conclusions must be true for all independent observation cases. For dependent observation cases, no proof is available.