Papers › Statistical Aspects of SHAP: Functional ANOVA for Model Interpretation

Statistical Aspects of SHAP: Functional ANOVA for Model Interpretation

21 Aug 2022arXiv:2208.09970archive 2025-07-28

Andrew Herren, P. Richard Hahn

SHAP is a popular method for measuring variable importance in machine learning models. In this paper, we study the algorithm used to estimate SHAP scores and outline its connection to the functional ANOVA decomposition. We use this connection to show that challenges in SHAP approximations largely relate to the choice of a feature distribution and the number of 2ᵖ ANOVA terms estimated. We argue that the connection between machine learning explainability and sensitivity analysis is illuminating in this case, but the immediate practical consequences are not obvious since the two fields face a different set of constraints. Machine learning explainability concerns models which are inexpensive to evaluate but often have hundreds, if not thousands, of features. Sensitivity analysis typically deals with models from physics or engineering which may be very time consuming to run, but operate on a comparatively small space of inputs.

PaperPDFCode

Code

andrewherren/shap-anova-examples officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Sensitivity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SHAP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections