---
title: "SHAP"
description: "SHapley Additive exPlanations: a feature-attribution method that assigns each input feature a share of a particular prediction, based on Shapley values; its explanations depend on the chosen…"
canonical: https://aigovernanceengineer.com/glossary/shap
author: "Jorge García Aibar"
license: "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)"
doi: https://doi.org/10.5281/zenodo.22956197
version: "0.5.0"
updated: 2026-09-24
---

# SHAP

SHapley Additive exPlanations: a feature-attribution method that assigns each input feature a share of a particular prediction, based on Shapley values [1]; its explanations depend on the chosen baseline or background data.

- Developed in: [ch. 16, Feature attribution: SHAP, LIME and integrated gradients](https://aigovernanceengineer.com/bok/fairness-and-explainability#feature-attribution-shap-lime-and-integrated-gradients)
- Chapters: [ch. 16, Fairness & XAI](https://aigovernanceengineer.com/bok/fairness-and-explainability)
- Contrast with: [LIME](https://aigovernanceengineer.com/glossary/lime)
- In the glossary chapter: https://aigovernanceengineer.com/bok/glossary#t-shap

## Sources

[1] "A Unified Approach to Interpreting Model Predictions" (Lundberg and Lee; SHAP; arXiv 1705.07874). arXiv. 2017-05-22. https://arxiv.org/abs/1705.07874 (verified: primary)