https://github.com/shap/shap

A game theoretic approach to explain the output of any machine learning model.
https://github.com/shap/shap

deep-learning explainability gradient-boosting interpretability machine-learning shap shapley

Last synced: 3 months ago
JSON representation

A game theoretic approach to explain the output of any machine learning model.

• Host: GitHub
• URL: https://github.com/shap/shap
• Owner: shap
• License: mit
• Created: 2016-11-22T19:17:08.000Z (about 9 years ago)
• Default Branch: master
• Last Pushed: 2025-09-02T04:23:15.000Z (3 months ago)
• Last Synced: 2025-09-04T05:00:40.175Z (3 months ago)
• Topics: deep-learning, explainability, gradient-boosting, interpretability, machine-learning, shap, shapley
• Language: Jupyter Notebook
• Homepage: https://shap.readthedocs.io
• Size: 280 MB
• Stars: 24,341
• Watchers: 248
• Forks: 3,421
• Open Issues: 690
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

• my-awesome-starred - shap/shap - A game theoretic approach to explain the output of any machine learning model. (Jupyter Notebook)
• awesome-learning - SHAP - A game theoretic approach to explain the output of any machine learning model. (Learning)
• my-awesome - shap/shap - learning,explainability,gradient-boosting,interpretability,machine-learning,shap,shapley pushed_at:2025-11 star:24.7k fork:3.4k A game theoretic approach to explain the output of any machine learning model. (Jupyter Notebook)
• awesome-cv - SHAP
• awesome-production-machine-learning - SHAP - SHapley Additive exPlanations is a unified approach to explain the output of any machine learning model. (Explainability and Fairness)
• awesome-data-analysis - SHAP - Game theoretic approach to explain the output of any machine learning model. (🤖 Machine Learning & AI / Tools)