https://github.com/slundberg/shap

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

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

Last synced: 5 days ago
JSON representation

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

• Host: GitHub
• URL: https://github.com/slundberg/shap
• Owner: shap
• License: mit
• Created: 2016-11-22T19:17:08.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2025-06-25T20:02:53.000Z (11 days ago)
• Last Synced: 2025-06-25T21:19:30.119Z (11 days ago)
• Topics: deep-learning, explainability, gradient-boosting, interpretability, machine-learning, shap, shapley
• Language: Jupyter Notebook
• Homepage: https://shap.readthedocs.io
• Size: 279 MB
• Stars: 24,039
• Watchers: 245
• Forks: 3,385
• Open Issues: 701
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-python-machine-learning - SHAP - SHAP (SHapley Additive exPlanations) is a unified approach to explain the output of any machine learning model. (Uncategorized / Uncategorized)
• awesome-production-machine-learning - SHAP - SHapley Additive exPlanations is a unified approach to explain the output of any machine learning model. (Explaining Black Box Models and Datasets)
• awesome-ai-ethics - SHAP (SHapley Additive exPlanations) - A unified framework for interpreting machine learning model predictions. (Explainable AI (XAI))
• awesome-ai-testing-tools - https://github.com/slundberg/shap
• awesome-list - shap - A game theoretic approach to explain the output of any machine learning model. (Linear Algebra / Statistics Toolkit / Statistical Toolkit)
• awesome-mlops - SHAP - A game theoretic approach to explain the output of any machine learning model. (Model Interpretability)
• awesome-open-data-centric-ai - SHAP