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 months 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 (about 9 years ago)
- Default Branch: master
- Last Pushed: 2025-06-25T20:02:53.000Z (6 months ago)
- Last Synced: 2025-06-25T21:19:30.119Z (6 months 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-deep-reinforcement-learning - slundberg/shap
- 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-list - shap - A game theoretic approach to explain the output of any machine learning model. (Linear Algebra / Statistics Toolkit / Statistical Toolkit)
- awesome-machine-learning-engineer - SHAP: SHapley Additive exPlanations - How to explain a model's output with Shapley values (30 min) (Machine Learning / Explainability)
- awesome-python-data-science - shap - A unified approach to explain the output of any machine learning model. <img height="20" src="img/sklearn_big.png" alt="sklearn"> (Model Explanation / NLP)
- Awesome-Uplift-Model - Shapley Value (SHAP)
- awesome_quantmetry - SHAP
- awesome-python-machine-learning-resources - GitHub - 69% open · ⏱️ 16.06.2022): (模型的可解释性)
- ai-links - GitHub - slundberg/shap: A game theoretic approach to explain the output of any machine learning model.
- AwesomeResponsibleAI - Shap
- Awesome-Ai-Tools - SHAP - Explain machine learning models. 🆓 (🛡️ AI Safety & Ethics / 🔒 AI Safety Tools)
- awesome-ai-testing-tools - https://github.com/slundberg/shap
- awesome-mlops - SHAP - A game theoretic approach to explain the output of any machine learning model. (Model Interpretability)
- awesome-explainable-reinforcement-learning - SHAP
- fucking-awesome-datascience - SHAP
- awesome-decision-tree-papers - [Code
- awesome-machine-learning-datascience_resources - Tree explainer using SHAP.
- Awesome-explainable-AI - https://github.com/slundberg/shap
- awesome-machine-learning-interpretability - shap -  | "a game theoretic approach to explain the output of any machine learning model. It connects optimal credit allocation with local explanations using the classic Shapley values from game theory and their related extensions" (Technical Resources / Open Source/Access Responsible AI Software Packages)
- awesome-decision-tree-papers - [Code
- awesome-meteo - shap
- awesome-xai - slundberg/shap - A Python module for using Shapley Additive Explanations. (Repositories / Critiques)
- awesome-python-data-science - shap - A unified approach to explain the output of any machine learning model. <img height="20" src="img/sklearn_big.png" alt="sklearn"> (Model Explanation / Others)
- awesome-datascience - SHAP
- awesome-open-data-centric-ai - SHAP
- awesome-python-data-science - shap - A unified approach to explain the output of any machine learning model. (Exploration)
- awesome-python-machine-learning - SHAP - SHAP (SHapley Additive exPlanations) is a unified approach to explain the output of any machine learning model. (Uncategorized / Uncategorized)