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

For calculating global feature importance using Shapley values.

The official implementation of "The Shapley Value of Classifiers in Ensemble Games" (CIKM 2021).

Shapley Interactions for Machine Learning

Explaining the output of machine learning models with more accurately estimated Shapley values

Reading list for "The Shapley Value in Machine Learning" (JCAI 2022)

Fast approximate Shapley values in R

Multi-Touch Attribution

ACV is a python library that provides explanations for any machine learning model or data. It gives local rule-based explanations for any model or data and different Shapley Values for tree-based models.

Amazon SageMaker Solution for explaining credit decisions.

A Julia package for interpretable machine learning with stochastic Shapley values

streamlit-shap provides a wrapper to display SHAP plots in Streamlit.

Break Down with interactions for local explanations (SHAP, BreakDown, iBreakDown)

An R package for computing asymmetric Shapley values to assess causality in any trained machine learning model

For calculating Shapley values via linear regression.

A lightweight implementation of removal-based explanations for ML models.

Package for a nice and smoothe usage of the shapley value for mlr

Shapley Values with H2O AutoML Example (ML Interpretability)

Counterfactual SHAP: a framework for counterfactual feature importance

Compute Shapley-Shorrocks value decompositions