Seonglae ChoShapley Additive exPlanations, Shapley Values
A classical method for interpreting AI that quantifies how much each feature contributes to a prediction
- The goal of SHAP is to explain the prediction of an instance x by computing the contribution of each feature to the prediction
- Build around idea of Shapley values (assume feature is a player and combination as colition)
SHAP variants
- KernelSHAP
- TreeSHA
SHAP interpretation methods
- SHAP Feature Importance
- SHAP Summary Plot
- SHAP Dependence Plot
- SHAP Interaction Values
