1 repo
Tools and algorithms for computing Shapley values to interpret machine learning model predictions.
Distinguishing note: Focuses specifically on model interpretability and feature attribution via tree-based methods, distinct from general-purpose machine learning frameworks.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Shapley Value Calculators. Refine with filters or upvote what's useful.
SHAP is an explainable AI toolkit that provides a game theoretic framework for interpreting machine learning model predictions. It functions as a feature attribution engine, decomposing model outputs into the sum of individual feature effects to clarify how specific input variables influence a final decision. By assigning importance values to these inputs, the library enables users to understand the logic behind complex predictive models. The project distinguishes itself through its versatility and specialized calculation methods. It operates as a model-agnostic diagnostic library, capable of
Calculates exact Shapley values for decision tree models to provide model interpretability without requiring retraining.