1 repo
Awesome GitHub RepositoriesFeature Attribution Methods
Techniques for decomposing model predictions into individual feature contributions.
Distinguishing note: Focuses on the mathematical decomposition of model outputs, distinct from general model monitoring.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Feature Attribution Methods. Refine with filters or upvote what's useful.
Awesome Feature Attribution Methods GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- shap/shap
shap/shap
25,049View on GitHubSHAP 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
Decomposes model predictions into a sum of individual feature effects to ensure the total output matches the sum of contributions.
Jupyter Notebookdeep-learningexplainabilitygradient-boosting
