shap - Explain machine learning predictions with SHAP.
Compute SHAP values, visualize feature importance, explain predictions, debug models, compare models, and analyze bias or fairness across supported model types.
Tags
Updated: 2026-10-04Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Compute SHAP values
- Generate SHAP plots
- Explain individual predictions
- Analyze feature importance
- Debug model behavior
- Compare multiple models
- Analyze bias and fairness
- Implement explainable AI
Inputs
- Trained machine learning model
- Input or test data
- Model output type
- Background data
- Protected-group attributes
- Ground-truth labels
Outputs
- SHAP values
- Feature importance visualizations
- Individual prediction explanations
- Model debugging findings
- Model comparison analyses
- Bias and fairness analyses
- Explainability implementation guidance
Requirements
- SHAP library
- Supported machine learning model