SHAP (SHapley Additive exPlanations) assigns importance values to features based on cooperative game theory. LIME approximates the model locally with an interpretable surrogate.
Key Uses:
Financial risk models, medical diagnosis systems, and regulatory compliance.
Hacks:
Use Kernel SHAP for model-agnostic explanations on tabular data. Visualize attention maps in transformers as an additional interpretability layer. Combine LIME with counterfactual explanations ("what if" analysis). Implement partial dependence plots alongside SHAP for global insights.
References:
Lundberg, S.M., & Lee, S.I. (2017). A Unified Approach to Interpreting Model Predictions. NeurIPS.
