explainable-ai

Two methods dominate local explanation, and both perturb the input. LIME fits a small interpretable model near one prediction. SHAP borrows the Shapley value from game theory and is the unique attribution satisfying local accuracy, missingness and consistency. This lesson builds both mechanisms, compares KernelSHAP with TreeSHAP, and is precise about what a SHAP value does not mean.

A model that predicts well can still be impossible to justify. This lesson maps explainable AI: interpretable-by-design versus post-hoc, global versus local, model-specific versus model-agnostic. It covers the global workhorses (permutation importance, partial dependence, ICE), faithfulness versus plausibility, and the argument that post-hoc explanation is the wrong tool for high-stakes decisions.

When a model is differentiable you can attribute a prediction with calculus instead of sampling. This lesson covers plain saliency, Integrated Gradients and its axioms, Grad-CAM, then counterfactual explanations, which answer what would have to change rather than what mattered. It closes with the evidence that explanations can fail or be deliberately faked, and a protocol for checking yours.

In banking, an accurate AI model is not enough; it must also be fair, explainable, and well-governed. Learn how AI can perpetuate lending bias and why fair-lending law forbids it, why consequential decisions must be explainable, how model risk management keeps banks safe, and why the institution, never the algorithm, remains accountable. The guardrails that make banking AI responsible.