A financial regulator asks a bank to explain why its AI credit model denied a specific customer's application. The model is a deep neural network with 50 layers. Which approach BEST satisfies the regulator's request while remaining technically honest?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — a is correct because SHAP (SHapley Additive exPlanations) provides individualized feature-level explanations for specific predictions — translating the contribution of each feature to the denial decision into plain language satisfies regulatory explanation requirements while being technically grounded. B provides raw model weights that are meaningless to regulators.
Full explanation below image
Full Explanation
A is correct because SHAP (SHapley Additive exPlanations) provides individualized feature-level explanations for specific predictions — translating the contribution of each feature to the denial decision into plain language satisfies regulatory explanation requirements while being technically grounded. B provides raw model weights that are meaningless to regulators. C is factually incorrect — post-hoc explainability methods exist. D is post-hoc rationalization, not an honest explanation of the actual model's decision.