Question

A bank uses a machine learning model to approve or deny personal loan applications. Regulators require the bank to provide each rejected applicant with a clear reason showing which specific input factors (such as income, debt ratio, or credit history) most influenced the individual decision. Which AWS capability best addresses this requirement?

Accepted Answer

Amazon SageMaker Clarify feature attribution using SHAP values for individual predictions

Answer

Amazon Bedrock Guardrails with a denied topics policy applied to model outputs

Answer

Amazon SageMaker Model Monitor to detect data drift in incoming applications

Answer

Amazon SageMaker Clarify pre-training bias metrics on the training dataset