Skip to content

FRM Part II · FRM Exam Part II · Credit Scoring and Retail Credit Risk Management

A bank introduces a machine-learning model for retail credit decisions that is more accurate than its previous scorecard but is hard to interpret. From a model risk management perspective, which step is most important before deployment?

Independent validation is most important, covering conceptual soundness, explainability for adverse action and fair lending needs, and ongoing monitoring with documented limitations. Higher accuracy does not eliminate model risk, and developer testing alone lacks the effective challenge that supervisory guidance requires.

  1. ASkip independent validation because higher accuracy lowers model risk
  2. BPerform independent validation covering conceptual soundness, explainability for adverse action and fair lending, and ongoing monitoring with documented limitationsCorrect
  3. CRely on the developers' backtest as the sole evidence of performance
  4. DDeploy without documentation to protect proprietary methods

Explanation

Supervisory model risk guidance requires effective challenge by independent validation, covering conceptual soundness, outcomes analysis, and ongoing monitoring. Opaque models raise added concern for explainability and fair lending compliance. Accuracy does not remove model risk, and developer-only testing lacks independence.

Did you get it right without looking?

One question tells you little. A timed set on Credit Scoring and Retail Credit Risk Management shows your real accuracy, how long you take and where you lose marks.

Practise Credit Scoring and Retail Credit Risk ManagementFree diagnostic mock

More Credit Scoring and Retail Credit Risk Management questions