Skip to content

FRM Part II · FRM Exam Part II · Case Study: Model Risk and Model Validation

A bank's credit-scoring model is used to price retail loans. The model risk team wants to reduce the chance that errors in model design go unnoticed before the model enters production. Which control is most directly aimed at this objective?

Independent validation before approval is the control aimed at catching design errors. Validators who did not build the model provide effective challenge to its assumptions, data and implementation. Developer self-approval lacks independence, and revenue reports or limited use do not test whether the model is sound.

  1. AIndependent validation by staff who did not build the model, performed before approval for useCorrect
  2. BAllowing the model developers to sign off on their own back-testing results to speed deployment
  3. CIncreasing the frequency of management reports on the model's revenue contribution
  4. DRestricting the model's use to a single business line without any documentation

Explanation

Effective challenge by an independent party with the competence and standing to question the developers is a core model risk control. It identifies conceptual and implementation errors before the model is used. Self-sign-off removes independence, and revenue reporting or narrowing use does not test model soundness.

Did you get it right without looking?

One question tells you little. A timed set on Case Study: Model Risk and Model Validation shows your real accuracy, how long you take and where you lose marks.

Practise Case Study: Model Risk and Model ValidationFree diagnostic mock

More Case Study: Model Risk and Model Validation questions