Skip to content

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

A bank's risk team builds a credit scoring model using customer data from a ten-year period of strong economic growth. After a recession begins, the model badly underestimates defaults. Which source of model risk best describes this failure?

The failure stems from development data that was unrepresentative of stressed conditions. A model calibrated only on a growth period understates defaults in a recession, so the problem lies in data and assumptions rather than coding, overrides or documentation.

  1. AUsing development data that is not representative of the conditions in which the model is appliedCorrect
  2. BA coding error in the model's production implementation
  3. CExcessive reliance on manual overrides by loan officers
  4. DFailure to document the model inventory

Explanation

The model was calibrated only on benign conditions, so its estimates do not hold in a downturn. This is a data and assumption limitation, not an implementation or governance defect. The coding error option would produce errors even in normal conditions, which is not the pattern described.

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