Skip to content

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

A bank's credit card loss forecasting model was built using data from a long period of economic expansion. During a sharp recession, actual losses far exceed forecasts, although the model's code runs exactly as designed and the inputs are accurate. Which source of model risk best explains the failure?

The best explanation is use of the model outside the conditions reflected in its development data. It was calibrated only on expansion-period data, so its assumptions failed in a recession, even though the code and inputs were correct.

  1. AImplementation error in the software code
  2. BUse of the model outside the conditions reflected in its development dataCorrect
  3. CData entry errors in the production feed
  4. DInadequate documentation of the model's version history

Explanation

The model was calibrated only on expansion-period data, so its assumptions did not hold in a recession. The code and data were stated to be correct, which rules out implementation and data-entry errors. Documentation weaknesses would not by themselves cause the forecast gap.

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