Skip to content

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

Validators find that a bank's loan loss model was tuned so closely to the development sample that it fits historical noise and performs poorly on out-of-sample data. This is best described as which type of model risk?

This is overfitting: the model captures noise specific to the development sample, giving strong in-sample fit but poor out-of-sample predictions. It is a model construction weakness, detectable through out-of-sample testing, not a problem of scope, documentation, or aggregation.

  1. AOverfitting leading to poor generalizationCorrect
  2. BModel use outside its scope
  3. CStale documentation
  4. DAggregation of model outputs across business lines

Explanation

Overfitting occurs when a model captures random noise specific to the development sample, so in-sample fit is strong but out-of-sample performance is weak. It is a model construction weakness, detected by out-of-sample testing, rather than a use or documentation problem.

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