Skip to content

FRM Part II · FRM Exam Part II · Introduction to Credit Risk Modeling and Assessment

A credit scoring model ranks 1,000 borrowers. Its cumulative accuracy profile (CAP) shows an area ratio, defined as the area between the model CAP and the random model divided by the area between the perfect model and the random model, of 0.60. How should the Accuracy Ratio of 0.60 be interpreted?

An accuracy ratio of 0.60 means the model achieves 60% of the improvement over random ranking that a perfect model would deliver. It measures discrimination, not calibration or hit rate, and corresponds to an AUC of 0.80.

  1. AThe model correctly classifies 60% of borrowers as defaulters or non-defaulters
  2. BThe model captures 60% of the discriminatory power of a perfect model relative to a random modelCorrect
  3. CThe model's default probability estimates are 60% accurate on average
  4. DThe model has a 40% probability of ranking a defaulter above a non-defaulter

Explanation

The accuracy ratio measures discriminatory power relative to the perfect model, with random scoring at 0 and perfect at 1. It is not a classification hit rate or a calibration measure. Since AUC = (AR+1)/2 = 0.80, the chance of ranking a defaulter worse than a non-defaulter is 80%, not 40%.

Did you get it right without looking?

One question tells you little. A timed set on Introduction to Credit Risk Modeling and Assessment shows your real accuracy, how long you take and where you lose marks.

Practise Introduction to Credit Risk Modeling and AssessmentFree diagnostic mock

More Introduction to Credit Risk Modeling and Assessment questions