Skip to content

FRM Part II · FRM Exam Part II · Credit Scoring and Retail Credit Risk Management

A retail lender builds a scorecard using only approved applicants' repayment outcomes, then validates it on those same approved accounts. Which bias most threatens the validity of the performance metrics for the full through-the-door population, and what is a common remedy?

The main threat is sample selection bias, since outcomes exist only for approved applicants and not for declined ones. Reject inference techniques estimate how rejected applicants would have performed, making validation and development better reflect the full through-the-door population.

  1. AReject inference bias (sample selection); apply reject inference techniques to estimate outcomes of declined applicantsCorrect
  2. BLook-ahead bias; shorten the observation window
  3. CSurvivorship bias in the bureau; purchase more bureau data
  4. DModel overfitting; remove all variables with low weight

Explanation

Using only accepted applicants creates sample selection bias because rejected applicants' outcomes are unobserved. Reject inference methods such as augmentation or parceling estimate their likely performance. The other options do not address the missing declined population.

Did you get it right without looking?

One question tells you little. A timed set on Credit Scoring and Retail Credit Risk Management shows your real accuracy, how long you take and where you lose marks.

Practise Credit Scoring and Retail Credit Risk ManagementFree diagnostic mock

More Credit Scoring and Retail Credit Risk Management questions