Skip to content

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

A retail bank is building an application scorecard for personal loans using logistic regression. The analyst groups an applicant's age into bands and replaces each band with its weight of evidence (WOE) before fitting the model. What is the main purpose of this step?

Weight of evidence transformation expresses each binned characteristic as the log odds of good versus bad, giving a comparable, typically monotonic scale that handles nonlinearity and outliers. It does not guarantee significance, remove the need for validation, or make discrimination perfect.

  1. ATo convert the predictors into a monotonic, comparable log-odds scale and handle nonlinearity and outliersCorrect
  2. BTo guarantee that every predictor will have a statistically significant coefficient
  3. CTo remove the need for any out-of-sample validation
  4. DTo force the scorecard's Gini coefficient to equal one

Explanation

WOE is the log of the ratio of the distribution of goods to the distribution of bads in a bin. Using it places predictors on a common log-odds scale, tames outliers and captures nonlinear effects. It does not guarantee significance, replace validation or make the Gini perfect.

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