Discussion Papers, Interdisciplinary Research Project 373: Quantification and Simulation of Economic Processes 2002,67
We discuss how to assess the performance for credit scores under the assumption that for credit data only a part of the defaults and nondefaults is observed. The paper introduces a criterion that is based on the difference of the score distributions under default and nondefault. We show how to estimate bounds for this criterion, the Gini coefficient and the accuracy ratio.
credit rating credit score discriminatory power sample selection Gini coefficient accuracy ratio