Towards Data Science is a community-powered publication that showcases work in data science, machine learning and artificial intelligence. Every day newcomers, seasoned researchers and industry practitioners publish tutorials, research notes and real-world case studies that help the field move forward.

Towards Data Science

The Kolmogorov-Smirnov (KS) statistic measures the maximum gap between cumulative distributions of defaulters and non-defaulters in credit risk models. Banks use this metric to evaluate model strength rather than set thresholds, with KS values below 20 considered weak, 20-40 acceptable, and 50-70 indicating good models. The calculation involves sorting applicants by predicted probability, computing cumulative rates for each group, and finding the maximum absolute difference between them.

The Kolmogorov–Smirnov Statistic, Explained: Measuring Model Power in Credit Risk Modeling

But does everyone get their loan application approved?

Do banks decide the threshold based on the KS Statistic?