Optimal bipartite scorecards

Authors:
David J. Hand;So Young Sohn;Yoonseong Kim
Affiliations:
Department of Mathematics, Imperial College, London, UK;Department of Computer Science and Industrial Engineering, Yonsei University, Shinchondong 134, Seoul, South Korea;Department of Computer Science and Industrial Engineering, Yonsei University, Shinchondong 134, Seoul, South Korea
Venue:
Expert Systems with Applications: An International Journal
Year:
2005

Citing 1
Cited 2

Credit Scoring and Its Applications

Credit Scoring and Its Applications

A Tripartite Scorecard for the Pay/No pay Decision-Making in the Retail Banking Industry

Proceedings of the 2008 conference on Applications of Data Mining in E-Business and Finance
Does segmentation always improve model performance in credit scoring?

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	12.05

Visualization

Abstract

In many retail banking applications, scorecards used for assessing creditworthiness must be simple and interpretable. For this reason, the industry has favoured logistic regression models based on categorised variables. In this paper we describe an extension of such models based on an optimal partition of the applicant population into two subgroups, with categorised logistic models being built in each part. Such bipartite models have the merits of yielding improved predictive accuracy, while retaining interpretive simplicity. They have been used in the industry before, but only in an ad hoc way, with no effort being made to find the optimal division. Some examples and properties of the resulting models are described.