An economic model for credit assessment problems using screening approaches

Abstract

How to combine varying credit information collected from various sources at difference periods for the purpose of credit assessment is an important issue for some financial companies. In this article, the screening procedures using individual cut and linear cut approaches are proposed to solve the issue and to control default rates in credit assessment problems. Then, an economic screening model is provided to incorporate with the proposed approaches so that optimal cutoff points are determined by maximizing total profit. An example of a loan programme is illustrated the use of the proposed economic screening procedures. The results show that the linear cut approach uniformly outperforms the individual cut approach in terms of total profit and computation complexity. Moreover, the linear cut approach can be easily extended to the case with multiple variables and the solution is also in a closed form. Therefore, the screening procedure using the linear cut approach is strongly recommended for credit assessment problems.

Keywords:

• credit
• scoring
• scorecard
• screening

Acknowledgements

The research was supported by the National Science Council, Republic of China, under Grant No. 89-2416-H-110-028 to the National Sun Yat-Sen University, Kaohsiung, Taiwan, ROC.