© 1992 by Institute of Mathematics and its Applications
The benefit to consumers from generic scoring models based on credit reports
The MDS Group Atlanta, Georgia
Credit Research Center, Purdue University
Received on 1 July 1991. The benefit to consumers from the use of informative credit reports is demonstrated by showing the improvement in credit decisions when generic scoring models based on credit reports are implemented. If these models are highly predictive, then the truncation of credit reports will reduce the predictive power of bureau-based generic scoring systems. As a result, more good credit risks will be denied credit, and more poor credit risks will be granted credit. It is shown that, even when applied to credit applications that had already been screened and approved, the use of generic scoring models significantly improves credit grantors' ability to predict and eliminate bankruptcies, charge-offs, and delinquencies. As applied to existing accounts, bureau-based generic scores are shown to have predictive value for at least 3 months, while scores 12 months old may not be very powerful. Even though bureau-based scores shift towards the high-risk end of the distribution during a recession, they continue to rank risk very well. When coupled with application-based credit-scoring models, scores based on credit-bureau data further improve the predictive power of the model-the improvements being greater with more complete bureau information. We conclude that government-imposed limits on credit information are anti-consumer by fostering more errors in credit decisions.