How is a credit scoring model developed?

To develop a model, a creditor or an organization skilled at mathematical modeling selects a random sample of customers or a sample of similar customers if their sample is not large enough, and analyzes it statistically to identify characteristics that relate to creditworthiness. Then, each of these factors is assigned a weight based on how strong a predictor it is of who would be a good credit risk. Each creditor may use its own credit scoring model, different scoring models for different types of credit, or a generic model developed by a credit scoring company.

Under the Equal Credit Opportunity Act, a credit scoring system may not use certain characteristics like -- race, sex, marital status, national origin, or religion -- as factors. However, creditors are allowed to use age in properly designed scoring systems. But any scoring system that includes age must give equal treatment to elderly applicants.

How reliable is the credit scoring system?

Credit scoring systems enable creditors to evaluate millions of applicants consistently and impartially on many different characteristics. But to be statistically valid, credit-scoring systems must be based on a big enough sample. Remember that these systems generally vary from creditor to creditor.

Although you may think such a system is arbitrary or impersonal, it can help make decisions faster, more accurately, and more impartially than individuals when it is properly designed. And many creditors design their systems so that in marginal cases, applicants whose scores are not high enough to pass easily or are low enough to fail absolutely are referred to a credit manager who decides whether the company or lender will extend credit. This may allow for discussion and negotiation between the credit manager and the consumer.