Reject Inference

A technique used to infer hidden patterns in credit scoring and risk assessment. It estimates the creditworthiness of applicants who were not approved for loans, which helps improve the accuracy and fairness of the decision-making process.

Example

Suppose a bank has a dataset of loan applicants, including both approved and rejected applicants. When building a credit scoring model, the bank only has performance data for approved applicants. Reject Inference helps the bank estimate the creditworthiness of rejected applicants, despite missing performance data. This lets the bank refine its decision-making process and assess future applicants more fairly and accurately. It can also help identify creditworthy individuals who were previously overlooked.