Prediction analysis of risky credit using Data mining classification models

Abstract

Customers benefit in a variety of ways from having a high credit score, while banks benefit from being able to evaluate their customers and provide credit properly thanks to this metric. This case In this work, we explore whether data mining approaches can accurately forecast and categories a customer's credit score (good/bad) in order to mitigate the potential future risks associated with lending money to borrowers who may not be able to pay back their loans. Our general models (predictive models) are built using a bank's historical information, and banks may utilize them to improve the results of their credit operations. If a consumer is given a poor credit score by one of these predictive categorization models, for instance, the bank would likely forbid further credit extensions to that person and conduct a thorough evaluation of any other potentially hazardous loans.