Application of AI in Credit Scoring Modeling

Scope of the Study

The scope of this study is to investigate the capability of AI methods to accurately detect and predict credit risks based on retail borrowers'' features.

Comparison of Methods

The comparison of logistic regression, decision tree, and random forest showed that machine learning methods are able to predict credit defaults of individuals more accurately than the logit model.

Model Sensitivity

Furthermore, it was demonstrated how random forest and decision tree models were more sensitive in detecting default borrowers.