engleski

Multinomial model in consumer credit scoring

Credit scoring is a process of determining how likely applicants are to default with their repayments. It has been used in consumer lending for more than three decades. The purpose of this paper is to investigate the predictive power of multinomial and binomial logit models in distinguishing between good, poor and bad applicants. Three binomial logit functions are estimated separately – bad versus good, bad versus poor and good versus poor. For the multinomial model, these three functions are estimated from a single estimation. The models are compared according to significant variables and classification accuracy.

credit scoring; generalized linear method; consumer credit

nije evidentirano