Credit scoring model based on Decision tree, Logit, K-nearest neighbor and neural network

Abstract

Credit scoring models have been widely studied in academic world and the business community. Over the last decades, there have been many studies in the field of credit conducted to improve the accuracy of credit scoring models. However, in Vietnam, there is not much research in this field. Most of researchs uses traditional techniques such as Logistic Regression (LR), discriminant analysis (DA), some others studies modern techniques included decision tree (DT), K-nearest neighbor (KNN), Artificial neural network (ANN). In this paper, we propose hybrid credit scoring models based on Decision Tree, Logistic Regression, K-nearest neighbor and artificial neural network. The experimental results demonstrate that DT_MLP hybrid credit scoring models is the most effective model.