Prediction Model of Eligibility of Lending in Credit Banks Using The C4.5 Algorithm and Naive Bayes Method

Abstract

People's credit banks are financial institutions that collect funds from savings and channel them back in the form of credit. One form of credit owned by Rural Banks is installment credit which is intended for customers who want to increase business capital or other needs. To determine quickly and reduce the risk of non-performing loans in lending, To prevent bad loans, accurate forecasting is needed, one of which uses technology in the field of data mining. Naive Bayes predicts future probabilities based on previous experience by studying the correlation of hypotheses which are the class labels that are the target of mapping in the classification and evidence which is the features that are input in the classification model. Data processing based on data mining is expected to be used as a tool in predicting creditworthiness which estimates whether or not an applicant or customer is eligible for credit.