Klasifikasi Penentuan Kelayakan Pemberian Kredit Menggunakan Metode Naive Bayes Classifier (Kasus: Koperasi Simpan Pinjam Artha Segara)

Abstract

Artha Segara Savings and Loans Cooperative is a company that provides savings and loan services to customers. In providing savings and loan services, it is not uncommon for customers to experience delays in paying bills or what is called bad credit. Bad credit is where the customer cannot do or is unable to pay the bill in part or all of the obligations as agreed. The cooperative must analyze the causes of the occurrence of bad loans using credit data that have been previously owned. Credit data owned by the Artha Segara Savings and Loans Cooperative can be analyzed using Data Mining. Where the data are classified using the Naïve Bayes Classifier method in calculating the probability level for each value of the target attribute in each customer credit case. The Naïve Bayes Classifier method can be used in several Data Mining tools or applications, one of which is the Orange Data Mining tool. The output of the Orange Data Mining system is the result of classification of customer credit data that is eligible or not eligible to reapply for credit. Researchers tested customer credit datasets from 2018 to 2020 as many as 1,200 data by dividing the dataset into 2 types of data, namely training data (training data) and test data (testing data). Comparison of training data and testing data is 70%:30%. Testing of training data as much as 840 data and testing data of 360 data produces 99.8% accuracy rate