The Implementation Of Naive Bayes Method In Classification Of Good And Problem Customers At PT. Adira Finance

Abstract

The problem that often arises is the number of customers who have problems paying installments, so the collectibility is not smooth. Customer installment payments affect their performance and existence in everyday life. We need a way to find out how the customer's installment payment pattern is so that it can be classified whether the customer is good or problematic so that the company can overcome the problem early on. The implementation of Naive Bayes Method in the classification of good and problem customers at PT. Adira Finance is a platform that can be used to determine whether a customer is classified as a good customer or a problem customer based on 4 (four) aspects of the assessment. The 4 (four) aspects of the assessment are financing, installments, time period, and income. The classification of customer data is done by comparing the training data that has been previously inputted with the test data for which you want to know the classification. The final result of the classification is the probability value of good and problematic customers by looking at the highest value. Based on the tests that have been carried out using the Black Box Method, the results show that the functionality of the application for determining customer classification is good and has problems at PT. Adira Finance has run as expected and the application is able to display the results of the classification of good and problem customer data.