3rd Asia Pacific International Conference on Industrial Engineering and Operations Management

Car Creditworthiness Classification Using Naive Bayes and Credit Scoring

Farhan Ariq, Yulison Chrisnanto, Ade Kania Ningsih & Faiza Renaldi
Publisher: IEOM Society International
0 Paper Citations
Track: Data Analytics and Big Data

Loans and their derivatives are one of the most important sources of income for financial services institutions such as banks and multi-finance companies. Challenges happen when customers cannot pay their monthly installments or are defined as bad credits. The use of data mining has been known to be able to predict the suitability of new credit applicants. Variables significantly influence the accuracy of car credit ratings. Although there have been many studies related to the determination of credit rating, they still have a low level of accuracy because of these variables. In this study, we use the Naïve Bayes method and combine it with credit scoring to weigh each variable. We also added more specific variables to increase the accuracy level. 10.000 data from a leasing company in Indonesia were used and produced a suitability level of 8,688. Calculations using credit scoring get a suitability value of 79%. Based on the test results, prospective debtors using the Naive Bayes method have an accuracy of approximately 89%. Further research is needed with better use of data that is already eligible for the convenience of the data training process.


Keywords — Naïve Bayes, Credit Scoring, Classification, multi-finance company

Published in: 3rd Asia Pacific International Conference on Industrial Engineering and Operations Management, Johor Bahru, Malaysia

Publisher: IEOM Society International
Date of Conference: September 13-15, 2022

ISBN: 978-1-7923-9162-0
ISSN/E-ISSN: 2169-8767