A WEB-BASED CREDITWORTHINESS DECISION SUPPORT SYSTEM USING THE NAIVE BAYES METHOD (Case Study: Savings and Loans Cooperative, Tepian Taduh, Sintang Regency)

YUSEFIN, VERONIKA YUSIANA (2026) A WEB-BASED CREDITWORTHINESS DECISION SUPPORT SYSTEM USING THE NAIVE BAYES METHOD (Case Study: Savings and Loans Cooperative, Tepian Taduh, Sintang Regency). Tugas Akhir thesis, University of Technology Yogyakarta.

[img] Text
5220411002_Veronika_Abstrak.pdf
Download (142kB)

Abstract

ABSTRACT Tepian Taduh Savings and Loan Cooperative (KSP) faces challenges in assessing creditworthiness as its membership and data complexity increase. The conventional assessment procedures currently in use result in inconsistent decisions and a high risk of bad debt. This study aims to develop a web-based Decision Support System (DSS) that employs the Naive Bayes algorithm to objectively automate creditworthiness classification. The system development follows the Waterfall model and utilizes 6,883 historical member records from 2024. The results demonstrate that the Naive Bayes algorithm delivers excellent performance, achieving 93% accuracy and an Area Under the Curve (AUC) of 0.96. This model exhibits strong conservative risk-mitigation characteristics, as indicated by a recall of 96% for the unfeasible class. Functional testing using Black Box Testing confirms that all system features, including confidence scoring and installment estimation, operate effectively. The implementation of this system has successfully enhanced operational efficiency, with an average processing time of 1.95 seconds per prediction, while also providing credit officers with transparency and objectivity to minimize the risk of non-performing loans at KSP Tepian Taduh. Keywords: Confidence Score, Creditworthiness, Cooperatives, Naïve Bayes, Decision Support System

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > T Technology (General) > T201 Patents. Trademarks
Divisions: Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User: Kaprodi S1 Informatika UTY
Date Deposited: 05 May 2026 03:48
Last Modified: 05 May 2026 03:48
URI: http://eprints.uty.ac.id/id/eprint/19780

Actions (login required)

View Item View Item
UTY Open Access is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.