PENENTUAN KELAYAKAN PENERIMA PEMBIAYAAN KREDIT MENGGUNAKAN METODE NAIVE BAYES DAN ALGORITMA C4.5 (Studi Kasus) KSPPS. BMT ADIL BERKAH SEJAHTERA

Tri Ardiyanto, TriA and Handoyo Widi Nugroho, HandoyoWN (2023) PENENTUAN KELAYAKAN PENERIMA PEMBIAYAAN KREDIT MENGGUNAKAN METODE NAIVE BAYES DAN ALGORITMA C4.5 (Studi Kasus) KSPPS. BMT ADIL BERKAH SEJAHTERA. Masters thesis, INFORMATICS & BUSINESS INSTITUTE DARMAJAYA BANDAR LAMPUNG.

[img] Text
COVER.pdf
Download (805kB)
[img] Text
Peryataan, pengesahan, persetujuan cetak.pdf
Download (3MB)
[img] Text
KATA PENGANTAR & MOTO.pdf
Download (46kB)
[img] Text
ABSTRACT .pdf
Download (35kB)
[img] Text
DAFTAR ISI.pdf
Download (217kB)
[img] Text
BAB I.pdf
Download (107kB)
[img] Text
BAB II.pdf
Download (332kB)
[img] Text
BAB III.pdf
Download (418kB)
[img] Text
BAB IV.pdf
Download (1MB)
[img] Text
BAB V.pdf
Download (33kB)
[img] Text
DAFTAR PUSTAKA DAN LAMPIRAN.pdf
Download (1MB)

Abstract

Cooperatives are part of the economic order of the community, which in their activities participate in realizing a prosperous economic life of the community. One of the benefits of cooperatives that greatly helps the community's economy is the savings and loans provided by cooperatives with low interest. In its implementation, cooperative businesses are often constrained by problems with non-current or bad credit returns. If this situation continues, the operation of the cooperative will certainly be disrupted. For this reason, screening is needed to determine the eligibility of customers to receive loans from cooperatives. Several studies on customer determination and prediction have been carried out with several methods, including using Naive Bayes and C4.5 algorithms which produce high accuracy. For this reason, in this study, a determination of customer eligibility was carried out in applying for credit at KSPPS. BMT Adil Berkah Sejahtera. The predictor attributes used in this study are gender, type of business, status of place of business, period of return, loan amount, guarantee, income, credit history, and credit smoothness and one target is feasible and unfeasible. In this study, the RapidMinner tool was used while the accuracy test used the confusion matrix method. From the results of the study, the C4.5 algorithm has a better accuracy of 91.23% while the accuracy of Naive Bayes only reaches 89.80%. Keywords : classification, bad debt, naïve bayes, C4.5 algorithm

Item Type: Thesis (Masters)
Subjects: Ilmu Komputer
eTheses
Divisions: Pasca Sarjana > Magister Teknik Informatika
Depositing User: Tri Ardianto
Date Deposited: 05 Jul 2023 07:51
Last Modified: 05 Jul 2023 07:51
URI: http://repo.darmajaya.ac.id/id/eprint/12174

Actions (login required)

View Item View Item