Applied of Classification Technique in Data Mining For Credit Scoring

In the development of the banking business, credit issues remain interesting to study and uncover. Most of the problems occur not in the system implemented by the bank, but the problem occurs precisely in the human resources who manage credit, either in their relationship with consumers or in errors...

Full description

Saved in:
Bibliographic Details
Main Authors: Heriyanto Heriyanto, Ika Kurniawati, Fachri Amsury, Muhammad Rizki Fahdia, Irwansyah Saputra, Nanang Ruhyana, Asrul
Format: Article
Language:English
Published: Universitas Teknologi Akba Makassar, Lembaga Penelitian dan Pengabdian Masyarakat 2022-12-01
Series:Inspiration
Subjects:
Online Access:https://ojs.unitama.ac.id/index.php/inspiration/article/view/17
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832583793721999360
author Heriyanto Heriyanto
Ika Kurniawati
Fachri Amsury
Muhammad Rizki Fahdia
Irwansyah Saputra
Nanang Ruhyana
Asrul
author_facet Heriyanto Heriyanto
Ika Kurniawati
Fachri Amsury
Muhammad Rizki Fahdia
Irwansyah Saputra
Nanang Ruhyana
Asrul
author_sort Heriyanto Heriyanto
collection DOAJ
description In the development of the banking business, credit issues remain interesting to study and uncover. Most of the problems occur not in the system implemented by the bank, but the problem occurs precisely in the human resources who manage credit, either in their relationship with consumers or in errors on the part of the bank which mispredicts in assessing consumers who apply for credit. Several studies in the computer field have been carried out to reduce credit risk which causes losses to the company. In this study, a comparison of the Naive Bayes, C4.5 and KNN algorithms was carried out which was applied to consumer data that received credit eligibility for good and bad customers. The best prediction results are nave Bayes with an accuracy of 95.95 % and an AUC of 0.974. The results of this classification are implemented in the form of a website-based application that can be used to facilitate related parties in the credit scoring system.
format Article
id doaj-art-888dc8d33602456686292c03949324b8
institution Kabale University
issn 2088-6705
2621-5608
language English
publishDate 2022-12-01
publisher Universitas Teknologi Akba Makassar, Lembaga Penelitian dan Pengabdian Masyarakat
record_format Article
series Inspiration
spelling doaj-art-888dc8d33602456686292c03949324b82025-01-28T05:31:39ZengUniversitas Teknologi Akba Makassar, Lembaga Penelitian dan Pengabdian MasyarakatInspiration2088-67052621-56082022-12-011229710410.35585/inspir.v12i2.1717Applied of Classification Technique in Data Mining For Credit ScoringHeriyanto Heriyanto0Ika Kurniawati1Fachri Amsury2Muhammad Rizki Fahdia3Irwansyah Saputra4Nanang Ruhyana5Asrul6Universitas Nusa MandiriUniversitas Nusa MandiriUniversitas Nusa MandiriUniversitas Nusa MandiriUniversitas Nusa MandiriUniversitas Nusa MandiriUniversitas Teknologi Akba MakassarIn the development of the banking business, credit issues remain interesting to study and uncover. Most of the problems occur not in the system implemented by the bank, but the problem occurs precisely in the human resources who manage credit, either in their relationship with consumers or in errors on the part of the bank which mispredicts in assessing consumers who apply for credit. Several studies in the computer field have been carried out to reduce credit risk which causes losses to the company. In this study, a comparison of the Naive Bayes, C4.5 and KNN algorithms was carried out which was applied to consumer data that received credit eligibility for good and bad customers. The best prediction results are nave Bayes with an accuracy of 95.95 % and an AUC of 0.974. The results of this classification are implemented in the form of a website-based application that can be used to facilitate related parties in the credit scoring system.https://ojs.unitama.ac.id/index.php/inspiration/article/view/17c4.5credit scoringdata miningk-nnnaïve bayes
spellingShingle Heriyanto Heriyanto
Ika Kurniawati
Fachri Amsury
Muhammad Rizki Fahdia
Irwansyah Saputra
Nanang Ruhyana
Asrul
Applied of Classification Technique in Data Mining For Credit Scoring
Inspiration
c4.5
credit scoring
data mining
k-nn
naïve bayes
title Applied of Classification Technique in Data Mining For Credit Scoring
title_full Applied of Classification Technique in Data Mining For Credit Scoring
title_fullStr Applied of Classification Technique in Data Mining For Credit Scoring
title_full_unstemmed Applied of Classification Technique in Data Mining For Credit Scoring
title_short Applied of Classification Technique in Data Mining For Credit Scoring
title_sort applied of classification technique in data mining for credit scoring
topic c4.5
credit scoring
data mining
k-nn
naïve bayes
url https://ojs.unitama.ac.id/index.php/inspiration/article/view/17
work_keys_str_mv AT heriyantoheriyanto appliedofclassificationtechniqueindataminingforcreditscoring
AT ikakurniawati appliedofclassificationtechniqueindataminingforcreditscoring
AT fachriamsury appliedofclassificationtechniqueindataminingforcreditscoring
AT muhammadrizkifahdia appliedofclassificationtechniqueindataminingforcreditscoring
AT irwansyahsaputra appliedofclassificationtechniqueindataminingforcreditscoring
AT nanangruhyana appliedofclassificationtechniqueindataminingforcreditscoring
AT asrul appliedofclassificationtechniqueindataminingforcreditscoring