A hybrid approach to credit risk assessment using bill payment habits data and explainable artificial intelligence

Basit Öğe Kaydı
dc.authorid0000-0002-4434-4871
dc.authorid0000-0003-4668-392X
dc.contributor.authorBulut, Cem
dc.contributor.authorArslan, Emel
dc.date.accessioned2025-06-21T13:49:33Z
dc.date.available2025-06-21T13:49:33Z
dc.date.issued2025
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Yazılım Mühendisliği Bölümü
dc.description.abstractCredit risk is one of the most important issues in the rapidly growing and devel oping finance sector. This study utilized a dataset containing real information about the bill payments of individuals who made transactions with a payment institution operating in Turkey. First, the transactions in the dataset were analyzed based on the bill type and the individual and features reflecting the payment habits were extracted. For the target class, real credit scores generated by the Credit Registry Office for the individuals whose payment habits were extracted were used. The dataset is a multi-class, unbalanced, and alternative dataset. Therefore, the dataset was prepared for the analysis by using data cleaning, feature selection, and sampling techniques. Then, the dataset was classified using various classification and evaluation methods. The best results were obtained with a model consisting of ANOVA F-Test, SMOTE, and Extra Tree algorithms. With this model, 80.49% accuracy, 79.89% precision, and 97.04% UAC rate were obtained. These results are quite efficient for an alternative dataset with 10 classes. This model was transformed into an explainable and interpretable form using LIME and SHAP, which are XAI techniques. This study presents a new hybrid model for credit risk assessment based on a multi-class and imbalanced alternative dataset and machine learning.
dc.identifier.citationBulut, C., & Arslan, E. (2025). A hybrid approach to credit risk assessment using bill payment habits data and explainable artificial intelligence. Applied Sciences, 15(10), pp. 1-28. https://doi.org/10.3390/app15105723
dc.identifier.doi10.3390/app15105723
dc.identifier.endpage28
dc.identifier.issn2076-3417
dc.identifier.issue10
dc.identifier.scopus2-s2.0-105006700627
dc.identifier.scopusqualityQ1
dc.identifier.startpage1
dc.identifier.urihttps://doi.org/10.3390/app15105723
dc.identifier.urihttps://hdl.handle.net/20.500.13055/1004
dc.identifier.volume15
dc.identifier.wosWOS:001495839800001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.indekslendigikaynak.otherSCI-E - Science Citation Index Expanded
dc.institutionauthorBulut, Cem
dc.institutionauthorid0000-0002-4434-4871
dc.language.isoen
dc.publisherMDPI Publishing
dc.relation.ispartofApplied Sciences
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectCredit Risk Assessment
dc.subjectMachine Learning
dc.subjectExplainable Artificial Intelligence (XAI)
dc.subjectResampling
dc.subjectLocal Interpretable Model Agnostic Explanations (LIME)
dc.subjectShapley Additive Explanations (SHAP)
dc.titleA hybrid approach to credit risk assessment using bill payment habits data and explainable artificial intelligence
dc.typeArticle
dspace.entity.typePublication
relation.isAuthorOfPublicationfb56c061-bb6e-40c5-a04f-fb3400e39bae
relation.isAuthorOfPublication.latestForDiscoveryfb56c061-bb6e-40c5-a04f-fb3400e39bae

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Tam Metin / Full Text
Boyut:
2.54 MB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Kapalı Erişim
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Yazılım Mühendisliği Bölümü
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu