Logo do repositório
 
Publicação

The Main Challenges of Machine Learning for Credit Scoring

2026-01-02Documento de conferência Acesso embargado
Ver registo simples
dc.contributor.authorPereira, Arthur
dc.contributor.authorAshofteh, Afshin
dc.contributor.institutionNOVA Information Management School (NOVA IMS)
dc.contributor.institutionInformation Management Research Center (MagIC) - NOVA Information Management School
dc.coverage.spatialCham, Switzerland
dc.date.accessioned2026-01-14T19:29:40Z
dc.date.available2026-01-14T19:29:40Z
dc.date.embargoedUntil2027-01-02
dc.date.issued2026-01-02
dc.descriptionPereira, A., & Ashofteh, A. (2026). The Main Challenges of Machine Learning for Credit Scoring: A Review. In Á. Rocha, F. J. García Peñalvo, R. Gonçalves, A. García-Holgado, & F. Moreira (Eds.), Proceedings of 19th Iberian Conference on Information Systems and Technologies (CISTI 2024) (Vol. 2, pp. 497–512). (Lecture Notes in Networks and Systems; Vol. 1747). Springer. https://doi.org/10.1007/978-3-032-12879-9_45
dc.description.abstractMachine learning models and new techniques have been widely researched in credit scoring. For most credit-scoring datasets, data is unbalanced since the “bad” class is usually lower in proportion than the “good” class. Also, the rejection rate is high in some fields, leading to sample bias when training the scores. This paper presents a literature review to address these concerns, bringing the most known techniques to solve them. 490 articles were initially screened in Scopus and Web of Science, of which 88 were subject to content analysis. The results show that a significant number of algorithms have been tested in different datasets. For the class imbalance problem, SMOTE (synthetic minority oversampling technique) is the most used technique, but robust machine learning techniques have also been introduced. Finally, it was noticed that there is a noticeable opportunity for combining different techniques for imbalanced data that can be explored in future research works as a research gap.en
dc.description.versionauthorsversion
dc.description.versionpublished
dc.format.extent16
dc.format.extent657713
dc.identifier.doi10.1007/978-3-032-12879-9_45
dc.identifier.isbn978-3-032-12878-2
dc.identifier.isbn978-3-032-12879-9
dc.identifier.issn2367-3370
dc.identifier.otherPURE: 95141760
dc.identifier.otherPURE UUID: 3f435b29-45cc-4553-9b0a-066ef3961979
dc.identifier.otherScopus: 105027528713
dc.identifier.otherWOS: 001737922700045
dc.identifier.urihttp://hdl.handle.net/10362/199145
dc.identifier.urlhttps://www.scopus.com/pages/publications/105027528713
dc.identifier.urlhttps://www.webofscience.com/wos/woscc/full-record/WOS:001737922700045
dc.language.isoeng
dc.peerreviewedyes
dc.publisherSpringer
dc.subjectCredit Scoring
dc.subjectCredit Risk
dc.subjectMachine Learning
dc.subjectReject Inference
dc.subjectUnbalanced Datasets
dc.subjectSmall and Medium Enterprises
dc.subjectControl and Systems Engineering
dc.subjectSignal Processing
dc.subjectComputer Networks and Communications
dc.subjectSDG 8 - Decent Work and Economic Growth
dc.subjectSDG 9 - Industry, Innovation, and Infrastructure
dc.titleThe Main Challenges of Machine Learning for Credit Scoringen
dc.title.subtitleA Reviewen
dc.typeconference object
degois.publication.firstPage
degois.publication.lastPage
degois.publication.titleProceedings of 19th Iberian Conference on Information Systems and Technologies (CISTI 2024)
degois.publication.title19th Iberian Conference on Information Systems and Technologies 2024
degois.publication.volume2
dspace.entity.typePublication
rcaap.rightsembargoedAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
Main_Challenge_of_ML_for_Credit_Scoring_AAM.pdf
Tamanho:
642.3 KB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

NIMS: MagIC - Documentos de conferências internacionais