Explainable Machine Learning Models for Credit Rating in Colombian Solidarity Sector Entities

Vista sencilla de ítem
dc.contributor.affiliationUniversidad de Medellín, Medellin, Colombia
dc.contributor.affiliationInstituto Tecnológico Metropolitano, Medellin, Colombia
dc.contributor.authorM.A., Arias-Serna, Maria Andrea
dc.contributor.authorJ.J., Quiza-Montealegre, Jhon Jair
dc.contributor.authorL.F., Montes-Gómez, Luis Fernando
dc.contributor.authorL.U., Clavijo, Leandro Uribe
dc.contributor.authorA., Orozco-Duque, Andrés
dc.date.accessioned2025-12-03T19:34:48Z
dc.date.available2025-12-03T19:34:48Z
dc.date.issued2025
dc.descriptionThis paper proposes a methodology for implementing a custom-developed explainability model for credit rating using behavioral data registered during the lifecycle of the borrowing that can replicate the score given by the regulatory model for the solidarity economy in Colombia. The methodology integrates continuous behavioral and financial variables from over 17,000 real credit histories into predictive models based on ridge regression, decision trees, random forests, XGBoost, and LightGBM. The models were trained and evaluated using cross-validation and RMSE metrics. LightGBM emerged as the most accurate model, effectively capturing nonlinear credit behavior patterns. To ensure interpretability, SHAP was used to identify the contribution of each feature to the model predictions. The presented model using LightGBM predicted the credit risk assessment in accordance with the regulatory model used by the Colombian Superintendence of the Solidarity Economy, with a root-mean-square error of 0.272 and an R2 score of 0.99. We propose an alternative framework using explainable machine learning models aligned with the internal ratings-based approach under Basel II. Our model integrates variables collected throughout the borrowing lifecycle, offering a more comprehensive perspective than the regulatory model. While the regulatory framework adjusts itself generically to national regulations, our approach explicitly accounts for borrower-specific dynamics. © 2025 Elsevier B.V., All rights reserved.
dc.identifier.doi10.3390/jrfm18090489
dc.identifier.instnameinstname:Universidad de Medellínspa
dc.identifier.issn19118074
dc.identifier.reponamereponame:Repositorio Institucional Universidad de Medellínspa
dc.identifier.repourlrepourl:https://repository.udem.edu.co/
dc.identifier.urihttps://hdl.handle.net/11407/9256
dc.language.isoeng
dc.publisherMultidisciplinary Digital Publishing Institute (MDPI)spa
dc.publisher.facultyFacultad de Ingenieríasspa
dc.publisher.programIngeniería Financieraspa
dc.publisher.programIngeniería de Telecomunicacionesspa
dc.relation.citationissue9
dc.relation.citationvolume18
dc.relation.isversionofhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-105017399909&doi=10.3390%2Fjrfm18090489&partnerID=40&md5=5840c391cabca557480cda0334d3e020
dc.relation.referencesMicaela Rev De Investig Unamba, (2024)
dc.relation.referencesAlsuhabi, Hassan, The new Topp-Leone exponentied exponential model for modeling financial data, Mathematical Modelling and Control, 4, 1, pp. 44-63, (2024)
dc.relation.referencesBermúdez, Iván Mauricio, Data Mining for the Adjustment of Credit Scoring Models in Solidarity Economy Entities: A Methodology for Addressing Class Imbalances, Risks, 13, 2, (2025)
dc.relation.referencesBischl, Bernd, Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 13, 2, (2023)
dc.relation.referencesJournal of Parametrics, (2006)
dc.relation.referencesArxiv, (2025)
dc.relation.referencesBussmann, Niklas, Explainable Machine Learning in Credit Risk Management, Computational Economics, 57, 1, pp. 203-216, (2021)
dc.relation.referencesChen, Tianqi, XGBoost: A scalable tree boosting system, 13-17-August-2016, pp. 785-794, (2016)
dc.relation.referencesBasilea III Marco Regulatorio Global Para Reforzar Los Bancos Y Los Ingeniería de Sistemas Bancarios Version Revisada, (2011)
dc.relation.referencesElements of Statistical Learning, (2009)
dc.rights.accesoRestricted access
dc.rights.accessrightsinfo:eu-repo/semantics/restrictedAccess
dc.sourceJournal of Risk and Financial Management
dc.sourceScopus
dc.subjectCredit Risk Modeling
dc.subjectExplainable Machine Learning
dc.subjectInternal Ratings-based Approach
dc.subjectLightgbm
dc.subjectShap Values
dc.titleExplainable Machine Learning Models for Credit Rating in Colombian Solidarity Sector Entities
dc.typeArticle
dc.type.localArtículospa
dc.type.versioninfo:eu-repo/semantics/publishedVersion

Archivos

Colecciones

Indexados Scopus