Cost-Sensitive Ensemble Models for Microcredit Risk Prediction: A Comparative Evaluation
DOI:
https://doi.org/10.63158/journalisi.v8i5.1902Keywords:
cost-sensitive classification, ensemble models, class imbalance, microcredit risk prediction, machine learningAbstract
Microcredit risk prediction is challenged by class imbalance and asymmetric misclassification costs. This study evaluates cost-sensitive ensemble models and examines model-selection stability across heterogeneous credit sources. Logistic Regression, Random Forest, XGBoost, and CatBoost were evaluated on one operational microcredit portfolio and three public credit datasets using development-only preprocessing, class-balanced fitting weights, and leakage controls. Model and threshold selection used validation data with a five-to-one false-negative cost ratio and minimum specificity of 0.70. XGBoost was selected for the operational, Credit Risk, and FIN ANA sources, while Logistic Regression was selected for German Credit. On the retrospectively held-out evaluation partitions, ROC-AUC values were 0.895, 0.940, 0.461, and 0.620, with recalls of 0.364, 0.839, 0.083, and 0.483, respectively. FIN ANA showed substantial degradation under broader distribution shift. The study jointly evaluates minority-class recall, asymmetric error costs, and validation-selected operating points, showing that cost-sensitive model selection is source-dependent and ROC-AUC alone is insufficient for practical risk detection. The operational analysis represents retrospective adverse-status screening rather than prospective default prediction because temporal feature snapshots and future outcome windows were unavailable.
Downloads
References
[1] E. Dumitrescu, S. Hué, C. Hurlin, and S. Tokpavi, “Machine learning for credit scoring: Improving logistic regression with non-linear decision-tree effects,” Eur. J. Oper. Res., vol. 297, no. 3, pp. 1178–1192, 2022, doi: 10.1016/j.ejor.2021.06.053.
[2] H. He, W. Zhang, and S. Zhang, “A novel ensemble method for credit scoring: Adaption of different imbalance ratios,” Expert Syst. Appl., vol. 98, pp. 105–117, 2018, doi: 10.1016/j.eswa.2018.01.012.
[3] J. Martin, S. Taheri, and M. Abdollahian, “Optimizing ensemble learning to reduce misclassification costs in credit risk scorecards,” Mathematics, vol. 12, no. 6, pp. 855, 2024, doi: 10.3390/math12060855.
[4] G. Petrides and W. Verbeke, “Cost-sensitive ensemble learning: A unifying framework,” Data Min. Knowl. Discov., vol. 36, pp. 1–28, 2022, doi: 10.1007/s10618-021-00790-4.
[5] Z. Li, J. Zhang, X. Yao, and G. Kou, “How to identify early defaults in online lending: A cost-sensitive multi-layer learning framework,” Knowledge-Based Syst., vol. 221, pp. 106963, 2021, doi: 10.1016/j.knosys.2021.106963.
[6] Y. Kang, L. Chen, N. Jia, W. Wei, J. Deng, and H. Qian, “A CWGAN-GP-based multi-task learning model for consumer credit scoring,” Expert Syst. Appl., vol. 206, pp. 117650, 2022, doi: 10.1016/j.eswa.2022.117650.
[7] J. Xiao, Y. Wang, J. Chen, L. Xie, and J. Huang, “Impact of resampling methods and classification models on the imbalanced credit scoring problems,” Inf. Sci., vol. 569, pp. 508–526, 2021, doi: 10.1016/j.ins.2021.05.029.
[8] S. Kapoor and A. Narayanan, “Leakage and the reproducibility crisis in machine-learning-based science,” Patterns, vol. 4, pp. 100804, 2023, doi: 10.1016/j.patter.2023.100804.
[9] S. Han and H. Jung, “NATE: Non-parametric approach for explainable credit scoring on imbalanced class,” PLoS One, vol. 19, no. 12, pp. e0316454, 2024, doi: 10.1371/journal.pone.0316454.
[10] I. Aruleba and Y. Sun, “Effective credit risk prediction using ensemble classifiers with model explanation,” IEEE Access, vol. 12, pp. 115015–115025, 2024, doi: 10.1109/ACCESS.2024.3445308.
[11] Y. Xia, S. Jiang, L. Meng, and X. Ju, “XGBoost-B-GHM: An ensemble model with feature selection and GHM loss function optimization for credit scoring,” Systems, vol. 12, no. 7, pp. 254, 2024, doi: 10.3390/systems12070254.
[12] Z. Zhao, T. Cui, S. Ding, J. Li, and A. G. Bellotti, “Resampling techniques study on class imbalance problem in credit risk prediction,” Mathematics, vol. 12, no. 5, pp. 701, 2024, doi: 10.3390/math12050701.
[13] Y. Chen, R. Calabrese, and B. Martin-Barragan, “Interpretable machine learning for imbalanced credit scoring datasets,” Eur. J. Oper. Res., vol. 312, no. 1, pp. 357–372, 2024, doi: 10.1016/j.ejor.2023.06.036.
[14] X. Dastile and T. Celik, “Making deep learning-based predictions for credit scoring explainable,” IEEE Access, vol. 9, pp. 50426–50440, 2021, doi: 10.1109/ACCESS.2021.3068854.
[15] H. Putra and R. Rumini, “Comparative study of Logistic Regression, Random Forest, and XGBoost for bank loan approval classification,” J. Appl. Informatics Comput., vol. 9, no. 5, pp. 2822–2835, 2025, doi: 10.30871/jaic.v9i5.10862.
[16] A. A. Saputra, B. N. Sari, and C. Rozikin, “Penerapan algoritma Extreme Gradient Boosting (XGBoost) untuk analisis risiko kredit,” J. Ilm. Wahana Pendidik., vol. 10, no. 7, pp. 27–36, 2024, doi: 10.5281/zenodo.10960080.
[17] L. Tse, “Credit Risk Dataset,” Kaggle, Jul. 27, 2020.
[18] M. Tahmid, “Credit Risk Dataset,” Kaggle, Jul. 27, 2024.
[19] H. Hofmann, “Statlog (German Credit Data),” UCI Machine Learning Repository, 1994.
[20] K. R. Jammalamadaka and S. Itapu, “Responsible AI in automated credit scoring systems,” AI Ethics, vol. 3, no. 2, pp. 485–495, 2023, doi: 10.1007/s43681-022-00175-3.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Author's Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
