IRO Journals
Journal of Information Technology and Digital World

Interpretable MSME Credit Risk Prediction Through XGBoost Feature Selection and LSSVM Classification

Open Access
Published: 14 October, 2026
Pages: 365-381
  • Sharmila Jeyarani S. , Sharmila Jeyarani S.
    Assistant Professor, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Assistant Professor, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Sanjay Raj J. , Sanjay Raj J.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Rajamannar N.G. , Rajamannar N.G.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Sabari Anandh M. Sabari Anandh M.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
view PDF
view PDF

How to Cite

S., Sharmila Jeyarani, Sanjay Raj J., Rajamannar N.G., and Sabari Anandh M. 2026. “Interpretable MSME Credit Risk Prediction Through XGBoost Feature Selection and LSSVM Classification”. Journal of Information Technology and Digital World 8 (4): 365-81. https://doi.org/10.36548/jitdw.2026.4.006.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Supply Chain Finance
MSME Credit Risk
XGBoost Feature Selection
RBF-LSSVM
SHAP Explainability
Counterfactual Analysis
SMOTE Balancing

Abstract

This research work proposes an interpretable hybrid ML approach to credit risk evaluation of MSMEs in supply chain financing, combining feature selection using XGBoost with classification using RBF-LSSVM. The credit information of the multi-sourced variety is standardized into a common set of financial and operational variables followed by stratification, training normalization, and class balance through SMOTE technique to minimize the impact of minority class bias while maintaining test set independence. Using the XGBoost classifier with TreeSHAP analysis of features selects the relevant predictors that are further classified using the RBF-LSSVM classifier with calibrated probability estimation and optimized decision threshold for risk-aware classification. This proposed approach achieves 97.96% accuracy, 94.52% precision, 97.43% recall, and 95.95% F1-score on the held-out evaluation set. SHAP and counterfactual explanations offer feature level interpretations of the risk assessments.

References

  1. Zhou, Guanglan, and Shiru Wang."Enhancing Credit Risk Decision-Making in Supply Chain Finance with Interpretable Machine Learning Model." IEEE Access, 2025, vol. 13: 14239-14251.
  2. Zhu, You, Li Zhou, Chi Xie, Gang-Jin Wang, and Truong V. Nguyen. "Forecasting Smes’ Credit Risk in Supply Chain Finance with an Enhanced Hybrid Ensemble Machine Learning Approach." International Journal of Production Economics, 2019, vol. 211: 22-33.
  3. Zhang, Hao, Yuxin Shi, Xueran Yang, and Ruiling Zhou. "A Firefly Algorithm Modified Support Vector Machine for the Credit Risk Assessment of Supply Chain Finance." Research in International Business and Finance, 2021, vol. 58: 101482.
  4. Ojha, Ritesh, Abhijeet Ghadge, Manoj Kumar Tiwari, and Umit S. Bititci. "Bayesian Network Modelling for Supply Chain Risk Propagation." International Journal of Production Research, 2018, vol. 56, no. 17: 5795-5819.
  5. Chen, Tianqi, and Carlos Guestrin. "XDBoost: A Scalable Tree Boosting System." In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, 785-794.
  6. Tang, Qian, Yan Lu, Bin Wang, and Zhen Li. "A Deep Convolutional Neural Network Based Risk Identification Method for E-Commerce Supply Chain Finance." Scientific Programming, 2022, vol. 2022, no. 1: 6298248.
  7. Maldonado, Sebastián, Juan Pérez, and Cristián Bravo. "Cost-Based Feature Selection for Support Vector Machines: An Application in Credit Scoring." European Journal of Operational Research, 2017, vol. 261, no. 2: 656-665.
  8. Lundberg, Scott M., and Su-In Lee. "A Unified Approach to Interpreting Model Predictions." Advances in Neural Information Processing Systems, 2017, vol. 30: 1-10.
  9. Lundberg, Scott M., Gabriel Erion, Hugh Chen, Alex DeGrave, Jordan M. Prutkin, Bala Nair, Ronit Katz, Jonathan Himmelfarb, Nisha Bansal, and Su-In Lee. "From Local Explanations to Global Understanding with Explainable AI For Trees." Nature Machine Intelligence, 2020, vol. 2, no. 1: 56-67.
  10. Shen, Feng, Xingchao Zhao, Gang Kou, and Fawaz E. Alsaadi. "A New Deep Learning Ensemble Credit Risk Evaluation Model with an Improved Synthetic Minority Oversampling Technique." Applied Soft Computing, 2021, vol. 98: 106852.
  11. Wachter, Sandra, Brent Mittelstadt, and Chris Russell. "Counterfactual Explanations Without Opening the Black Box: Automated Decisions and The GDPR." Harvard Journal and Technology, 2017, vol. 31: 841.
  12. Ekanayake, I. U., D. P. P. Meddage, and Upaka Rathnayake. "A Novel Approach to Explain the Black-Box Nature of Machine Learning in Compressive Strength Predictions of Concrete using Shapley Additive Explanations (SHAP)." Case Studies in Construction Materials, 2022, vol. 16: e01059.
  13. Mo, Tiexiang, Shanshan Li, and Guodong Li. "An Interpretable Machine Learning Model For Predicting Cavity Water Depth and Cavity Length Based on Xgboost–SHAP." Journal of Hydroinformatics, 2023, vol. 25, no. 4: 1488-1500.
  14. Shakil, Mohammad Hassan. "Environmental, Social and Governance Performance and Financial Risk: Moderating Role of ESG Controversies and Board Gender Diversity." Resources Policy, 2021, vol. 72: 102144.
  15. Gafsi, Nesrine. "Machine Learning Approaches to Credit Risk: Comparative Evidence from Participation and Conventional Banks in The UK." Journal of Risk and Financial Management, 2025, vol. 18, no. 7: 345.
  16. Raj, Taflin S, and Radhika R. 2026. “A Machine Learning Framework for Evaluating MSME Incubation Dynamics”. Journal of Trends in Computer Science and Smart Technology 8 (1): 114-29. https://doi.org/10.36548/jtcsst.2026.1.006.
  17. Credit Risk Dataset - https://www.kaggle.com/datasets/laotse/credit-risk-dataset
  18. Leading Indian Bank & CIBIL Real-World Dataset – https://www.kaggle.com/datasets/saurabhbadole/leading-indian-bank-and-cibil-real-world-dataset
  19. Ensemble Learning with Feature Optimization for Credit Risk Assessment –https://www.researchgate.net/publication/382688309_Ensemble_Learning_with_Feature_Optimization_for_Credit_Risk_Assessment