Research on the Improved Gray Wolf-Random Forest Hybrid Model in Credit Risk Assessment

Article Sidebar

PDF
Published: 2026-01-20
Keywords:
credit risk, Random Forest, Grey Wolf Optimization, default prediction, imbalanced data, F1-score, model tuning

Main Article Content

James R. Coleman
School of Computing and Communications, Lancaster University, Lancaster, LA1 4YW, United Kingdom
Michael S. Bradford
School of Computing and Communications, Lancaster University, Lancaster, LA1 4YW, United Kingdom
Sarah K. Foster
School of Computing and Communications, Lancaster University, Lancaster, LA1 4YW, United Kingdom

Abstract

Credit risk models must deal with imbalanced data and mixed borrower features. In this study, a Random Forest model tuned with Grey Wolf Optimization is used to raise the accuracy of default prediction on two UCI credit datasets. The optimizer adjusts the number of trees and the depth of each tree under an F1-based rule. After cleaning and encoding 2,000 records, the tuned model reaches an F1-score of 0.78, higher than the 0.74 achieved by the grid-search RF. Test accuracy increases from 0.83 to 0.85, and AUC rises from 0.89 to 0.91. Recall for default cases improves from 0.71 to 0.77, while precision stays near 0.79. These results show that a small change in model settings can reduce missed defaults without raising false alarms. The method is simple to train and can be used in regular scoring tasks. The study is limited by the use of public datasets with few variables and by the focus on one model type. Future work should include richer financial data and test multi-period predictions for broader use in lending systems.

Article Details

Issue

Vol. 1 No. 2 (2025): 2025 International Conference on Computer Science, Artificial Intelligence and Communication Systems (CSACS 2025)

Section

Articles

How to Cite

Research on the Improved Gray Wolf-Random Forest Hybrid Model in Credit Risk Assessment. (2026). Journal of Science, Innovation & Social Impact, 1(2), 161-167. https://sagespress.com/index.php/JSISI/article/view/70

References

1. K. Brown, and P. Moles, "Credit risk management," Credit Risk Management, 2014.

2. L. Maralbayeva, "Research of existing machine learning methods for borrower credit scoring," Computing & Engineering, vol. 1, no. 4, pp. 6-11, 2023.

3. V. Kuzin, M. Marcellino, and C. Schumacher, "Pooling versus model selection for nowcasting GDP with many predictors: Empirical evidence for six industrialized countries," Journal of Applied Econometrics, vol. 28, no. 3, pp. 392-411, 2013. doi: 10.1002/jae.2279

4. L. Tan, D. Liu, X. Liu, W. Wu, and H. Jiang, "Efficient grey wolf optimization: A high-performance optimizer with reduced memory usage and accelerated convergence," 2025. doi: 10.20944/preprints202412.1974.v2

5. S. J. S. Krishna, M. Aarif, N. K. Bhasin, S. Kadyan, and B. K. Bala, "Predictive analytics in credit scoring: Integrating XGBoost and neural networks for enhanced financial decision making," In Proceedings of the 2024 International Conference on Data Science and Network Security, 2024, pp. 1-6.

6. J. Xue, and B. Shen, "Dung beetle optimizer: A new meta-heuristic algorithm for global optimization," The Journal of Supercomputing, vol. 79, no. 7, pp. 7305-7336, 2023. doi: 10.1007/s11227-022-04959-6

7. S. El-Sappagh, H. Saleh, F. Ali, E. Amer, and T. Abuhmed, "Two-stage deep learning model for Alzheimer's disease detection and prediction of the mild cognitive impairment time," Neural Computing and Applications, vol. 34, no. 17, pp. 14487-14509, 2022. doi: 10.1007/s00521-022-07263-9

8. J. Li, S. Wu, and N. Wang, "A CLIP-based uncertainty modal modeling (UMM) framework for pedestrian re-identification in autonomous driving," 2025. doi: 10.70711/aitr.v2i10.7149

9. E. Baş, "Improved particle swarm optimization based on a quantum-behaved framework for big data optimization," Neural Processing Letters, vol. 55, no. 3, pp. 2551-2586, 2023.

10. M. Yang, Y. Wang, J. Shi, and L. Tong, "Reinforcement learning-based multi-stage ad sorting and personalized recommendation system design," 2025.

11. F. S. Gharehchopogh, A. Ucan, T. Ibrikci, B. Arasteh, and G. Isik, "Slime mould algorithm: A comprehensive survey of its variants and applications," Archives of Computational Methods in Engineering, vol. 30, no. 4, pp. 2683-2723, 2023. doi: 10.1007/s11831-023-09883-3

12. J. Tian, J. Lu, M. Wang, H. Li, and H. Xu, "Predicting property tax classifications: An empirical study using multiple machine learning algorithms on U," S. state-level data, 2025.

13. C. Wu, and H. Chen, "Research on system service convergence architecture for AR/VR systems," 2025.

14. W. Sun, “Integration of Market-Oriented Development Models and Marketing Strategies in Real Estate,” European Journal of Business, Economics & Management, vol. 1, no. 3, pp. 45–52, 2025.

15. W. Li, Y. Xu, X. Zheng, S. Han, J. Wang, and X. Sun, "Dual advancement of representation learning and clustering for sparse and noisy images," In Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 1934-1942. doi: 10.1145/3664647.3681402

16. Z. Yin, X. Chen, and X. Zhang, "AI-integrated decision support system for real-time market growth forecasting and multi-source content diffusion analytics," Preprint, 2025.

17. Y. Li, Y. Yao, J. Lin, and N. Wang, "A deep learning algorithm based on a CNN-LSTM framework for predicting cancer drug sales volume," Preprint, 2025.

18. S. Yuan, “Data Flow Mechanisms and Model Applications in Intelligent Business Operation Platforms”, Financial Economics Insights, vol. 2, no. 1, pp. 144–151, 2025, doi: 10.70088/m66tbm53.

19. S. N. Makhadmeh, M. A. Al-Betar, I. A. Doush, M. A. Awadallah, S. Kassaymeh, S. Mirjalili, and R. A. Zitar, "Recent advances in grey wolf optimizer, its versions and applications," IEEE Access, vol. 12, pp. 22991-23028, 2023.

20. R. Chen, B. Gu, and Z. Ye, "Design and implementation of a big data-driven business intelligence analytics system," 2025.

21. A. Salhi, R. Alshamrani, A. Althbiti, A. Ismail, M. Abd-ElRahman, and B. M. Hassan, "Optimizing high-dimensional data classification with a hybrid AI-driven feature selection framework and machine learning schema," Scientific Reports, vol. 15, no. 1, p. 35038, 2025.

22. M. S. Reza, M. I. Mahmud, I. A. Abeer, and N. Ahmed, "Linear discriminant analysis in credit scoring: A transparent hybrid model approach," In Proceedings of the 27th International Conference on Computer and Information Technology, 2024, pp. 56-61. doi: 10.1109/iccit64611.2024.11022149

23. M. Yuan, H. Mao, W. Qin, and B. Wang, "A BIM-driven digital twin framework for human-robot collaborative construction with on-site scanning and adaptive path planning," 2025. doi: 10.20944/preprints202508.1387.v1

24. S. Wu, J. Cao, X. Su, and Q. Tian, "Zero-shot knowledge extraction with hierarchical attention and an entity-relationship transformer," In Proceedings of the 5th International Conference on Sensors and Information Technology, 2025, pp. 356-360. doi: 10.1109/icsi64877.2025.11009253