Artificial intelligence

Abstract: This paper presents a hybrid decision support system that integrates a Belief Rule Base (BRB) model, a Machine Learning (ML) model, and Particle Swarm Optimization (PSO). The system predicts the credit rating of fintech clients based on data obtained through the Open Banking API. For a real-world dataset, the classification ML model Random Forest demonstrates high predictive accuracy. The BRB model is represented by a complete set of rules covering four attributes with three referential values for each attribute. By analyzing the distribution of the number of activated rules and their activation weights, the representativeness of the data was assessed. A group of rules with low activation weights was identified, corresponding to the referential value Middle for one of the attributes. PSO was applied to optimize BRB parameters, ensuring both interpretability of the results and the capability to model incomplete data. For model validation, data were synthesized using a Rule-Based Data Synthetic approach. The results show that BRB models maintain stable accuracy across real and validation datasets. In contrast, the accuracy of the ML model decreased on validation data by an average of 5% compared to the initial dataset. These findings highlight the advantages of the hybrid approach, which combines the accuracy of ML with the interpretability and robustness of BRB in data-limited environments.

Keywords: machine learning, neural networks, fuzzy logic, BRB, ER, open banking, credit rating

References:

1. Zhiguo He, Jing Huang, Jidong Zhou (2023). Open banking: Credit market competition when borrowers own the data, Journal of Financial Economics, Volume 147, Issue 2, https://doi.org/10.1016/j.jfineco.2022.12.003
2. Xiong Rui (2024) Open banking and fintech lending: evidence from a crowdfunding platform. http://dx.doi.org/10.2139/ssrn.5046894
3. João B. G. de Brito, Rodrigo Heldt (2025). Predicting and Explaining Customer Data Sharing in the Open Banking arXiv:2507.01987 https://doi.org/10.48550/arXiv.2507.01987
4. Hjelkrem, L. O., de Lange, P. E., & Nesset, E. (2022). The Value of Open Banking Data for Application Credit Scoring: Case Study of a Norwegian Bank. Journal of Risk and Financial Management, 15(12), 597. https://doi.org/10.3390/jrfm15120597
5. Xiuxian Yin, Xin Zhang, Hongyu Li, Yujia Chen, Wei He (2023) An interpretable model for stock price movement prediction based on the hierarchical belief rule base, Heliyon, Volume 9, Issue 6, https://doi.org/10.1016/j.heliyon.2023.e16589
6. Guanxiang Hu, Wei He, Chao Sun, Hailong Zhu, Kangle Li, Li Jiang (2023) Hierarchical belief rule-based model for imbalanced multi-classification, Expert Systems with Applications, Volume 216, https://doi.org/10.1016/j.eswa.2022.119451
7. Fei Gao, Wenhao Bi, (2023) A fast belief rule base generation and reduction method for classification problems, International Journal of Approximate Reasoning, Volume 160, https://doi.org/10.1016/j.ijar.2023.108964.
8. Y. Fu, Z. Yin, M. Su, Y. Wu, G. Liu, (2020) Construction and Reasoning Approach of Belief Rule-Base for Classification Base on Decision Tree in IEEE Access, vol. 8, pp. 138046-138057, doi: 10.1109/ACCESS.2020.3012453
9. Sun, C., Yang, R., He, W. et al. A novel belief rule base expert system with interval-valued references. Sci Rep 12, 6786 (2022). https://doi.org/10.1038/s41598-022-10636-8
10. Sachan, S., Yang, J.-B., & Xu, D.-L. (2020). Global and Local Interpretability of Belief Rule Base. In Proceedings of FLINS2020 World Scientific Publishing Co. https://doi.org/10.1142/9789811223334_0009
11. R. Kumar et al., (2024) Practicing the Rule-Based Classifier Using Metaheuristics Gravitational Search Algorithm to Generate a Credit Score Model to Avail Loans, 1st International Conference on Sustainable Computing and Integrated Communication in Changing Landscape of AI, Greater Noida, India, pp. 1-9, doi: 10.1109/ICSCAI61790.2024.10866544
12. Xiang, G., Wang, J., Han, X. et al. A novel optimization method for belief rule base expert system with activation rate. Sci Rep 13, 584 (2023). https://doi.org/10.1038/s41598-023-27498-3
13. Jiao, L., Geng, X., & Pan, Q. (2019). Compact Belief Rule Base Learning for Classification with Evidential Clustering. Entropy, 21(5), 443. https://doi.org/10.3390/e21050443
14. Yang-Geng Fu, Ji-Feng Ye, Ze-Feng Yin, Long-Jiang Chen, Ying-Ming Wang, Geng-Geng Liu, (2021) Construction of EBRB classifier for imbalanced data based on Fuzzy C-Means clustering, Knowledge-Based Systems, Volume 234, 107590, https://doi.org/10.1016/j.knosys.2021.107590.
15. K. Derrick (2024) A Comprehensive Survey of Belief Rule Base (BRB) Hybrid Expert system: Bridging Decision Science and Professional Services arXiv:2402.16651 https://doi.org/10.48550/arXiv.2402.16651
16. Fostyak М., Demkiv L. (2024) Development of data mesh data platform with ml domain of data analysism, Electronics and information technologies. 2024. 27. doi: https://doi.org/10.30970/eli
17. M. Fostyak, L. Demkiv (2025) A data-centric approach to building ai models for determining the credit rating of fintech company clients based on open banking // ISSN 2710 – 1673 Artificial Intelligence 2025 № 1. https://doi.org/10.15407/jai2025.01.132
18. Fostyak М., (2024) Development of an AI domain in a data mesh network for customer credit classification using transaction data, IEEE 19th International Conference on Computer Science and Information Technologies. DOI:10.1109/CSIT65290.2024.10982569
19. T. M. Shami, A. A. El-Saleh, M. Alswaitti, Q. Al-Tashi, M. A. Summakieh and S. Mirjalili (2022) Particle Swarm Optimization: A Comprehensive Survey, in IEEE Access, vol. 10, pp. 10031-10061, doi: 10.1109/ACCESS.2022.3142859. r