AP19675226 – Intelligent credit system for the manufacturer/importer of goods

Objective of the project: Create an intelligent system based on a scoring model. The scoring model will allow banks to quickly make decisions on lending to customers based on big data and artificial intelligence methods.

Relevance: Currently, banks are implementing artificial intelligence (AI) and machine learning in every business process and plan to extend this technology to all areas of their business. For example, banks have been automatically scoring borrowers for a long time. However, there are no credit lines for manufacturers and importers of goods in Kazakhstan, so many companies use foreign solutions for the commercial use of technologies in the domestic market. Consequently, confidential user data exported using foreign solutions has a negative impact on the economy of Kazakhstan. They include the dissemination of personal data, which is currently assessed as a valuable national resource.

Scientific supervisor: Ph.D., Associate Professor, Moldagulova Aiman

Results obtained: The study established scientific and methodological foundations for developing an intelligent system for assessing the creditworthiness of manufacturers and importers. Structural analysis, knowledge base approaches, and machine learning methods were integrated to provide a comprehensive solution. An ontological model and credit risk prediction algorithms were developed to ensure formalization and efficient data analysis. A modular software architecture was proposed, enabling integration with existing financial platforms. The results demonstrate improved accuracy of credit scoring and better decision-making quality. Implementation of the system reduces risks, automates processes, and enhances overall economic efficiency.

List of publications with links to them

1. Ali M., Razaque A., Yoo J., Uskenbayeva R., Moldagulova A., Satybaldiyeva R., Kalpeyeva Zh., Kassymova A. Designing an intelligent scoring system for crediting manufacturers and importers of goods in Industry 4.0 // Logistics. – 2024. – Vol. 8, No. 1. – P. 33. DOI: https://doi.org/10.3390/logistics8010033. – URL: https://www.mdpi.com/2305-6290/8/1/33
2. Razaque A., Beishenaly A., Kalpeyeva Zh., Uskenbayeva R., Moldagulova A.N. A reinforcement learning and predictive analytics approach for enhancing credit assessment in manufacturing // Decision Analytics Journal. – 2025. DOI: https://doi.org/10.1016/j.dajour.2025.100560. – URL: https://www.sciencedirect.com/science/article/pii/S2772662225000165
3. Moldagulova A. et al. Advancing credit assessment: a hybrid methodology for importer crediting // Business Modeling and Software Design. BMSD 2025 / ed. B. Shishkov. – Cham: Springer, 2026. – (Lecture Notes in Business Information Processing, Vol. 559). DOI: https://doi.org/10.1007/978-3-031-98033-6_19. – URL: https://link.springer.com/chapter/10.1007/978-3-031-98033-6_19
4. Uskenbayeva R.K., Kalpeyeva Zh.B., Moldagulova A.N., Kassymova A.B., Satybaldiyeva R.Zh. Machine learning-based credit scoring for manufacturers and importers // International Journal of Information and Communication Technologies. – 2025. – Vol. 6, No. 3 (23). – P. 323–335. DOI: https://doi.org/10.54309/IJICT.2025.23.3.020. – URL: https://journal.iitu.edu.kz/index.php/ijict/issue/view/33/80
5. Kalpeyeva Zh.B. et al. Development intelligent credit system to support manufacturer/importer of goods // Eastern-European Journal of Enterprise Technologies. – 2025. – No. 6 (138).
6. Свидетельство о внесении сведений в государственный реестр прав на объекты, охраняемые авторским правом № 62521 от 30 сентября 2025 года.