The Application of Machine Learning Combined with Graph Databases in Financial Technology

Xuanrui Zhang

Authors

Xuanrui Zhang College of Engineering, University of California, Berkeley, CA, 94720, USA Author

Keywords:

machine learning, graph database, financial technology, fraud detection, risk management

Abstract

Against the backdrop of rapid advances in financial technology, the surge in data volume and the diversity of data structures have posed great challenges to traditional data analysis methods. The combination of machine learning and graph databases provides a new means of data processing and analysis for the financial industry. Graph databases have unique advantages in handling complex relational data, while machine learning can mine deep patterns in large amounts of data. This article mainly studies the application of these two technologies in the field of financial technology, focusing on enhancing data analysis, financial forecasting, and risk control capabilities. By combining these two technologies, financial institutions can more efficiently complete tasks such as fraud detection, credit evaluation, anti-money laundering, and marketing. Detailed discussions were held on the technical architecture and methods required to implement these technologies, including key technologies such as data integration, graph model construction, and distributed computing, to help the financial industry move towards intelligent operations.

References

1. G. Karuna, G. B. Santhi, M. Al-Farouni, G. V. Reddy, A. Shukla, and C. P. Patnaik, “Enhancing financial data traceability using graph neural networks for provenance methods,” in Proc. 2024 Int. Conf. IoT, Commun. Autom. Technol. (ICICAT), Nov. 2024, pp. 1334–1339, doi: 10.1109/ICICAT62666.2024.10923449.

2. Q. Sun, X. Wei, and X. Yang, “GraphSAGE with deep reinforcement learning for financial portfolio optimization,” Expert Syst. Appl., vol. 238, p. 122027, 2024, doi: 10.1016/j.eswa.2023.122027.

3. P. Azad, C. Akcora, and A. Khan, “Machine learning for blockchain data analysis: Progress and opportunities,” Distrib. Ledger Technol.: Res. Pract., 2024, doi: 10.1145/3728474.

4. R. Mitra, A. Dongre, P. Dangare, A. Goswami, and M. K. Tiwari, “Knowledge graph driven credit risk assessment for micro, small and medium-sized enterprises,” Int. J. Prod. Res., vol. 62, no. 12, pp. 4273–4289, 2024, doi: 10.1080/00207543.2023.2257807.

5. L. Zhao, Z. Yao, C. Liu, Y. Du, H. Hou, and Z. Hu, “Construction and empirical analysis of data governance system based on knowledge graph,” in Proc. 2nd Int. Conf. Big Data, Comput. Intell., Appl. (BDCIA), vol. 13550, Mar. 2025, pp. 179–186, doi: 10.1117/12.3059088.