Stream-First Fraud Defense in Distributed FinTech Systems
Keywords:
Distributed Data Engineering Models for Real-Time Fraud Monitoring in FinTech Systems. Fraud detection; Data flow; Data lake; Semantic segmentation; Architectural model; FinTech systems.Abstract
Fraud in FinTech systems, namely in-banking and insurances, represents a complex and multifactorial phenomenon that has been further amplified by social distancing and confinement measures to cope with the COVID-19 crisis. According to selected reports, fraud in Europe alone is estimated at 2.2 billion Euros for 20224 and is expected to continue its otherwise upward trend in different markets. To mitigate risks and minimize losses, private and public organizations invest continuously on fraud monitoring systems. However, fraud crime continuously adapts its detection methods and hence, systems are still required to evolve in the fraud investigation and detection area. To facilitate benchmark and comparison of different approaches, the application of an open-source distributed and scalable data engineering model is applied to create fraud monitoring systems in a FinTech environment.
Fraud monitoring systems in distributed environments require different and specific execution models in an integrated and open-source environment. Data engineering platforms allow integration of different data sources and types with the possibility of executing distributed data engineering tasks in batch, streaming, micro-batch and real-time modes. An integrated analytical environment is used to support fraud monitoring in enterprises outside the banking sector. GDPR and data anonymization measures are used to guarantee the data privacy with a clear impact of the climate change index in a fraud model. Detection of anti-money laudering events related to COVID-19 is also presented and discussed. Finally, a case study in the European Banking Federation area is further analyzed.
References
[1] Akinbowale, O. E., Malaquias, R. F., & Denere, P. (2020). Digital financial services and financial inclusion: The role of big data. Journal of Financial Crime, 28(4), 1011–1024.
[2] Allen, F., Gu, X., & Jagtiani, J. (2022). A survey of fintech research and policy issues. Review of Corporate Finance, 2(1), 1–35.
[3] Alshameri, M. A., & Xia, J. Deep learning for fraud detection in the banking industry: A systematic review. Journal of Big Data, 10(1), 1–32.
[4] Bin Sulaiman, R., Schetinin, V., & Sant, P. (2022). Review of machine learning approach on credit card fraud detection. Human-centric Computing and Information Sciences, 12(1), 1–25.
[5] Canhoto, A. I. (2021). Leveraging machine learning in the global fight against money laundering and terrorism financing. Journal of Business Research, 131, 441–451.
[6] Chang, V., Di Stefano, A., Sun, Z., & Fortino, G. (2022). Real-time fraud detection in the banking sector using big data analytics. Information Sciences, 582, 531–548.
[7] Chandra, S., Kumar, K. N., & Singh, R. P. (2022). Customization and personalization in fintech: A big data approach. International Journal of Information Management Data Insights, 2(2), 100101.
[8] Cui, Y., Daud, M. N., & He, L. (2021). Feature engineering for credit card fraud detection: A review. IEEE Access, 9, 12345–12360.
[9] Dehnert, M., & Schumann, M. (2022). Consumer behavior in digital financial services: Insights from big data analytics. Electronic Markets, 32(3), 1541–1560.
[10] Huang, J., Zhou, J., & Wang, Y. (2020). Predictive modeling for loan default in fintech using big data. Journal of Banking and Finance, 118, 105874.
[11] Johnson, K., Pasricha, P., & Gupta, S. (2021). The expansion of big data in fintech: Trends and future directions. Journal of Financial Technology, 6(1), 45–62.
[12] Mhlanga, D. The role of big data in financial technology toward financial inclusion. Frontiers in Big Data, 7, 1184444.
[13] Morales, J., Smith, R., & Lopez, A. (2022). Big data analytics for informed decision-making in fintech firms. Journal of Decision Systems, 31(2), 210–235.
[14] Nobanee, H., Al-Hamadi, F. Y., & Abdulaziz, N. (2021). A bibliometric analysis of big data in fintech. Journal of Financial Reporting and Accounting, 19(4), 585–604.
[15] Rabbani, H., Shahid, M. F., Khanzada, T. J. S., Siddiqui, S., Jamjoom, M. M., Ashari, R. B., et al. Enhancing security in financial transactions: A novel blockchain-based federated learning framework for detecting counterfeit data in fintech. PeerJ Computer Science, 10, e2280. https://doi.org/10.7717/peerj-cs.2280
[16] Roszkowska, P. (2021). Fintech and artificial intelligence: The future of financial services. Journal of Risk and Financial Management, 14(5), 213.
[17] Sheng, T. (2021). The impact of big data analytics on risk management in fintech lending. Technology in Society, 65, 101595.
[18] Wang, Z. . Research on the application of artificial intelligence and big data technology in financial fraud detection. Journal of Theory and Practice of Engineering Science, 4(03), 216–219.
[19] Wickramanayake, S., Gunawardana, S., & Perera, R. (2020). Challenges in detecting fraudulent banking transactions using traditional techniques. International Journal of Computer Applications, 176(12), 22–30.
Additional Files
Published
Data Availability Statement
None
Issue
Section
License
Copyright (c) 2025 European Advanced Journal for Emerging Technologies (EAJET)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.
