Article Sidebar

Download
PDF
Statistic
Read Counter : 0 Download : 0

Main Article Content

Abstract

AI-enabled FinTech platforms increasingly rely on automated fraud-risk prediction to secure high-volume digital payments, mobile-money transactions, and real-time financial services. However, fraud detection remains difficult because fraudulent transactions are rare, financial data are sensitive, and centralized machine-learning models may create privacy and data-governance risks. This study evaluates a leakage-aware and imbalance-aware federated-style simulation for fraud-risk prediction in AI-enabled FinTech platforms. The study does not implement FedAvg, cryptographic secure aggregation, differential privacy, or model-parameter exchange. Instead, the PaySim Synthetic Financial Dataset was partitioned into five simulated FinTech clients, local models were trained separately, and prediction-level aggregation was used to compare centralized and simulated decentralized learning settings. The experimental workflow included data-quality assessment, leakage-aware feature selection, feature engineering, class-imbalance analysis, centralized model development, threshold optimization, and federated-style model comparison. The results show that fraud cases represented only 0.0466% of all transactions and occurred only in CASH_OUT and TRANSFER operations. The best-balanced centralized model was the Improved Random Forest at a threshold of 0.33, achieving an F1-score of 0.3019. Federated Ensemble Aggregation achieved the highest PR-AUC of 0.2699 and a precision of 1.0000, but its recall remained low at 0.1429. The centralized Improved Random Forest retained the highest F1-score of 0.3019, indicating a stronger overall precision-recall balance. Global feature-importance analysis showed that transaction amount, log-transformed amount, temporal features, transaction type, and destination-account activity were the main fraud-risk indicators. These findings should be interpreted as evidence from simulated decentralized fraud-risk learning rather than a full secure federated learning implementation.

Keywords

Federated-style simulation Fraud-risk prediction Global feature importance Class-imbalanced learning FinTech fraud detection Resource-aware digital infrastructure

Article Details

How to Cite
Agarwal, J. ., & Uddin , M. . (2026). Leakage-aware federated-style simulation for fraud risk prediction in AI-enabled FinTech platforms. Future Technology, 5(4), 108–118. Retrieved from https://fupubco.com/futech/article/view/1105
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
Bookmark and Share

References

  1. H. A. Al Dulaimi et al., “AI-driven behavioral anomaly and fraud detection models for real-time high-frequency financial transactions in FinTech systems,” in Proc. 2025 3rd Int. Conf. Cyber Resilience (ICCR), Dubai, United Arab Emirates, 2025, pp. 1–7, doi: 10.1109/ICCR67387.2025.11292440.
  2. M. K. Sandaruwan, D. V. D. S. Abeysinghe, and L. D. S. B. Weerasinghe, “AI-enhanced microservice architecture in the financial domain: A systematic review of security and performance,” in Proc. 2026 IEEE Int. Research Conf. Smart Computing and Systems Engineering (SCSE), vol. 9, Mar. 2026, pp. 1–6.
  3. K. Jayabalan, S. Parmsivan, G. Sunkara, M. Parikh, P. Challa, and V. Nutalapati, “Innovative framework for secure and scalable web and mobile application development in fintech: A user-centric and AI-driven approach,” in Proc. 2025 5th Int. Conf. Ubiquitous Computing and Intelligent Information Systems (ICUIS), Nov. 2025, pp. 1499–1505.
  4. A. Tripathi, “Transforming finance with AI: A capability-based framework for intelligent banking,” in Proc. 2025 Int. Conf. Responsible, Generative and Explainable AI (ResGenXAI), Sep. 2025, pp. 1–5.
  5. V. Sampathkumar and K. Veeras, “Adversarial attacks on FinTech AI models: Threats and mitigation techniques,” in Proc. 2025 IEEE Int. Carnahan Conf. Security Technology (ICCST), Oct. 2025, pp. 1–7.
  6. S. Chandra, S. Muniraj, S. Y. Reddy, V. Raju, B. R. Kumar, and S. K. Katta, “Blockchain and AI integration in fintech: Securing financial transactions and ensuring transparency,” in Proc. 2025 IEEE 4th World Conf. Applied Intelligence and Computing (AIC), Jul. 2025, pp. 257–261.
  7. J. Fan, L. K. Shar, R. Zhang, Z. Liu, W. Yang, D. Niyato, and K. Y. Lam, “Deep learning approaches for anti-money laundering on mobile transactions: Review, framework, and directions,” IEEE Internet of Things Journal, 2026.
  8. Z. M. Guria, I. Rahman, S. Kowser, N. Morshed, R. S. Shammah, and O. Faruq, “AI-driven risk management and fraud prevention in digital finance as a catalyst for US economic resilience and global financial leadership,” in Proc. 2025 IEEE 19th Int. Conf. Open Source Systems and Technologies (ICOSST), Dec. 2025, pp. 1–8.
  9. P. Chinnasamy, A. R. Shaik, A. Akhila, Y. Tejasri, D. Vaishnavi, and D. P. Degala, “FinGuard—AI-powered credit risk assessment for the underbanked using machine learning,” in Proc. 2025 Int. Conf. Future Technologies (ICFT), Nov. 2025, pp. 1–6.
  10. Y. Zuo, “Exploring the synergy: AI enhancing blockchain, blockchain empowering AI, and their convergence across IoT applications and beyond,” IEEE Internet of Things Journal, vol. 12, no. 6, pp. 6171–6195, 2024.
  11. B. Madupati, R. K. Cherukuri, P. K. Keer, N. Naik, N. N. Prabhu, and S. J. Kidwai, “A secure cloud–AI collaborative framework for financially intelligent and autonomous manufacturing enterprises,” in Proc. 2026 Innovations in Machine, Engineering, and Digital Conference (IMED), Mar. 2026, pp. 1–7.
  12. M. F. Ansari, A. Mohammed, K. R. Janamolla, S. W. Khadri, S. A. Khader, and M. A. Raheem, “The double-edged sword: Navigating AI’s role in banking cybersecurity,” in Proc. 2025 Int. Conf. Transformative Computing Technologies (ICTCT), Sep. 2025, pp. 294–300.
  13. R. Lotus, L. R. Peram, S. K. R. Vangala, and S. V. Kusampudi, “A resilient cybersecurity framework for enhancing mobile application security with artificial intelligence,” in Proc. 2025 4th Int. Conf. Automation, Computing and Renewable Systems (ICACRS), Dec. 2025, pp. 1879–1883.
  14. M. Rizinski, H. Peshov, K. Mishev, L. T. Chitkushev, I. Vodenska, and D. Trajanov, “Ethically responsible machine learning in fintech,” IEEE Access, vol. 10, pp. 97531–97554, 2022.
  15. V. R. Pasam, B. Krishnan, R. R. Charla, R. Somayajula, and S. M. Veerapaneni, “AI-enhanced data engineering for complex workflows: Lessons from retail intelligence and financial risk models,” in Proc. 2025 Int. Conf. Computing Technologies & Data Communication (ICCTDC), Jul. 2025, pp. 1–8.
  16. V. Jaiswal, A. Shahi, and A. Kaushal, “Integration of blockchain with artificial intelligence for financial security: A comprehensive review,” in Proc. 2025 IEEE 7th Int. Conf. Computing, Communication and Automation (ICCCA), Nov. 2025, pp. 1–6.
  17. R. G. Franklin, S. Kaur, B. Kumari, Z. Haixia, M. Gupta, and T. Agarwal, “Cyber-resilient financial management framework using blockchain, AI, and cloud-oriented auditing,” in Proc. 2025 IEEE 1st Int. Conf. Smart Innovations in Systems, Infrastructure, Mechanical, Power, AI and Computing Technologies (SISIMPACT), Nov. 2025, pp. 815–820.
  18. P. D. Akre, U. Pacharaney, and W. Siraskar, “Smart finance: An overview of artificial intelligence integration in fintech,” in Proc. 2024 2nd DMIHER Int. Conf. Artificial Intelligence in Healthcare, Education and Industry (IDICAIEI), Nov. 2024, pp. 1–6.
  19. K. Saradhi and S. Kaliappan, “AI-based smart payment systems for preventing cash flow imbalances in trade,” in Proc. 2025 IEEE 1st Int.
  20. E. A. Lopez-Rojas, A. Elmir, and S. Axelsson, “PaySim: A financial mobile money simulator for fraud detection,” in Proc. 28th European Modeling and Simulation Symposium (EMSS), Larnaca, Cyprus, 2016.