Hybrid AI-Based Real-Time Financial Risk Assessment System
DOI:
https://doi.org/10.15662/IJEETR.2026.0802097Keywords:
Financial Fraud Detection, Hybrid Artificial Intelligence, Random Forest, Isolation Forest, Behavioral Analysis, Real-Time Risk AssessmentAbstract
Financial fraud has become increasingly sophisticated due to the rapid growth of digital transactions, online banking, and mobile payment platforms. Traditional fraud detection systems relying solely on rule-based mechanisms or single machine learning models often fail to adapt to evolving fraud strategies. This paper proposes a Hybrid AI-Based Real-Time Financial Risk Assessment System that integrates rule-based detection, supervised machine learning, unsupervised anomaly detection, and behavioural profiling to improve fraud detection accuracy while maintaining low latency
The proposed system processes transaction data in real time through a Fast API-based backend service. Initially, rule-based analysis identifies high-risk transactions using predefined indicators such as abnormal transaction amounts, velocity patterns, and suspicious geographical activity. The system then applies a Random Forest classifier trained on labelled transaction data to detect known fraud patterns. In addition, an Isolation Forest anomaly detection model identifies unusual transaction behaviour that may indicate previously unseen fraud strategies. Behavioural analysis further evaluates user transaction patterns, including transaction timing, spending habits, device usage, and location consistency
The outputs of these modules are combined using a dynamic risk aggregation mechanism that calculates a final fraud risk score. Transactions are then classified into three categories: approved, flagged for review, or blocked. Experimental evaluation using simulated financial transaction datasets demonstrates that the hybrid approach improves detection accuracy and recall while significantly reducing false positives compared to traditional rule-based systems.
The system achieves real-time performance with low processing latency, making it suitable for deployment in modern financial systems such as online banking, digital wallets, and payment gateways. The results demonstrate that integrating multiple artificial intelligence techniques enhances fraud detection robustness, adaptability, and reliability in dynamic financial environments.
References
1. Afriyie, K., et al., "Machine Learning Techniques for Credit Card Fraud Detection," Journal of Financial Security, 2023.
2. Patel, R., and Mehta, S., "Supervised Learning Methods for Fraud Detection in Financial Systems," IEEE Access, 2024.
3. Jiang, Y., et al., "Unsupervised Attentional Anomaly Detection for Financial Fraud," IEEE Transactions on AI, 2023.
4. Kumar, A., and Singh, P., "A Survey on Fraud Detection Techniques Using Machine Learning," ACM Computing Surveys, 2024.
5. C.Nagarajan and M.Madheswaran - ‘Stability Analysis of Series Parallel Resonant Converter with Fuzzy Logic Controller Using State Space Techniques’- Taylor &Francis, Electric Power Components and Systems, Vol.39 (8), pp.780-793, May 2011. DOI: 10.1080/15325008.2010.541746
6. C.Nagarajan and M.Madheswaran - ‘Experimental verification and stability state space analysis of CLL-T Series Parallel Resonant Converter’ - Journal of Electrical Engineering, Vol.63 (6), pp.365-372, Dec.2012. DOI: 10.2478/v10187-012-0054-2
7. C.Nagarajan and M.Madheswaran - ‘Performance Analysis of LCL-T Resonant Converter with Fuzzy/PID Using State Space Analysis’- Springer, Electrical Engineering, Vol.93 (3), pp.167-178, September 2011. DOI 10.1007/s00202-011-0203-9
8. S.Tamilselvi, R.Prakash, C.Nagarajan,“Solar System Integrated Smart Grid Utilizing Hybrid Coot-Genetic Algorithm Optimized ANN Controller” Iranian Journal Of Science And Technology-Transactions Of Electrical Engineering, DOI10.1007/s40998-025-00917-z,2025
9. S.Tamilselvi, R.Prakash, C.Nagarajan,“ Adaptive sliding mode control of multilevel grid-connected inverters using reinforcement learning for enhanced LVRT performance” Electric Power Systems Research 253 (2026) 112428, doi.org/10.1016/j.epsr.2025.112428
10. S.Thirunavukkarasu, C. Nagarajan, 2024, “Performance Investigation on OCF and SCF study in BLDC machine using FTANN Controller," Journal of Electrical Engineering And Technology, Volume 20, pages 2675–2688, (2025), doi.org/10.1007/s42835-024-02126-w
11. C. Nagarajan, M.Madheswaran and D.Ramasubramanian- ‘Development of DSP based Robust Control Method for General Resonant Converter Topologies using Transfer Function Model’- Acta Electrotechnica et Informatica Journal , Vol.13 (2), pp.18-31,April-June.2013, DOI: 10.2478/aeei-2013-0025.
12. C.Nagarajan and M.Madheswaran - ‘DSP Based Fuzzy Controller for Series Parallel Resonant converter’- Springer, Frontiers of Electrical and Electronic Engineering, Vol. 7(4), pp. 438-446, Dec.12. DOI 10.1007/s11460-012-0212-0.
13. C.Nagarajan and M.Madheswaran - ‘Experimental Study and steady state stability analysis of CLL-T Series Parallel Resonant Converter with Fuzzy controller using State Space Analysis’- Iranian Journal of Electrical & Electronic Engineering, Vol.8 (3), pp.259-267, September 2012.
14. C.Nagarajan and M.Madheswaran, “Analysis and Simulation of LCL Series Resonant Full Bridge Converter Using PWM Technique with Load Independent Operation” has been presented in ICTES’08, a IEEE / IET International Conference organized by M.G.R.University, Chennai.Vol.no.1, pp.190-195, Dec.2007
15. Suganthi Mullainathan, Ramesh Natarajan, “An SPSS and CNN modelling based quality assessment using ceramic materials and membrane filtration techniques”, Revista Materia (Rio J.) Vol. 30, 2025, DOI: https://doi.org/10.1590/1517-7076-RMAT-2024-0721
16. M Suganthi, N Ramesh, “Treatment of water using natural zeolite as membrane filter”, Journal of Environmental Protection and Ecology, Volume 23, Issue 2, pp: 520-530,2022
17. Rathore, S., and Park, J., "Real-Time Fraud Detection Using Machine Learning and Streaming Analytics," IEEE Conference on Big Data, 2025.
18. Dal Pozzolo, A., Caelen, O., Johnson, R. A., and Bontempi, G., "Calibrating Probability with Under sampling for Unbalanced Classification," 2015 IEEE Symposium Series on Computational Intelligence, pp. 159-166, 2015.
