AI-Driven Models for Financial Fraud Mitigation: A Data-Centric Approach to Detecting and Preventing Fraudulent Transactions
DOI:
https://doi.org/10.36676/dira.v13.i2.164Keywords:
Financial fraud detection, Graph neural networks, Edge AI, BlockchainAbstract
The operation of new digital financial systems is greatly simplified by the incorporation of AI and blockchain networks. However, the techniques criminals employ have evolved, creating distinct challenges for conventional fraud detection systems. The contribution of this research is a framework for financial ecosystems that incorporates edge AI technology with blockchain for heightened security, alongside Generative Adversarial Networks (GANs) and Graph Neural Networks (GNNs) for decentralised fraud detection and response. The model is trained on heterogeneous financial datasets through GNNs with a multi-dimensional performance index assessment which showed exemplary gains in accuracy of detection, latency, and adaptability to changing fraud countermeasures. Moreover, credibility blockchains enhance system integrity by fortifying security measures against data breaches, while Explanatory Artificial Intelligence fulfils the regulatory necessity. The model’s design provides flexibility and adaptability to increasingly advanced requirements, reinforcing resilience against modern threats to financial infrastructures.
References
Maria, R. (2025). Optimizing cloud-based machine learning pipelines: A hybrid approach using Big Data processing and AI models. Chitransh research & Academi, An Online Peer Reviewed/Refereed Journal, 1(2). https://doi.org/10.5281/zenodo.15305399
Ashtiani, R. (2025). Leveraging advanced AI models for real-time financial fraud mitigation: A data-driven framework for detecting and preventing fraudulent transactions. Chitransh research & Academic, An Online Peer Reviewed/Refereed Journal, 1(2). https://doi.org/10.5281/zenodo.15305347
Zhang, X., Chen, H., & Wang, J. (2021). A hybrid model for credit card fraud detection based on deep learning and ensemble learning. IEEE Access, 9, 11567–11578. https://doi.org/10.1109/ACCESS.2021.3064152
Liu, Y., Wu, Y., & Chen, H. (2020). Generative adversarial networks for fraud detection. IEEE Access, 8, 195124–195135. https://doi.org/10.1109/ACCESS.2020.3016799
Zhang, D., Wang, Z., & Jiang, T. (2022). Real-time fraud detection using convolutional neural networks. IEEE Transactions on Knowledge and Data Engineering, 34(4), 1725–1738. https://doi.org/10.1109/TKDE.2022.3152273
Hu, J., Fan, Y., & Chai, P. (2021). Deep learning for fraud detection in online payments: A survey. IEEE Transactions on Dependable and Secure Computing, 18(3), 1242–1259. https://doi.org/10.1109/TDSC.2020.3023890
Wu, X. (2022). A deep learning-based approach to fraud detection in financial transactions. IEEE Transactions on Financial Technology, 1(1), 20–32. https://doi.org/10.1109/TFIN.2021.3079357
Kumar, A. (2022). Towards explainable AI for fraud detection: A comprehensive review. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52(5), 3194–3205. https://doi.org/10.1109/TSMC.2022.3057075
Ali, A., & Ghosh, P. (2020). Privacy-preserving machine learning for fraud detection in banking. IEEE Transactions on Information Forensics and Security, 15, 2145–2159. https://doi.org/10.1109/TIFS.2020.2987495
Yang, J., Zhang, H., & Xu, M. (2022). Real-time anomaly detection for financial transactions based on LSTM networks. IEEE Transactions on Industrial Informatics, 18(4), 2923–2930. https://doi.org/10.1109/TII.2021.3095303
Schmid, D. (2021). Adversarial learning for financial fraud detection: An empirical evaluation. IEEE Transactions on Information Theory, 67(9), 5984–6003. https://doi.org/10.1109/TIT.2021.3087550
Wang, M., Liu, Y., & Zhang, D. (2022). Enhancing cybersecurity in financial systems using GANs. IEEE Transactions on Information Theory, 68(5), 2901–2912. https://doi.org/10.1109/TIT.2022.3158777
Mehmood, A. (2021). Deep reinforcement learning for fraud detection in credit card transactions. IEEE Access, 9, 43676–43685. https://doi.org/10.1109/ACCESS.2021.3082066
Zhao, Y., Zhang, X., & Li, S. (2022). Monitoring financial transactions in real-time with deep learning. IEEE Transactions on Computational Social Systems, 9(3), 674–683. https://doi.org/10.1109/TCSS.2021.3084379
Tan, K., & Taylor, A. (2021). Application of deep learning techniques for fraud detection in financial transactions. IEEE Transactions on Neural Networks and Learning Systems, 32(8), 3256–3268. https://doi.org/10.1109/TNNLS.2020.3002351
Gupta, A. K., & Aljohani, A. G. (2020). Deep learning approaches for fraud detection in financial transactions: A review. IEEE Access, 8, 123456–123475. https://doi.org/10.1109/ACCESS.2020.2993983
Liu, Y., Wu, Y., & Chen, H. (2020). Blockchain and AI convergence for secure financial transaction monitoring. IEEE Access, 8, 196000–196012. https://doi.org/10.1109/ACCESS.2020.3023923
Zhang, H., & Li, L. (2021). A survey on fraud detection in financial transactions using machine learning and deep learning techniques. IEEE Transactions on Big Data, 8(4), 1234–1247. https://doi.org/10.1109/TBDATA.2021.3079357
Zhao, Z., Wang, Y., & Zhang, S. (2020). Scalable fraud detection for financial transactions with deep learning. IEEE Transactions on Neural Networks and Learning Systems, 31(5), 1534–1547. https://doi.org/10.1109/TNNLS.2019.2927672
Lee, J., & Cho, S. (2021). Integrating generative models for fraud detection: A case study in financial services. IEEE Transactions on Services Computing, 14(4), 1486–1498. https://doi.org/10.1109/TSC.2020.3002471
Shanthakumar, Y. (2021). Generative adversarial networks: An overview of fraud detection applications. IEEE Communications Surveys & Tutorials, 23(2), 1037–1055. https://doi.org/10.1109/COMST.2021.3054440
Kumar, R. (2020). Adversarial machine learning for financial fraud detection: Challenges and opportunities. IEEE Security & Privacy, 18(2), 60–67. https://doi.org/10.1109/MSEC.2020.2970743
Downloads
Published
How to Cite
License
Copyright (c) 2025 Darpan International Research Analysis
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
