Harnessing AI to Enhance Security in Digital Payments: Detection of High-Risk Users and Mitigation of Financial Crime
Keywords:
Artificial Intelligence, Digital Payments, Fraud Detection, High-Risk Users, Financial CrimeAbstract
The escalating complexity of financial crime in digital payment systems demands robust solutions to detect high-risk users and mitigate fraud. This paper explores artificial intelligence (AI) applications for enhancing transaction secu- rity through real-time anomaly detection, behavioral biometrics, and adaptive machine learning models. By analyzing transaction velocity, geolocation, and device interactions, AI systems achieve 98.7% accuracy in identifying fraudu- lent activities, reducing false positives by 40% compared to rule-based systems. Building on Chen and Zhao’s (2021) evaluation of supervised learning mod- els, we demonstrate the efficacy of hybrid AI architectures combining graph neural networks and anomaly detection algorithms. Case studies highlight AI’s role in thwarting synthetic identity fraud and adversarial attacks, with sys- tems processing 10,000+ transactions per second. Ethical challenges, including algorithmic bias and data privacy, are addressed through explainable AI (XAI) frameworks. The study concludes with recommendations for federated learning and blockchain-AI integration to combat cross-border money laundering[1].
Downloads
References
Chen, L., Zhao, M.: Machine learning for fraud detection in payment systems. IEEE Transactions on Neural Networks and Learning Systems 32(4), 1234–1245
Mavroeidis, V., Bromander, S.: Artificial intelligence for detecting financial fraud: Challenges and opportunities. IEEE Security & Privacy 19(2), 76–84
Gupta, R., Patel, S.: Real-time anomaly detection in cross-border payment sys- tems using federated learning. ACM Transactions on Management Information Systems 14(3), 1–24
Johnson, M., Lee, E., Chen, W.: Hybrid machine learning architectures for fraud detection in high-frequency transactions. IEEE Access 9, 145678–145692
Smith, J., Kumar, A.: Fairness-aware ai for financial crime detection: A demo- graphic parity approach. Nature Machine Intelligence 4(11), 987–1001
Nanda, A.P., et al.: Role of ai in enhancing digital payment security. African Journal of Biomedical Research 27(3s), 2113–2114
Sharma, N., Garg, S., Singla, S.: Ai-powered digital payments: Evolution, securing transactions & preventing fraud. International Journal of Innovative Research in Technology 12, 4253–4260
Anonymous: Ai and machine learning in fraud detection: Securing digital pay- ments and economic stability. International Journal of Scientific Research in Science and Technology 11(2), 1–15
Gupta, S., Patel, R.: Federated learning for privacy-preserving fraud detection. ACM Transactions on Knowledge Discovery from Data 17(8), 1–25
Chen, W., Zhang, L.: Fairness in ai-driven financial systems. Nature Machine Intelligence 6(3), 221–230
Sharma, N., Singh, A.: Explainable ai for regulatory compliance in banking. Journal of Financial Compliance 7(1), 45–63
Anonymous: Ai-driven fraud detection in banking: A systematic review of data science approaches. GSC Advanced Research and Reviews 21(2), 227–237 https: //doi.org/10.30574/gscarr.2024.21.2.0418
Anonymous: Enhancing performance of financial fraud detection through machine learning model. SSRN Electronic Journal https://doi.org/10.2139/ssrn.4993827
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
