AI-Driven Anomaly Detection in Real-Time Payment Processing Systems
International Journal of Computational and Experimental Science and Engineering · 02.10.2024 · 10 (4)
DOI: 10.22399/ijcesen.5194 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computational and Experimental Science and Engineering, online erschienen am 02.10.2024. Verfasst von Anil Putapu. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The rapid digitization of financial services has significantly increased the volume and velocity of payment transactions, exposing systems to increasingly sophisticated fraud schemes and cyber threats. Traditional rule-based fraud detection approaches are becoming progressively inadequate for handling the dynamic, large-scale, and high-dimensional nature of modern transactional data. These systems often fail to detect emerging fraud patterns and tend to generate high false-positive rates, thereby impacting operational efficiency and user experience. This paper investigates the role of artificial intelligence (AI), particularly machine learning and deep learning techniques, in enabling effective real-time anomaly detection within payment processing systems. It presents a scalable and robust architectural framework that integrates streaming analytics, behavioral modeling, and adaptive learning mechanisms to improve detection accuracy while maintaining low processing latency. The proposed approach leverages both supervised and unsupervised learning methods to identify known and previously unseen fraudulent activities. The study synthesizes existing literature to establish a comprehensive conceptual framework for AI-driven anomaly detection and critically examines key implementation challenges, including data imbalance, model interpretability, computational complexity, and data privacy concerns. Additionally, the paper discusses the importance of continuous model updating and feedback loops in adapting to evolving fraud strategies. The findings indicate that AI-based systems significantly outperform traditional rule-based approaches in detecting complex and subtle fraud patterns. These systems enhance the resilience, scalability, and adaptability of real-time payment infrastructures, making them essential for securing modern financial ecosystems against rapidly evolving threats.
Zitieren
APA
Putapu, A. (2024). AI-Driven Anomaly Detection in Real-Time Payment Processing Systems. International Journal of Computational and Experimental Science and Engineering, 10(4). https://doi.org/10.22399/ijcesen.5194
Vancouver
Putapu A. AI-Driven Anomaly Detection in Real-Time Payment Processing Systems. International Journal of Computational and Experimental Science and Engineering. 2024;10(4). doi:10.22399/ijcesen.5194
BibTeX
@article{Putapu2024,
author = {Putapu, Anil},
title = {AI-Driven Anomaly Detection in Real-Time Payment Processing Systems},
journal = {International Journal of Computational and Experimental Science and Engineering},
year = {2024},
volume = {10},
number = {4},
doi = {10.22399/ijcesen.5194}
}
EUVIMED