EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Real Time Fraud Detection at Scale in High Volume Enterprise Payment Ecosystems

Yuxuan Qin, Jiesi Yang, Zimeng Wang

Journal of Computing and Electronic Information Management · 22.04.2026 · 21 (1) · 19-26

DOI: 10.54097/51td8c59 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computing and Electronic Information Management, online erschienen am 22.04.2026. Verfasst von Yuxuan Qin und 2 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid proliferation of digital payment channels has created unprecedented opportunities for fraudulent activity, compelling enterprise organizations to deploy increasingly sophisticated detection mechanisms capable of operating at high throughput with minimal latency. This paper presents a comprehensive review of real-time fraud detection (RTFD) methodologies applied within high-volume enterprise payment ecosystems, encompassing machine learning (ML), deep learning (DL), graph neural networks (GNN), and streaming data architectures. We examine how ensemble methods, anomaly detection frameworks, and feature engineering pipelines converge to form robust, production-grade fraud detection systems (FDS). The paper further discusses the tension between detection accuracy and operational latency, the challenge of class imbalance in transactional datasets, and the evolving regulatory landscape that shapes deployment constraints. By synthesizing findings from recent literature, this review identifies key trends including federated learning (FL) for privacy-preserving fraud detection, transformer-based sequence models for behavioral analysis, and adaptive threshold mechanisms for dynamic fraud pattern recognition. Our analysis reveals that no single algorithmic approach suffices in isolation; rather, layered architectures combining rule-based systems with data-driven models consistently achieve superior performance across precision, recall, and throughput metrics in enterprise-scale deployments.

Zitieren

APA

Qin, Y., Yang, J., & Wang, Z. (2026). Real Time Fraud Detection at Scale in High Volume Enterprise Payment Ecosystems. Journal of Computing and Electronic Information Management, 21(1), 19-26. https://doi.org/10.54097/51td8c59

Vancouver

Qin Y, Yang J, Wang Z. Real Time Fraud Detection at Scale in High Volume Enterprise Payment Ecosystems. Journal of Computing and Electronic Information Management. 2026;21(1):19-26. doi:10.54097/51td8c59

BibTeX
@article{Qin2026,
  author = {Qin, Yuxuan and Yang, Jiesi and Wang, Zimeng},
  title = {Real Time Fraud Detection at Scale in High Volume Enterprise Payment Ecosystems},
  journal = {Journal of Computing and Electronic Information Management},
  year = {2026},
  volume = {21},
  number = {1},
  pages = {19--26},
  doi = {10.54097/51td8c59}
}
Kostenlos starten →