Innovative novel regularized memory graph attention capsule network for financial fraud detection
PLOS One · 2025
DOI: 10.1371/journal.pone.0317893 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Xiangting Shi und 5 weiteren Autor:innen. Beteiligte Einrichtung: Industrial Engineering and Operations Research Department, Columbia University, New York, New York, United States of America. Hauptthemen laut MEDLINE: Fraud, Neural Networks, Computer. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Financial fraud detection (FFD) is crucial for ensuring the safety and efficiency of financial transactions. This article presents the Regularised Memory Graph Attention Capsule Network (RMGACNet), an original architecture aiming at improving fraud detection using Bidirectional Long Short-Term Memory (BiLSTM) networks combined with advanced feature extraction and classification algorithms. The model is tested on two reliable datasets: the European Cardholder (ECH) transactions dataset, which contains 284,807 transactions and 492 fraud instances, and the IEEE-CIS dataset, which has more than 1 million transactions. Our approach enhances comparison to existing methods of feature selection and classification accuracy. On the ECH dataset, RMGACNet achieves an accuracy of 0.9772, a precision of 0.9768, and an F1 score of 0.9770 measures; on the IEEE-CIS dataset, it achieves an accuracy of 0.9882, a precision of 0.9876 and an F1 score of 0.9879. The findings indicate that RMGACNet routinely surpasses existing models’ efficiency and accuracy while ensuring strong execution time performance, especially when handling large-scale datasets. The suggested model demonstrates scalability and stability, making it suitable for real-time financial systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Industrial Engineering and Operations Research Department, Columbia University, New York, New York, United States of America.
- Department of Finance, The London School of Economics and Political Science, London, United Kingdom.
- College of Liberal Arts and Science, University of Illinois Urbana-Champaign, Illinois, United States of America.
- Department of Statistics, Columbia University, New York, New York, United States of America.
- Department of Information Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong.
ORCID-Profile: Xiangting Shi, Yakang Zhang, Lihao Zhang
Zitieren
APA
Shi, X., Wang, X., Zhang, Y., Zhang, X., Yu, M., & Zhang, L. (2025). Innovative novel regularized memory graph attention capsule network for financial fraud detection. PLOS One. https://doi.org/10.1371/journal.pone.0317893
Vancouver
Shi X, Wang X, Zhang Y, Zhang X, Yu M, Zhang L. Innovative novel regularized memory graph attention capsule network for financial fraud detection. PLOS One. 2025. doi:10.1371/journal.pone.0317893
BibTeX
@article{Shi2025,
author = {Shi, Xiangting and Wang, Xiaochen and Zhang, Yakang and Zhang, Xiaoyi and Yu, Manning and Zhang, Lihao},
title = {Innovative novel regularized memory graph attention capsule network for financial fraud detection},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0317893}
}
EUVIMED