Spade+: A Generic Real-Time Fraud Detection Framework on Dynamic Graphs
IEEE Transactions on Knowledge and Data Engineering · 2024-11 · 36 (11) · 7058-7073
DOI: 10.1109/tkde.2024.3394155 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2024-11. Verfasst von Jiaxin Jiang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Research Foundation Singapore, AI Singapore Programme.
Abstract (Originalsprache)
Real-time fraud detection remains a pressing issue for many financial and e-commerce platforms. $\mathsf {Grab}$ Grab , a prominent technology company in Southeast Asia, addresses this by constructing a transactional graph. This graph aids in pinpointing dense subgraphs, possibly indicative of fraudster networks. Notably, prevalent methods are designed for static graphs, neglecting the evolving nature of transaction graphs. This static approach is ill-suited to the real-time necessities of modern industries. In our earlier work, $\mathsf {Spade}$ Spade , the focus was mainly on edge insertions. However, $\mathsf {Grab}$ Grab 's operational demands necessitated managing outdated transactions. Persistently adding edges without a deletion mechanism might inadvertently lead to densely connected legitimate communities. To resolve this, we present $\mathsf {Spade+}$ Spade + , a refined real-time fraud detection system at $\mathsf {Grab}$ Grab . Contrary to $\mathsf {Spade}$ Spade , $\mathsf {Spade+}$ Spade + manages both edge additions and removals. Leveraging an incremental approach, $\mathsf {Spade+}$ Spade + promptly identifies suspicious communities in large graphs. Moreover, $\mathsf {Spade+}$ Spade + efficiently handles batch updates and employs edge packing to diminish latency. A standout feature of $\mathsf {Spade+}$ Spade + is its user-friendly APIs, allowing for tailored fraud detection methods. Developers can easily integrate their specific metrics, which $\mathsf {Spade+}$ Spade + autonomously refines. Rigorous evaluations validate the prowess of $\mathsf {Spade+}$ Spade + ; fraud detection mechanisms powered by $\mathsf {Spade+}$ Spade + were up to a million times faster than their static counterparts.
Förderung
- National Research Foundation Singapore
- AI Singapore Programme
Zitieren
APA
Jiang, J., Chen, Y., He, B., Chen, M., & Chen, J. (2024). Spade+: A Generic Real-Time Fraud Detection Framework on Dynamic Graphs. IEEE Transactions on Knowledge and Data Engineering, 36(11), 7058-7073. https://doi.org/10.1109/tkde.2024.3394155
Vancouver
Jiang J, Chen Y, He B, Chen M, Chen J. Spade+: A Generic Real-Time Fraud Detection Framework on Dynamic Graphs. IEEE Transactions on Knowledge and Data Engineering. 2024;36(11):7058-7073. doi:10.1109/tkde.2024.3394155
BibTeX
@article{Jiang2024,
author = {Jiang, Jiaxin and Chen, Yuhang and He, Bingsheng and Chen, Min and Chen, Jia},
title = {Spade+: A Generic Real-Time Fraud Detection Framework on Dynamic Graphs},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2024},
volume = {36},
number = {11},
pages = {7058--7073},
doi = {10.1109/tkde.2024.3394155}
}
EUVIMED