Spade plus : A Generic Real-Time Fraud Detection Framework on Dynamic Graphs

Real-time fraud detection remains a pressing issue for many financial and e-commerce platforms. 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, Spade, , the focus was mainly on edge insertions. However, Grab's 's operational demands necessitated managing outdated transactions.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 Spade+, , a refined real-time fraud detection system at Grab. . Contrary to Spade, , Spade+ manages both edge additions and removals. Leveraging an incremental approach, Spade+ promptly identifies suspicious communities in large graphs. Moreover, Spade+ efficiently handles batch updates and employs edge packing to diminish latency. A standout feature of Spade+ is its user-friendly APIs, allowing for tailored fraud detection methods. Developers can easily integrate their specific metrics, which Spade+ autonomously refines. Rigorous evaluations validate the prowess of Spade+; ; fraud detection mechanisms powered by Spade+ were up to a million times faster than their static counterparts.