Graph Neural Networks in Real-Time Fraud Detection with Lambda Architecture
This work addresses fraud detection for e-commerce marketplaces, representing an incremental advancement by combining graph networks with a lambda architecture for real-time processing.
The paper tackles transaction checkout fraud detection in e-commerce by proposing a Directed Dynamic Snapshot (DDS) linkage design for graph construction and a Lambda Neural Networks (LNN) architecture for inference with Graph Neural Networks embeddings, resulting in significant performance improvements over baseline models with computational efficiency for real-time applications.
Transaction checkout fraud detection is an essential risk control components for E-commerce marketplaces. In order to leverage graph networks to decrease fraud rate efficiently and guarantee the information flow passed through neighbors only from the past of the checkouts, we first present a novel Directed Dynamic Snapshot (DDS) linkage design for graph construction and a Lambda Neural Networks (LNN) architecture for effective inference with Graph Neural Networks embeddings. Experiments show that our LNN on DDS graph, outperforms baseline models significantly and is computational efficient for real-time fraud detection.