Suspicious Massive Registration Detection via Dynamic Heterogeneous Graph Neural Networks
This work provides an early-stage detection method for suspicious registration behaviors, which is significant for e-commerce companies to minimize potential financial losses.
This paper addresses the problem of detecting suspicious massive account registrations in e-commerce by proposing a Dynamic Heterogeneous Graph Neural Network (DHGReg) framework. The model constructs a dynamic heterogeneous graph from registration data and predicts suspicious/benign accounts, outperforming baseline models and demonstrating computational efficiency on a real-world dataset.
Massive account registration has raised concerns on risk management in e-commerce companies, especially when registration increases rapidly within a short time frame. To monitor these registrations constantly and minimize the potential loss they might incur, detecting massive registration and predicting their riskiness are necessary. In this paper, we propose a Dynamic Heterogeneous Graph Neural Network framework to capture suspicious massive registrations (DHGReg). We first construct a dynamic heterogeneous graph from the registration data, which is composed of a structural subgraph and a temporal subgraph. Then, we design an efficient architecture to predict suspicious/benign accounts. Our proposed model outperforms the baseline models and is computationally efficient in processing a dynamic heterogeneous graph constructed from a real-world dataset. In practice, the DHGReg framework would benefit the detection of suspicious registration behaviors at an early stage.