PromoGuardian: Detecting Promotion Abuse Fraud with Multi-Relation Fused Graph Neural Networks

TL;DR

PromoGuardian tackles promotion abuse fraud in e-commerce by modeling authentic perpetrators as groups exhibiting high spatial-temporal cohesion across multiple relations. It constructs a multi-relational, fused homogeneous graph and uses kg-based relation embeddings with weighted concatenation, followed by attention-based aggregation and a semi-supervised autoencoder, plus anomaly propagation to scale in production. Evaluations on a real Meituan dataset and a public subset show superior precision, recall, and economic impact compared with state-of-the-art baselines, with successful deployment reducing losses. The work provides a practical framework and open resources for researching fraud detection in large-scale, real-world e-commerce environments, highlighting the importance of cross-relational cohesion in identifying coordinated abuse.

Abstract

As e-commerce platforms develop, fraudulent activities are increasingly emerging, posing significant threats to the security and stability of these platforms. Promotion abuse is one of the fastest-growing types of fraud in recent years and is characterized by users exploiting promotional activities to gain financial benefits from the platform. To investigate this issue, we conduct the first study on promotion abuse fraud in e-commerce platforms MEITUAN. We find that promotion abuse fraud is a group-based fraudulent activity with two types of fraudulent activities: Stocking Up and Cashback Abuse. Unlike traditional fraudulent activities such as fake reviews, promotion abuse fraud typically involves ordinary customers conducting legitimate transactions and these two types of fraudulent activities are often intertwined. To address this issue, we propose leveraging additional information from the spatial and temporal perspectives to detect promotion abuse fraud. In this paper, we introduce PROMOGUARDIAN, a novel multi-relation fused graph neural network that integrates the spatial and temporal information of transaction data into a homogeneous graph to detect promotion abuse fraud. We conduct extensive experiments on real-world data from MEITUAN, and the results demonstrate that our proposed model outperforms state-of-the-art methods in promotion abuse fraud detection, achieving 93.15% precision, detecting 2.1 to 5.0 times more fraudsters, and preventing 1.5 to 8.8 times more financial losses in production environments.

Figures (6)

• Figure 1: The distribution of the number of relations between users.
• Figure 2: (a) Users and transactions on the e-commerce platform. Users connected with certain products indicate that they purchase this product. Users connected by the same line type indicate that their transactions share the same value in that relation. (b) Users establish connections when their transactions involve the same product and share the same relation value. User $v_{2}$ does not have any relation with other users and is therefore not shown in the fused graph.
• Figure 3: Workflow of PromoGuardian.
• Figure 4: The detection performance of PromoGuardian and baselines in real-world deployment.
• Figure 5: The ablation study of PromoGuardian in real-world deployment.