Identifying Linked Fraudulent Activities Using GraphConvolution Network

TL;DR

This paper introduces a Graph Convolution Network-based method to detect linked fraudulent activities, overcoming traditional limitations by learning similarities between nodes with less training data and outperforming existing methods.

Contribution

The paper presents a novel GCN-based approach for identifying linked fraud activities that requires less data and improves detection accuracy over traditional community detection and supervised methods.

Findings

Outperforms label propagation and GBTs in solution quality

Requires smaller datasets for training

Effectively detects fraud rings with both strong and weak links

Abstract

In this paper, we present a novel approach to identify linked fraudulent activities or actors sharing similar attributes, using Graph Convolution Network (GCN). These linked fraudulent activities can be visualized as graphs with abstract concepts like relationships and interactions, which makes GCNs an ideal solution to identify the graph edges which serve as links between fraudulent nodes. Traditional approaches like community detection require strong links between fraudulent attempts like shared attributes to find communities and the supervised solutions require large amount of training data which may not be available in fraud scenarios and work best to provide binary separation between fraudulent and non fraudulent activities. Our approach overcomes the drawbacks of traditional methods as GCNs simply learn similarities between fraudulent nodes to identify clusters of similar attempts and require much smaller dataset to learn. We demonstrate our results on linked accounts with both strong and weak links to identify fraud rings with high confidence. Our results outperform label propagation community detection and supervised GBTs algorithms in terms of solution quality and computation time.