FraudNE: a joint embedding approach for fraud detection

Abstract

Detecting fraudsters is a meaningful problem for both users and e-commerce platform. Existing graph-based approaches mainly adopt shallow models, which cannot capture the highly non-linear relationship between vertexes in a bipartite graph composed of users and items. To address this issue, in this paper we propose a joint deep structure embedding approach FraudNE for fraud detection that (a) can preserve the highly non-linear structural information of networks, (b) is robust to sparse networks, (c) embeds different types of vertexes jointly in the same latent space. It is worth mentioning that we can detect multiple fraudulent groups without the number of groups as a priori. Compared with baselines, our method achieved significant accuracy improvement.

Publication
2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings
Shirui Pan
Shirui Pan
Professor and ARC Future Fellow

My research interests include data mining, machine learning, and graph analysis.