FraudNE: a joint embedding approach for fraud detection

Mengyu Zheng, Chuan Zhou, Jia Wu, Shirui Pan, Jinqiao Shi, And Li Guo

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

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.

Original languageEnglish
Title of host publication2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings
EditorsTeresa Ludermir
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages4739-4746
Number of pages8
ISBN (Electronic)9781509060146
ISBN (Print)9781509060153
DOIs
Publication statusPublished - 2018
Externally publishedYes
EventIEEE International Joint Conference on Neural Networks 2018 - Rio de Janeiro, Brazil
Duration: 8 Jul 201813 Jul 2018
Conference number: 2018
http://www.ecomp.poli.br/~wcci2018/

Conference

ConferenceIEEE International Joint Conference on Neural Networks 2018
Abbreviated titleIJCNN 2018
CountryBrazil
CityRio de Janeiro
Period8/07/1813/07/18
Internet address

Keywords

  • Deep Structure Learning
  • Dense Block Detection
  • Network Embedding

Cite this

Zheng, M., Zhou, C., Wu, J., Pan, S., Shi, J., & Guo, A. L. (2018). FraudNE: a joint embedding approach for fraud detection. In T. Ludermir (Ed.), 2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings (pp. 4739-4746). [8489585] Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IJCNN.2018.8489585
Zheng, Mengyu ; Zhou, Chuan ; Wu, Jia ; Pan, Shirui ; Shi, Jinqiao ; Guo, And Li. / FraudNE : a joint embedding approach for fraud detection. 2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings. editor / Teresa Ludermir. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 4739-4746
@inproceedings{8cf13e68c8d54631b256191a33c73265,
title = "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.",
keywords = "Deep Structure Learning, Dense Block Detection, Network Embedding",
author = "Mengyu Zheng and Chuan Zhou and Jia Wu and Shirui Pan and Jinqiao Shi and Guo, {And Li}",
year = "2018",
doi = "10.1109/IJCNN.2018.8489585",
language = "English",
isbn = "9781509060153",
pages = "4739--4746",
editor = "Teresa Ludermir",
booktitle = "2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Zheng, M, Zhou, C, Wu, J, Pan, S, Shi, J & Guo, AL 2018, FraudNE: a joint embedding approach for fraud detection. in T Ludermir (ed.), 2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings., 8489585, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 4739-4746, IEEE International Joint Conference on Neural Networks 2018, Rio de Janeiro, Brazil, 8/07/18. https://doi.org/10.1109/IJCNN.2018.8489585

FraudNE : a joint embedding approach for fraud detection. / Zheng, Mengyu; Zhou, Chuan; Wu, Jia; Pan, Shirui; Shi, Jinqiao; Guo, And Li.

2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings. ed. / Teresa Ludermir. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 4739-4746 8489585.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - FraudNE

T2 - a joint embedding approach for fraud detection

AU - Zheng, Mengyu

AU - Zhou, Chuan

AU - Wu, Jia

AU - Pan, Shirui

AU - Shi, Jinqiao

AU - Guo, And Li

PY - 2018

Y1 - 2018

N2 - 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.

AB - 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.

KW - Deep Structure Learning

KW - Dense Block Detection

KW - Network Embedding

UR - http://www.scopus.com/inward/record.url?scp=85056514379&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2018.8489585

DO - 10.1109/IJCNN.2018.8489585

M3 - Conference Paper

SN - 9781509060153

SP - 4739

EP - 4746

BT - 2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings

A2 - Ludermir, Teresa

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Zheng M, Zhou C, Wu J, Pan S, Shi J, Guo AL. FraudNE: a joint embedding approach for fraud detection. In Ludermir T, editor, 2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 4739-4746. 8489585 https://doi.org/10.1109/IJCNN.2018.8489585