文献类型：期刊文献

英文题名：Improving graph-based label propagation algorithm with group partition for fraud detection

作者：Wang, Jiahui[1];Guo, Yi[1,2,3];Wen, Xinxiu[1];Wang, Zhihong[1];Li, Zhen[4];Tang, Minwei[4]

机构：[1]East China Univ Sci & Technol, Shanghai, Peoples R China;[2]Natl Engn Lab Big Data Distribut & Exchange Techn, Shanghai, Peoples R China;[3]Shanghai Engn Res Ctr Big Data & Internet Audienc, Shanghai, Peoples R China;[4]China Telecom BestPay Co Ltd, Shanghai, Peoples R China

年份：2020

卷号：50

期号：10

起止页码：3291

外文期刊名：APPLIED INTELLIGENCE

收录：;EI(收录号：20202208769874);WOS:【SCI-EXPANDED(收录号:WOS:000535665300001)】；

基金：This research is financially supported by The National Key Research and Development Program of China (grant number 2018YFC0807105), National Natural Science Foundation of China (grant number 61462073) and Science and Technology Committee of Shanghai Municipality (STCSM) (under grant numbers 17DZ1101003, 18511106602 and 18DZ2252300).

语种：英文

外文关键词：Label propagation; Group partition; Semi-supervised; Knowledge graph; Fraud detection; Risk management

摘要：Fraudulent user detection is a crucial issue in financial risk management. Due to the lack of labeled data and the reliability of labeling, label propagation algorithms (LPA) are effective solutions in this scenario. Most existing models only propagate the risk probabilities for individual users through feature level, while ignoring the real-world graph structure and the characteristics of gang crime. This paper improves the graph-based LPA through group partition, which can be directly implemented on the graph at hand with full consideration of the group information. The exhaustive experimental results testify the performance of our proposed model KGLPA over other off-the-shelf models and amend the insufficiency of feature-based LPA with higher reliability and stability to improve the detection of fraudulent users and secure the marketing budgets.