期刊
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
卷 34, 期 8, 页码 3800-3813出版社
IEEE COMPUTER SOC
DOI: 10.1109/TKDE.2020.3025588
关键词
Neural networks; Task analysis; Credit cards; Three-dimensional displays; Feature extraction; Convolution; Predictive models; Fraud detection; spatial-temporal attention; graph neural network
类别
资金
- National Key R&D Program of China [2018AAA0100704]
- China Postdoctoral Science Foundation [2019M651499]
- National Natural Science Foundation of China [61802345]
- ARC [DP180103096, FT170100128]
This article introduces a spatial-temporal attention-based graph network (STAGN) for credit card fraud detection, and demonstrates its superiority in fraud detection and knowledge discovery through experiments and research with domain experts.
Card fraud is an important issue and incurs a considerable cost for both cardholders and issuing banks. Contemporary methods apply machine learning-based approaches to detect fraudulent behavior from transaction records. But manually generating features needs domain knowledge and may lay behind the modus operandi of fraud, which means we need to automatically focus on the most relevant fraudulent behavior patterns in the online detection system. Therefore, in this work, we propose a spatial-temporal attention-based graph network (STAGN) for credit card fraud detection. In particular, we learn the temporal and location-based transaction graph features by a graph neural network first. Afterwards, we employ the spatial-temporal attention on top of learned tensor representations, which are then fed into a 3D convolution network. The attentional weights are jointly learned in an end-to-end manner with 3D convolution and detection networks. After that, we conduct extensive experiments on the real-word card transaction dataset. The result shows that STAGN performs better than other state-of-the-art baselines in both AUC and precision-recall curves. Moreover, we conduct empirical studies with domain experts on the proposed method for fraud detection and knowledge discovery; the result demonstrates its superiority in detecting suspicious transactions, mining spatial and temporal fraud hotspots, and uncover fraud patterns. The effectiveness of the proposed method in other user behavior-based tasks is also demonstrated. Finally, in order to tackle the challenges of big data, we integrate our proposed STAGN into the fraud detection system as the predictive model and present the implementation detail of each module in the system.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据