Spatio-Temporal Attention-Based Neural Network for Credit Card Fraud Detection

Abstract

Credit card fraud is an important issue and incurs a considerable cost for both cardholders and issuing institutions. 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 patterns in fraudulent behavior. Therefore, in this work, we propose a spatial-temporal attention-based neural network (STAN) for fraud detection. In particular, transaction records are modeled by attention and 3D convolution mechanisms by integrating the corresponding information, including spatial and temporal behaviors. Attentional weights are jointly learned in an end-to-end manner with 3D convolution and detection networks. Afterward, we conduct extensive experiments on real-word fraud transaction dataset, the result shows that STAN 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 post-analysis; the result demonstrates the effectiveness of our proposed method in both detecting suspicious transactions and mining fraud patterns.

NAG: neural feature aggregation framework for credit card fraud detection

“…They compare this likelihood value to a threshold value to determine whether the transaction is fraudulent. Another recent approach has been to use a spatiotemporal attention mechanism along with 3d convolution layers to learn end-to-end spatial and temporal feature aggregations [7]. Nami and Shajari [30] use the average distance similarity measure between the current and past transactions as additional context for the model's decision, here a fading factor is used to assign more weight to more recent transactions.…”

Risk assessment for contagion path in complex loan network

“…在端到端的网络特征学 习方面, 研究者们提出了图神经网络来处理图数据 [15] . 例如: 图注意力网络 [6] 可以用注意机制确定 节点邻域的权重; 图时空网络可以同时捕捉时空图的时空相关性, 来预测未来时空图中的节点值或标 签, 在预测不同区域的网约车用车量 [16] 、网络节点类别预测 [17] 等方面得到了很好的应用. 在担保网 络中, BHONEM [18] 基于担保网络的节点角色的二元性和节点距离的高阶性提出了二元高阶担保网络 表示学习模型用于单个节点的风险特征提取.…”

Fraud Detection: A Study of AdaBoost Classifier and K-Means Clustering

“…A hierarchical structure was created for node-level attention and view level attention. An attention-based neural network for credit card fraud detection was proposed in [4]. Opinion fraud detection can be done by using decision trees as shown in [5].…”