基于图神经网络的银行交易欺诈检测方法  

Bank Transaction Fraud Detection Method Based on Graph Neural Network

作　　者：秦忠飘 周亚同 李哲 QIN Zhongpiao;ZHOU Yatong;LI Zhe(School of Electronics and Information Engineering,Hebei University of Technology,Tianjin 300401,China;Institute of Digital Economy Industry Research,Hebei University of Technology,Shijiazhuang 050000,China)

机构地区：[1]河北工业大学电子信息工程学院,天津300401 [2]河北工业大学数字经济产业研究院,石家庄050000

出　　处：《计算机科学》2024年第S02期911-918,共8页Computer Science

基　　金：京津冀基础研究合作专项(J210008,21JCZXJC00170,H2021202008);内蒙古自治区纪检监察大数据实验室开放课题(IMDBD202105)。

摘　　要：随着电子支付的迅速发展,欺诈问题日益增多。传统欺诈检测方法受限于规则和特征工程,难以捕获复杂的交易模式。相反,基于图的方法虽然强调了数据的关系性,但通常忽略了特征工程的重要性。为了解决这个问题,提出一种端到端的电信诈骗检测方法——基于图神经网络的银行交易欺诈检测方法。该方法设计了一个针对图数据的特征工程,并利用融合模型对其进行训练。具体来说,使用过采样和设置节点权重的方式对银行交易数据进行不平衡处理,然后采用改进的自适应相似度边和节点度权重融合策略,构建用户交易图数据并挖掘交易节点间的潜在关联信息,最后综合局部特征和全局特征通过模型融合来弥补单一分类器的不足。实验结果表明,在广西玉林银行的交易数据中,所提模型对于交易欺诈数据的检测在F1分数、召回率、AUC 3个指标上相比GraphSAGE分别提升1.65,1.36,4.2个百分点,图数据构建时间缩短了80%左右,与其他主流的检测算法相比也取得了更高的检测精度。With the rapid development of electronic payments,the fraud problem is increasing.Limited by rule and feature engineering,traditional fraud detection methods are difficult to capture complex transaction patterns.Conversely,graph-based me-thods often downplay the significance of feature engineering while highlighting the relational aspect of the data.In addition,few studies have examined the application of graph methods in the field of fraud detection for specific bank transaction data.To address this problem,this paper proposes an end-to-end telecom fraud detection method,a fraud detection method for banking transactions based on graph neural networks.The proposed method designs a feature engineering for graph models and trains it using a fusion model.Specifically,oversampling and node weighting are used to address the unbalanced dataset.Next,a user transaction graph model is built utilizing an adaptive similarity edge and node degree weight fusion technique to construct a user transaction graph model and mine potential correlation information between transaction nodes.Furthermore,model fusion is employed to merge local and global variables to overcome the constraints of separate classifiers.Experimental results show that in Guangxi Yulin Bank transaction data,the proposed model for the detection of transaction fraud data on the three indicators of F1 score,recall rate,and AUC is improved by 1.65%,1.36% and 4.2% compared to GraphSAGE,respectively.The model also achieves a reduction of approximately 80% in training time.In comparison to other mainstream detection algorithms,it exhibits higher detection accuracy.

关 键 词：银行交易欺诈检测 特征工程 不平衡处理 相似度边 图神经网络 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] F830.49[自动化与计算机技术—控制科学与工程]