Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Financial Anti-Fraud Based on Dual-Channel Graph Attention Network
Journal of Theoretical and Applied Electronic Commerce Research ( IF 5.318 ) Pub Date : 2024-02-02 , DOI: 10.3390/jtaer19010016
Sizheng Wei 1, 2 , Suan Lee 2
Affiliation  

This article addresses the pervasive issue of fraud in financial transactions by introducing the Graph Attention Network (GAN) into graph neural networks. The article integrates Node Attention Networks and Semantic Attention Networks to construct a Dual-Head Attention Network module, enabling a comprehensive analysis of complex relationships in user transaction data. This approach adeptly handles non-linear features and intricate data interaction relationships. The article incorporates a Gradient-Boosting Decision Tree (GBDT) to enhance fraud identification to create the GBDT–Dual-channel Graph Attention Network (GBDT-DGAN). In a bid to ensure user privacy, this article introduces blockchain technology, culminating in the development of a financial anti-fraud model that fuses blockchain with the GBDT-DGAN algorithm. Experimental verification demonstrates the model’s accuracy, reaching 93.82%, a notable improvement of at least 5.76% compared to baseline algorithms such as Convolutional Neural Networks. The recall and F1 values stand at 89.5% and 81.66%, respectively. Additionally, the model exhibits superior network data transmission security, maintaining a packet loss rate below 7%. Consequently, the proposed model significantly outperforms traditional approaches in financial fraud detection accuracy and ensures excellent network data transmission security, offering an efficient and secure solution for fraud detection in the financial domain.

中文翻译:

基于双通道图注意力网络的金融反欺诈

本文通过将图注意力网络(GAN)引入图神经网络来解决金融交易中普遍存在的欺诈问题。文章集成了节点注意力网络和语义注意力网络,构建了双头注意力网络模块,能够全面分析用户交易数据中的复杂关系。这种方法能够熟练地处理非线性特征和复杂的数据交互关系。该文章结合了梯度提升决策树(GBDT)来增强欺诈识别,以创建 GBDT-双通道图注意力网络(GBDT-DGAN)。为了确保用户隐私,本文引入了区块链技术,最终开发了一种将区块链与GBDT-DGAN算法融合的金融反欺诈模型。实验验证表明,该模型的准确率达到了93.82%,与卷积神经网络等基线算法相比,显着提高了至少5.76%。召回率和 F1 值分别为 89.5% 和 81.66%。此外,该模型还具有卓越的网络数据传输安全性,丢包率保持在7%以下。因此,所提出的模型在金融欺诈检测精度方面显着优于传统方法,并保证了良好的网络数据传输安全性,为金融领域欺诈检测提供了高效、安全的解决方案。
更新日期:2024-02-02
down
wechat
bug