《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (8): 2634-2642.DOI: 10.11772/j.issn.1001-9081.2023081153
杨帆1, 邹窈2,3, 朱明志2,3, 马振伟1, 程大伟2,3(), 蒋昌俊2,3
收稿日期:
2023-08-28
修回日期:
2023-09-20
接受日期:
2023-10-08
发布日期:
2024-08-22
出版日期:
2024-08-10
通讯作者:
程大伟
作者简介:
杨帆(1982—),男,重庆人,高级工程师,硕士,主要研究方向:数据挖掘、金融风险防控、金融大数据基金资助:
Fan YANG1, Yao ZOU2,3, Mingzhi ZHU2,3, Zhenwei MA1, Dawei CHENG2,3(), Changjun JIANG2,3
Received:
2023-08-28
Revised:
2023-09-20
Accepted:
2023-10-08
Online:
2024-08-22
Published:
2024-08-10
Contact:
Dawei CHENG
About author:
YANG Fan, born in 1982, M. S., senior engineer. His research interests include data mining, financial risk prevention and control, financial big data.Supported by:
摘要:
针对现有模型无法精准识别复杂多变的团伙诈骗模式的问题,提出一种新型实用的基于复杂交易图谱的信用卡反欺诈检测模型。首先,利用用户原始的交易信息构造关联交易图谱;随后,使用图自注意力Transformer神经网络模块直接从交易网络中挖掘团伙欺诈特征,无需构建繁冗的特征工程;最后,通过欺诈预测网络联合优化图谱中的拓扑模式和时序交易模式,实现对欺诈交易的高精度检测。在信用卡交易数据上的反欺诈实验结果表明,所提模型在全部评价指标上均优于7个对比的基线模型:在交易欺诈检测任务中,平均精度(AP)比基准图注意力神经网络(GAT)提升了20%,ROC曲线下方面积(AUC)平均提升了2.7%,验证了所提模型在信用卡欺诈交易检测中的有效性。
中图分类号:
杨帆, 邹窈, 朱明志, 马振伟, 程大伟, 蒋昌俊. 基于图注意力Transformer神经网络的信用卡欺诈检测模型[J]. 计算机应用, 2024, 44(8): 2634-2642.
Fan YANG, Yao ZOU, Mingzhi ZHU, Zhenwei MA, Dawei CHENG, Changjun JIANG. Credit card fraud detection model based on graph attention Transformation neural network[J]. Journal of Computer Applications, 2024, 44(8): 2634-2642.
模型 | AP | AUC | 特征数 | ||||
---|---|---|---|---|---|---|---|
7月 | 8月 | 9月 | 7月 | 8月 | 9月 | ||
SVM | 0.120 3 | 0.158 2 | 0.117 2 | 0.659 9 | 0.646 7 | 0.684 2 | 90 |
RF | 0.154 7 | 0.165 8 | 0.125 8 | 0.732 4 | 0.684 1 | 0.689 2 | 90 |
XGBoost | 0.207 4 | 0.209 9 | 0.257 0 | 0.889 4 | 0.821 6 | 0.867 1 | 90 |
DNN | 0.251 2 | 0.348 3 | 0.250 9 | 0.894 8 | 0.911 3 | 0.891 9 | 90 |
STAN | 0.302 1 | 0.396 3 | 0.331 5 | 0.904 1 | 0.905 1 | 0.921 3 | 12 |
GCN | 0.347 3 | 0.429 3 | 0.327 5 | 0.900 6 | 0.898 1 | 0.887 0 | 12 |
GAT | 0.388 5 | 0.427 8 | 0.398 5 | 0.924 1 | 0.919 3 | 0.916 9 | 12 |
TGTN | 0.463 7* | 0.526 1* | 0.473 2* | 0.947 1* | 0.944 6* | 0.942 2* | 12 |
表1 不同模型在信用卡欺诈交易检测任务中的精度对比
Tab. 1 Accuracy comparison of different methods in credit card fraud detection task
模型 | AP | AUC | 特征数 | ||||
---|---|---|---|---|---|---|---|
7月 | 8月 | 9月 | 7月 | 8月 | 9月 | ||
SVM | 0.120 3 | 0.158 2 | 0.117 2 | 0.659 9 | 0.646 7 | 0.684 2 | 90 |
RF | 0.154 7 | 0.165 8 | 0.125 8 | 0.732 4 | 0.684 1 | 0.689 2 | 90 |
XGBoost | 0.207 4 | 0.209 9 | 0.257 0 | 0.889 4 | 0.821 6 | 0.867 1 | 90 |
DNN | 0.251 2 | 0.348 3 | 0.250 9 | 0.894 8 | 0.911 3 | 0.891 9 | 90 |
STAN | 0.302 1 | 0.396 3 | 0.331 5 | 0.904 1 | 0.905 1 | 0.921 3 | 12 |
GCN | 0.347 3 | 0.429 3 | 0.327 5 | 0.900 6 | 0.898 1 | 0.887 0 | 12 |
GAT | 0.388 5 | 0.427 8 | 0.398 5 | 0.924 1 | 0.919 3 | 0.916 9 | 12 |
TGTN | 0.463 7* | 0.526 1* | 0.473 2* | 0.947 1* | 0.944 6* | 0.942 2* | 12 |
1 | 王密. 2020年中国信用卡在用发卡量、授信额度、透支余额及不良率分析[EB/OL]. (2021-11-17) [2022-03-18]. . |
WANG M. Analysis of the issuance volume, credit limit, overdraft balance and non-performing rate of credit cards in China in 2020[EB/OL]. (2021-11-17) [2022-03-18]. . | |
2 | Federal Trade Commission. Consumer sentinel network data book 2021[EB/OL]. (2022-02-22) [2022-03-22]. . |
3 | CARCILLO F, Y-A BORGNE, CAELEN O, et al. Combining unsupervised and supervised learning in credit card fraud detection[J]. Information Sciences, 2019, 557: 317-331. |
4 | POZZOLO A D, BORACCHI G, CAELEN O, et al. Credit card fraud detection: a realistic modeling and a novel learning strategy[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(8): 3784-3797. |
5 | MILO T, NOVGORODOV S, TAN W-C. Rudolf: interactive rule refinement system for fraud detection [J]. Proceedings of the VLDB Endowment, 2016, 9(13): 1465-1468. |
6 | CARNEIRO N, FIGUEIRA G, COSTA M. A data mining based system for credit-card fraud detection in e-tail[J]. Decision Support Systems, 2017, 95: 91-101. |
7 | BHATTACHARYYA S, JHA S, THARAKUNNEL K, et al. Data mining for credit card fraud: a comparative study[J]. Decision Support Systems, 2011, 50(3): 602-613. |
8 | KUMAR M S, SOUNDARYA V, KAVITHA S, et al. Credit card fraud detection using random forest algorithm[C]// Proceedings of the 2019 3rd International Conference on Computing and Communications Technologies. Piscataway: IEEE, 2019: 149-153. |
9 | DORRONSORO J R, GINEL F, SGNCHEZ C, et al. Neural fraud detection in credit card operations[J]. IEEE Transactions on Neural Networks, 1997, 8(4): 827-834. |
10 | CHAUDHARY K, YADAV J, MALLICK B. A review of fraud detection techniques: credit card[J]. International Journal of Computer Applications, 2012, 45(1): 39-44. |
11 | LeCUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444. |
12 | FU K, CHENG D, TU Y, et al. Credit card fraud detection using convolutional neural networks[C]// Proceedings of the 23rd International Conference on Neural Information Processing. Cham: Springer, 2016: 483-490. |
13 | CHENG D, XIANG S, SHANG C, et al. Spatio-temporal attention-based neural network for credit card fraud detection[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(1): 362-369. |
14 | CHENG D, WANG X, ZHANG Y, et al. Graph neural network for fraud detection via spatial-temporal attention[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(8): 3800-3813. |
15 | 程大伟,牛志彬,刘新海,等.复杂担保网络中传染路径的风险评估[J].中国科学:信息科学,2021,51(7):1068-1083. |
CHENG D W, NIU Z B, LIU X H, et al. Risk assessment for contagion path in complex loan network[J]. SCIENTIA SINICA Informationis, 2021,51(7):1068-1083. | |
16 | WANG D, LIN J, CUI P, et al. A semi-supervised graph attentive network for financial fraud detection[C]// Proceedings of the 2019 IEEE International Conference on Data Mining. Piscataway: IEEE, 2019: 598-607. |
17 | DENG L, YU D. Deep Learning: Methods and Applications[M]. Hanover, MA: Now, 2014. |
18 | SCARSELLI F, GORI M, TSOI A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2009, 20(1): 61-80. |
19 | YANG H. AliGraph: a comprehensive graph neural network platform[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2019: 3165-3166. |
20 | CAO D, WANG Y, DUAN J, et al. Spectral temporal graph neural network for multivariate time-series forecasting[C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2020: 17766-17778. |
21 | MARCHEGGIANI D, BASTINGS J, TITOV I. Exploiting semantics in neural machine translation with graph convolutional networks[C]// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: ACL, 2018: 486-492. |
22 | LIANG X, HU Z, ZHANG H, et al. Symbolic graph reasoning meets convolutions[C]// Proceedings of the 2018 32nd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2018: 1858-1868. |
23 | ATA S K, FANG Y, WU M, et al. Disease gene classification with metagraph representations[J]. Methods in Molecular Biology, 2018, 1807:211-224. |
24 | ZHANG S, TONG H, XU J, et al. Graph convolutional networks: a comprehensive review[J]. Computational Social Networks, 2019, 6: Article No. 11. |
25 | HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc, 2017: 1025-1035. |
26 | VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks[EB/OL]. (2017-10-30) [2023-09-19]. . |
27 | YANG T, HU L, SHI C, et al. HGAT: heterogeneous graph attention networks for semi-supervised short text classification[J]. ACM Transactions on Information Systems, 2021, 39(3): Article No. 32. |
28 | ZHANG C, SSONG D, HUANG C, et al. Heterogeneous graph neural network[C]// Proceedings of the 2019 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2019: 793-803. |
29 | FU X, ZHANG J, MENG Z, et al. MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding[C]// Proceedings of the Web Conference 2020. New York: ACM, 2020: 2331-2341. |
30 | YUN S, JEONG M, YOO S, et al. Graph transformer networks: learning meta-path graphs to improve GNNs[J]. Neural Networks, 2022, 153:104-119. |
31 | FAWCETT T, PROVOST F. Adaptive fraud detection[J]. Data Mining and Knowledge Discovery, 1997, 1: 291-316. |
32 | MASUDA B. Credit card fraud prevention: a successful retail strategy[J]. Crime Prevention Studies, 1993, 1: 121-134. |
33 | HUSEJINOVIĆ A. Credit card fraud detection using naive Bayesian and C4.5 decision tree classifiers[J]. Periodicals of Engineering and Natural Sciences, 2020, 8(1): 1-5. |
34 | FIORE U, DE SANTIS A, PERLA F, et al. Using generative adversarial networks for improving classification effectiveness in credit card fraud detection[J]. Information Sciences, 2019, 479: 448-455. |
35 | CHEN J I-Z, LAI K-L. Deep convolution neural network model for credit-card fraud detection and alert[J]. Journal of Artificial Intelligence and Capsule Networks, 2021, 3(2): 101-112. |
36 | ALGHOFAILI Y, ALBATTAH A, RASSAM M A. A financial fraud detection model based on LSTM deep learning technique[J]. Journal of Applied Security Research, 2020, 15(4): 498-516. |
37 | 莫赞,盖彦蓉,樊冠龙.基于GAN-AdaBoost-DT不平衡分类算法的信用卡欺诈分类[J].计算机应用, 2019, 39(2): 618-622. |
MO Z, GAI Y R, FAN G L. Credit card fraud classification based on GAN-AdaBoost-DT imbalance classification algorithm[J]. Journal of Computer Applications, 2019, 39(2): 618-622. | |
38 | 琚春华,陈冠宇,鲍福光.基于kNN-Smote-LSTM的消费金融风险检测模型:以信用卡欺诈检测为例[J].系统科学与数学,2021, 41(2): 481-498. |
JU C H, CHEN G Y, BAO F G. KNN-Smote-LSTM based consumer financial risk detection model: a case credit card fraud detection[J]. Journal of Systems Science and Mathematical Sciences, 2021, 41(2): 481-498. | |
39 | LEBICHOT B, BRAUN F, CAELEN O, et al. A graph-based, semi-supervised, credit card fraud detection system[C]// Proceedings of the 5th International Workshop on Complex Networks and their Applications. Cham: Springer, 2016: 721-733. |
40 | XIE Y, LIU G, YAN C, et al. Time-aware attention-based gated network for credit card fraud detection by extracting transactional behaviors[J]. IEEE Transactions on Computational Social Systems, 2023, 10(3): 1004-1016. |
41 | ZHANG G, LI Z, HUANG J, et al. eFraudCom: an e-commerce fraud detection system via competitive graph neural networks[J]. ACM Transactions on Information Systems, 2022, 40(3): Article No. 47. |
42 | SINGH G, GUPTA R, RASTOGI A, et al. A machine learning approach for detection of fraud based on SVM[J]. International Journal of Scientific Engineering and Technology, 2012, 1(3): 194-198. |
43 | MENG C, ZHOU L, LIU B. A case study in credit fraud detection with SMOTE and XGBoost[J]. Journal of Physics: Conference Series, 2020,1601: 052016. |
44 | ASHA R B, SURESH KUMAR K R. Credit card fraud detection using artificial neural network[J]. Global Transitions Proceedings, 2021, 2(1): 35-41. |
[1] | 唐廷杰, 黄佳进, 秦进. 基于图辅助学习的会话推荐[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2711-2718. |
[2] | 杨航, 李汪根, 张根生, 王志格, 开新. 基于图神经网络的多层信息交互融合算法用于会话推荐[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2719-2725. |
[3] | 杜郁, 朱焱. 构建预训练动态图神经网络预测学术合作行为消失[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2726-2731. |
[4] | 吴相岚, 肖洋, 刘梦莹, 刘明铭. 基于语义增强模式链接的Text-to-SQL模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2689-2695. |
[5] | 杨兴耀, 陈羽, 于炯, 张祖莲, 陈嘉颖, 王东晓. 结合自我特征和对比学习的推荐模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2704-2710. |
[6] | 杨莹, 郝晓燕, 于丹, 马垚, 陈永乐. 面向图神经网络模型提取攻击的图数据生成方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2483-2492. |
[7] | 毛典辉, 李学博, 刘峻岭, 张登辉, 颜文婧. 基于并行异构图和序列注意力机制的中文实体关系抽取模型[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2018-2025. |
[8] | 林欣蕊, 王晓菲, 朱焱. 基于局部扩展社区发现的学术异常引用群体检测[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1855-1861. |
[9] | 姚迅, 秦忠正, 杨捷. 生成式标签对抗的文本分类模型[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1781-1785. |
[10] | 汪炅, 唐韬韬, 贾彩燕. 无负采样的正样本增强图对比学习推荐方法PAGCL[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1485-1492. |
[11] | 郭洁, 林佳瑜, 梁祖红, 罗孝波, 孙海涛. 基于知识感知和跨层次对比学习的推荐方法[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1121-1127. |
[12] | 徐大鹏, 侯新民. 基于网络结构设计的图神经网络特征选择方法[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 663-670. |
[13] | 王楷天, 叶青, 程春雷. 基于异构图表示的中医电子病历分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(2): 411-417. |
[14] | 胡能兵, 蔡彪, 李旭, 曹旦华. 基于图池化对比学习的图分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3327-3334. |
[15] | 花晓雨, 李冬芬, 付优, 毕可骏, 应时, 王瑞锦. 结合层次图神经网络与长短期记忆的产业链风险评估预警模型[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3223-3231. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||