金融交易数据驱动的图谱网络智能化欺诈侦测

doi:10.3969/j.issn.0255-8297.2020.05.005

应用科学学报 ›› 2020, Vol. 38 ›› Issue (5): 713-723.doi: 10.3969/j.issn.0255-8297.2020.05.005

• 智能计算新技术 • 上一篇

金融交易数据驱动的图谱网络智能化欺诈侦测

孙权^1,2, 汤韬^1,2, 郑建宾¹, 潘婧^1,2, 赵金涛²

1. 复旦大学计算机科学技术学院, 上海 200433;
2. 中国银联电子支付研究院, 上海 201201

收稿日期:2020-05-11 发布日期:2020-10-14
通信作者: 汤韬,博士,研究员,研究方向为数据挖掘风险防控.E-mail:tangtao2@unionpay.com E-mail:tangtao2@unionpay.com
基金资助:
国家发改委项目（No.2018AAA0100700，No.2016YFB1001003）；上海市学科带头人项目（No.19XD1433700）资助

Financial Transaction Data Based Intelligent Fraud Graph Network Detection

SUN Quan^1,2, TANG Tao^1,2, ZHENG Jianbin¹, PAN Jing^1,2, ZHAO Jintao²

1. School of Computer Science, Fudan University, Shanghai 200433, China;
2. China UnionPay Research Institute of Electronic Payment, Shanghai 201201, China

Received:2020-05-11 Published:2020-10-14

摘要/Abstract

摘要： 针对当前金融领域营销场景中商户与持卡人团伙化的交易欺诈行为难以侦测、挖掘的不足的问题，该文基于交易流水数据，构建了持卡人-商户的智能化交易图谱网络，建立了图拓扑特征体系框架和机器学习的异常检测算法，对当前营销欺诈团伙化网络进行了智能化侦测.基于相关样本数据提出的模型效果比传统模型具有较大提升，对欺诈团伙证据链挖掘和画像分析提供了有效方法.

关键词: 图计算, 可解释性, 人工智能, 数据融合

Abstract: Nowadays, fraud risk has been changing from individual fraud to group fraud, leading to jump rise of financial payment. How to identify and detect the group fraud is becoming a challenge in risk management. To deal with the group fraud transaction, this article builds a transaction graph network based on financial transaction data, and founds a topological graph feature extraction framework and anomaly detection model. Experiment on sample data shows that the proposed model obtains better results comparing with the previous individual feature analysis models, and gives reasonable explanation and evidence for the fraud detection.

Key words: graph computing, explainable, artificial intelligence, data aggregation

中图分类号:

TP181

孙权, 汤韬, 郑建宾, 潘婧, 赵金涛. 金融交易数据驱动的图谱网络智能化欺诈侦测[J]. 应用科学学报, 2020, 38(5): 713-723.

SUN Quan, TANG Tao, ZHENG Jianbin, PAN Jing, ZHAO Jintao. Financial Transaction Data Based Intelligent Fraud Graph Network Detection[J]. Journal of Applied Sciences, 2020, 38(5): 713-723.

参考文献

[1] 赵军, 张建肖. 网络黑灰产治理须多管齐下[J]. 中国信息安全, 2017(12):73-74. Zhao J, Zhang J X. The management of network black ash production should be multi pronged[J]. China Information Security, 2017(12):73-74. (in Chinese)
[2] 赵宇飞, 邓中豪. 谨防信用卡套现"里应外合"[J]. 今日南国, 2014(4):11. Zhao Y F, Deng Z H. Guard against "internal and external cooperation" of credit card fraud[J]. The South of China Today, 2014(4):11. (in Chinese)
[3] 尚丹. 2017年国家网络安全宣传周新亮点[J]. 信息系统工程, 2017(10):8-10. Shang D. New highlights of national cyber security week in 2017[J]. China CIO News, 2017(10):8-10. (in Chinese)
[4] 戴先任. 别让网络黑灰产业恶化网络生态[J]. 青年记者, 2017(22):63. Dai X R. Don't let the network black gray industry worsen the network ecology[J]. Youth Journalist, 2017(22):63. (in Chinese)
[5] 叶菁. 大数据与黑灰产规模齐飞, 保护隐私需三管齐下[J]. 中国报业, 2018, 456(23):107. Ye Q. Big data and black ash production scale fly together, privacy protection needs three pronged approach[J]. China Newspaper Industry, 2018, 456(23):107. (in Chinese)
[6] 高增安. 基于交易的可疑洗钱行为模式与反洗钱对策研究[D]. 成都:西南交通大学, 2007.
[7] 徐程佳. 基于指纹识别的银行卡交易欺诈侦测系统的优化方案的研究[D]. 上海:华东师范大学, 2013.
[8] Sánchez D, Vila M A, Cerda L, et al. Association rules applied to credit card fraud detection[J]. Expert Systems with Applications, 2009, 36(2):3630-3640.
[9] Weng H, Li Z, Ji S, et al. Online e-commerce fraud:a large-scale detection and analysis[C]//2018 IEEE 34th International Conference on Data Engineering (ICDE). IEEE, 2018:1435-1440.
[10] Bekirev A S, Klimov V V, Kuzin M V, et al. Payment card fraud detection using neural network committee and clustering[J]. Optical Memory and Neural Networks, 2015, 24(3):193-200.
[11] Šubelj L, Furlan Š, Bajec M. An expert system for detecting automobile insurance fraud using social network analysis[J]. Expert Systems with Applications, 2011, 38(1):1039-1052.
[12] Hilas C S, Mastorocostas P A, Rekanos I T. Clustering of telecommunications user profiles for fraud detection and security enhancement in large corporate networks:a case study[J]. Applied Mathematics & Information Sciences, 2015, 9(4):1709.
[13] Bahnsen A C, Stojanovic A, Aouada D, et al. Improving credit card fraud detection with calibrated probabilities[J]. SIAM International Conference on Data Mining, 2014:677-685.
[14] 孙万龙. 基于GBDT的社区问题标签推荐技术研究[D]. 哈尔滨:哈尔滨工业大学, 2015.
[15] 蔡文学, 罗永豪, 张冠湘, 等. 基于GBDT与Logistic回归融合的个人信贷风险评估模型及实证分析[J]. 管理现代化, 2017(2):3-4. Cai W X, Luo Y H, Zhang G X. Personal credit risk assessment model and empirical analysis based on gbdt and logistic regression[J]. Modernization of Management, 2017(2):3-4. (in Chinese)

金融交易数据驱动的图谱网络智能化欺诈侦测

Financial Transaction Data Based Intelligent Fraud Graph Network Detection

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	方俊杰, 雷凯. 面向边缘人工智能计算的区块链技术综述[J]. 应用科学学报, 2020, 38(1): 1-21.
[2]	张磊, 陆宇平, 殷明. 多传感器融合四旋翼协同控制算法及其实现[J]. 应用科学学报, 2016, 34(2): 190-202.
[3]	王伟, 张金艺, 张洪辉, 蔡春艳, 李建宇. 异质双9轴MEMS惯性传感器数据互补-加权迭代融合算法[J]. 应用科学学报, 2015, 33(5): 491-501.
[4]	JIN Xing1, YU Da-hai1,2, HAN Jian-feng3, LI Hui-hui1, HAN Jun-wei1. 采用多方向插值融合的快速铁路货运图像修复[J]. 应用科学学报, 2014, 32(2): 191-198.
[5]	任亚飞，柯熙政. 多尺度小波分解融合在微机电陀螺数据处理中的应用[J]. 应用科学学报, 2010, 28(4): 394-398.
[6]	刘以安, 陈松灿, 张明俊, 马秀芳. 缓冲算子及数据融合技术在目标跟踪中的应用[J]. 应用科学学报, 2006, 24(2): 154-158.
[7]	金施群, 丁晓牧, 费业泰, 余晓芬, 陈晓怀. 大轴直径的高精度多滚轮法测量[J]. 应用科学学报, 2005, 23(2): 200-203.
[8]	刘永刚, 陈光, 孙瑜, 孙国雄. 耦合相图计算的凝固过程显微偏析形成数值模拟[J]. 应用科学学报, 2004, 22(4): 523-527.
[9]	张尤赛, 刘维亭. 雷达网数据融合的自组织模糊神经网络模型[J]. 应用科学学报, 2001, 19(2): 149-152.
[10]	滕召胜, 郁文贤. 数据融合技术在储粮水分自动测试系统中的应用[J]. 应用科学学报, 1999, 17(4): 469-472.