W EB：一种基于网络嵌入的互联网借贷欺诈预测方法

doi:10.11959/j.issn.2096-0271.2019052

大数据 ›› 2019, Vol. 5 ›› Issue (6): 85-100.doi: 10.11959/j.issn.2096-0271.2019052

W EB：一种基于网络嵌入的互联网借贷欺诈预测方法

王成^1,^2,³(),舒鹏飞^1,²

¹ 同济大学计算机科学与技术系，上海 201804
² 嵌入式系统与服务计算教育部重点实验室，上海 201804
³ 上海智能科学与技术研究院，上海 200092

出版日期:2019-11-15 发布日期:2020-01-10
作者简介:王成（1980- ），男，同济大学计算机科学与技术系教授，主要研究方向为网络服务优化与安全、互联网金融反欺诈和网络空间异常事件检测研究|舒鹏飞（1994- ），男，同济大学计算机科学与技术系硕士生，主要研究方向为数据挖掘、机器学习和欺诈检测
基金资助:
国家自然科学基金资助项目(6197228);国家自然科学基金资助项目(61571331);工业和信息化部工业互联网创新发展工程项目([2018]282);霍英东教育基金会高等院校青年教师基金(151066);中央高校基本科研业务费专项资金资助项目(kx0137020181527);上海市青年拔尖人才开发计划

WEB:a fraud prediction method of Internet lending using network embedding

Cheng WANG^1,^2,³(),Pengfei SHU^1,²

¹ Department of Computer Science,Tongji University,Shanghai 201804,China
² The Key Lab of Embedded System and Service Computing Ministry of Education,Shanghai 201804,China
³ Shanghai Institute of Intelligent Science and Technology,Shanghai 200092,China

Online:2019-11-15 Published:2020-01-10
Supported by:
The National Natural Science Foundation of China(6197228);The National Natural Science Foundation of China(61571331);The Major Project of Ministry of Industry and Information Technology of China([2018]282);Fok Ying-Tong Education Foundation for Young Teachers in the Higher Education Institutions of China(151066);The Fundamental Research Funds for Central Universities(kx0137020181527);Municipal Human Resources Development Program for Outstanding Young Talents in Shanghai

摘要/Abstract

摘要：

基于关联图谱的互联网借贷欺诈预测方法限制了特征的挖掘效率、挖掘深度以及特征的可复用性、可表达性。针对此问题，引入网络嵌入技术，在保留欺诈特征的前提下，将网络中的节点嵌入低维的向量空间，利用向量对网络中的结构和语义信息进行表达；提出了基于周期性时间窗口的网络更新方法和决策批处理方法来提升网络嵌入在精准性和实时性方面的性能。实验表明，网络嵌入技术能够自动有效地学习网络中隐含的关联关系与特征；通过将传统方法和网络嵌入方法相结合，欺诈预测性能得到了显著提升。

关键词: 关联图谱, 互联网借贷, 网络嵌入, 反欺诈, 风险防控

Abstract:

Internet lending fraud prediction method based on association graph limits the mining efficiency and depth of features,as well as the reusability and expressibility of features.To solve this problem,the network embedding technology was introduced,and the structure and semantic information in the network by using the vector was expressed.The network update method based on periodic time window and decision batch method were proposed to improve the performance of network embedding in the two business requirements of accuracy and real-time.The experiment shows that the network embedding technology can automatically and effectively learn the implicit relationship and characteristics of the network.By combining the traditional method and the network embedding method,the fraud prediction performance has been significantly improved.

Key words: association graph, internet lending, network embedding, anti-fraud, risk management

中图分类号:

TP181

王成, 舒鹏飞. W EB：一种基于网络嵌入的互联网借贷欺诈预测方法[J]. 大数据, 2019, 5(6): 85-100.

Cheng WANG, Pengfei SHU. WEB:a fraud prediction method of Internet lending using network embedding[J]. Big Data Research, 2019, 5(6): 85-100.

图/表 10

图1

表1

图2

表2

图3

图4

图5

表3

图6

图7

参考文献 26

[1]	SONG M , WANG J . An objective measurement of information value usingapplication traces in infomediary:A case study of credit reporting system in China[C]// The 20th International Conference on Information Quality(ICIQ2015),July 24,2015,Cambridge,USA.[S.l.:s.n]. , 2015.
[2]	XIE S , YU P S . Next generation trustworthy fraud detection[C]// The 4th IEEE International Conference on Collaboration and Internet Computing,October 18-20,2018,Pennsylvania,USA. Piscataway:IEEE Press, 2018: 279-282.
[3]	XUAN S Y , LIU G J , LI Z C . Refined weighted random forest and its application to credit card fraud detection[C]// The 7th International Conference on Computational Data and Social Networks,December 18-20,2018,Shanghai,China. Heidelberg:Springer, 2018: 343-355.
[4]	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.
[5]	HOOI B , SHIN K , SONG H A ,et al. Graph-based fraud detection in the face of camouflage[J]. ACM Transactions on Knowledge Discovery from Data, 2017,11(4): 1-26.
[6]	CAO B , MAO M , VIIDU S ,et al. Hitfraud:a broad learning approachfor collective fraud detection in heterogeneous information networks[C]// The 2017 IEEE International Conference on Data Mining,November 18-21,2017,New Orleans,USA. Piscataway:IEEE Press, 2017: 769-774.
[7]	MAO R , LI Z , FU J . Fraud transaction recognition:a money flow network approach[C]// The 24th ACM International Conference on Informationand Knowledge Management,October 18-23,2015,Melbourne,Australia. New York:ACM Press, 2015: 1871-1874.
[8]	MCGLOHON M , BAY S , ANDERLE M G ,et al. SNARE:a link analytic system for graph labelingand risk detection[C]// The 15th ACM SIGKDD International Conferenceon Knowledge Discovery and Data Mining,June 28-July 1,2009,Paris,France. New York:ACM Press, 2009: 1265-1274.
[9]	CUI P , WANG X , PEI J ,et al. A survey on network embedding[J]. IEEE Transaction on Knowledge Data Engineering, 2019,31(5): 833-852.
[10]	VLASSELAER V V , BRAVO C , CAELEN O ,et al. APATE:a novel approach for automated credit card transaction fraud detection using network-based extensions[J]. Decision Support Systems, 2015,75: 38-48.
[11]	LIANG C , LIU Z Q , LIU B ,et al. Who stole the postage? Fraud detection in return-freight insurance claims[C]// The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,August 19-23,2018,London,UK. New York:ACM Press, 2018.
[12]	LI Y , SUN Y H , CONTRACTOR N . Graph mining assisted semi-supervised learning for fraudulent cash-out detection[C]// The 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining,July 31-August 3,2017,Sydney,Australia. New York:ACM Press, 2017: 546-553.
[13]	LEBICHOT B , BRAUN F , CAELEN O ,et al. A graph-based,semi-supervised,credit card fraud detection system[C]// International Workshop on Complex Networks and their Applications,November 29 - December 1,2017,Lyon,France. Heidelberg:Springer, 2017.
[14]	LU P , LIN R H . Fraud phone calls analysis based on label propagation community detection algorithm[C]// 2018 IEEE World Congress on Services,July 2-7,2018,San Francisco,USA. Piscataway:IEEE Press, 2018: 23-24.
[15]	GANGOPADHYAY A , CHEN S . Health care fraud detection with community detection algorithms[C]// 2016 IEEE International Conference on Smart Computing,May 18-20,2016,St.Louis,USA. Piscataway:IEEE Press, 2016.
[16]	KIM J , KIM H J , KIM H . Fraud detection for job placement using hierarchical clustersbased deep neural networks[J]. Applied Intelligence, 2019,49(8): 2842-2861.
[17]	HAMILTON W L , YING R , LESKOVEC J . Representation learning on graphs:methods and applications[J]. IEEE Data Engineering Bulletin, 2017: 52-74.
[18]	OU M , CUI P , PEI J ,et al. Asymmetric transitivity preserving graph embedding[C]// The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,August 13-17,2016,San Francisco,USA. New York:ACM Press, 2016: 672-681.
[19]	WANG X , CUI P , WANG J ,et al. Community preserving network embedding[C]// The 31st AAAI Conference on Artificial Intelligence,February 4–9,2017,San Francisco,USA. Palo Alto:AAAI Press, 2017: 203-209.
[20]	MIKOLOV T , CHEN K , CORRADO G ,et al. Efficient estimation of word representationsin vector space[C]// The 1st International Conference on Learning Representations,May 2-4,2013,Scottsdale,Arizona.[S.l.:s.n. ], 2013.
[21]	PEROZZI B , AL-RFOU R , SKIENA S . Deepwalk:online learning of social representations[C]// The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,August 24-27,2014,New York,USA. New York:ACM Press, 2014: 701-710.
[22]	TANG L , LIU H . Uncovering crossdimension group structures in multidimensional networks[C]// SDM workshop on Analysis of Dynamic,Networks International AAAI Conference on Connecting Corresponding Identities Across Communities,May 2,2009,Calgary,Cananda. Palo Alto:AAAI Press, 2009.
[23]	TANG J , QU M , WANG M Z ,et al. LINE:large-scale information network embedding[C]// The 24th International Conference on World Wide Web,May 18-22,2015,Florence,Italy.[S.l.:s.n. ], 2015: 1067-1077.
[24]	WANG D X , CUI P , ZHU W W . Structural deep network embedding[C]// The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,August 13-17,2016,San Francisco,USA. New York:ACM Press, 2016: 1225-1234.
[25]	CAO S S , LU W , XU Q K . Deep neural networks for learning graph representations[C]// The 30th AAAI Conference on Artificial Intelligence,February 12-17,2016,Phoenix,Arizona. Palo Alto:AAAI Press, 2016: 1145-1152.
[26]	GROVER A , LESKOVEC J . Node2vec:scalable feature learning for networks[C]// The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 13-17, 2016, San Francisco. USA. New York: ACM Press, 2016: 855-864.

编号	时间	姓名	公司	住址
x₁	t₁	Bob	C1	Addr1
x₂	t₂	Jack	C1	Addr2
x₃	t₃	Sandy	C2	Addr3
x₄	t₄	Bob	C2	Addr1
x₅	t₅	Tim	C3	Addr2

编号	时间	姓名	公司	住址
x₆	t₆	Lucy	C3	Addr1
x₇	t₇	Sandy	C2	Addr3

检测方法	精确率	召回率	打扰率	KS值
网络嵌入	0.638 2	0.434 2	0.053 9	0.380 2
传统网络分析	0.614 3	0.495 4	0.068	0.426 9
两者结合	0.623 6	0.570 5	0.086 1	0.484 4

W EB：一种基于网络嵌入的互联网借贷欺诈预测方法

WEB:a fraud prediction method of Internet lending using network embedding

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 26

相关文章 4

Metrics

推荐阅读 0

[1]	陈强, 代仕娅. 基于金融知识图谱的会计欺诈风险识别方法[J]. 大数据, 2021, 7(3): 116-129.
[2]	金磐石,万光明,沈丽忠. 基于知识图谱的小微企业贷款申请反欺诈方案[J]. 大数据, 2019, 5(4): 100-112.
[3]	胡鹏飞. 金融科技在互联网金融行业性风险防范领域的应用[J]. 大数据, 2018, 4(1): 117-123.
[4]	刘阳, 白卉, 伯晓晨. 基因表达谱大数据在抗癌药物研发中的应用[J]. 大数据, 2016, 2(5): 22-31.