图异常检测在金融反欺诈中的应用研究进展

doi:10.3778/j.issn.1002-8331.2203-0233

摘要/Abstract

摘要： 随着数字金融的快速发展，欺诈呈现出智能化、产业化以及强隐蔽性等新特点，传统的专家规则和机器学习方法局限性日益显现。图异常检测技术对关联信息具有强大的处理能力，为金融反欺诈提供了新的思路。简要介绍了图异常检测的发展历程和优势；着重从个体反欺诈和群体反欺诈两个视角，将图异常检测划分为基于特征、基于邻近性、基于图表示学习和基于社区划分的个体欺诈检测，以及基于稠密子图、基于稠密子张量和基于深层网络结构的团伙欺诈检测，并对每类技术的基本思想、优缺点、研究进展和典型应用进行对比分析；同时归纳总结了常用的数据集和评价指标，并给出图异常检测在金融反欺诈中的发展前景和研究方向。

关键词: 金融反欺诈, 图异常检测, 数字化金融服务

Abstract: With the rapid development of digital finance, fraud presents new characteristics such as intellectualization, industrialization and strong concealment. And the limitations of traditional expert rules and machine learning methods are increa-
singly apparent. Graph anomaly detection technology has a strong ability to deal with associated information, which provides new idea for financial anti-fraud. Firstly, the development and advantages of graph anomaly detection are briefly introduced. Secondly, from the perspectives of individual anti-fraud and group anti-fraud, graph anomaly detection technology is divided into individual fraud detections based on feature, proximity, graph representation learning or community division, and gang fraud detections based on dense subgraph, dense subtensor or deep network structure. The basic idea, advantages, disadvantages, research progress and typical applications of each anomaly detection technology are analyzed and compared. Finally, the common test data sets and evaluation criteria are summarized, and the development prospect and research direction of graph anomaly detection technology in financial anti-fraud are given.

Key words: financial anti-fraud, graph anomaly detections, digital financial service

刘华玲, 刘雅欣, 许珺怡, 陈尚辉, 乔梁. 图异常检测在金融反欺诈中的应用研究进展[J]. 计算机工程与应用, 2022, 58(22): 41-53.

LIU Hualing, LIU Yaxin, XU Junyi, CHEN Shanghui, QIAO Liang. Research Progress in Application of Graph Anomaly Detection in Financial Anti-Fraud[J]. Computer Engineering and Applications, 2022, 58(22): 41-53.

参考文献

[1] 刘瑜晓，杨华.以金融科技赋能，构建信用卡智能风控体系[J].中国信用卡，2021（5）：24-29.
LIU Y X，YANG H.Build credit card intelligent risk control system with financial technology empowerment[J].China Credit Card，2021（5）：24-29.
[2] 王乾.智能风控在商业银行普惠金融中的应用[J].银行家，2021（5）：122-124.
WANG Q.Application of intelligent risk control of inclusive finance in commercial banks[J].The Chinese Banker，2021（5）：122-124.
[3] 刘殿中.动态金融复杂数据的欺诈检测[D].青岛：青岛大学，2020.
LIU D Z，Fraud detection for dynamic financial complex data[D].Qingdao：Qingdao University，2020.
[4] HOOGS B，KIEHL T，LACOMB C，et al.A genetic algorithm approach to detecting temporal patterns indicative of financial statement fraud[J].Intelligent Systems in Accounting，Finance & Management，2007，15（1/2）：41-56.
[5] YUE D M，WU X D，WANG Y F，et al.A review of data mining-based financial fraud detection research[C]//2007 International Conference on Wireless Communications，Networking and Mobile Computing，Shanghai，Sep 21-25，2007.Piscataway：IEEE，2007：5519-5522.
[6] VELAMPALLI S，EBERLE W.Novel graph based anomaly detection using background knowledge[C]//30th International Flairs Conference，Florida，May 22-24，2017.Menlo Park：AAAI，2017：538-543.
[7] HAWKINS D M.Identification of outliers[M].London：Chapman and Hall，1980：100-110.
[8] NOBLE C C，COOK D J.Graph-based anomaly detection[C]//9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，Washington，Aug 24-27，2003.New York：ACM，2003：631-636.
[9] WANG J D，KAN H T，MENG F，et al.Fake review detection based on multiple feature fusion and rolling collaborative training[J].IEEE Access，2020，8：182625-182639.
[10] MARCHAL S，SZYLLER S.Detecting organized eCommerce fraud using scalable categorical clustering[C]//35th Annual Computer Security Applications Conference，Puerto Rico，Dec 9-13，2019.New York：ACM，2019：215-228.
[11] AKOGLU L，TONG H，KOUTRA D.Graph-based anomaly detection and description：a survey[J].Data Mining & Knowledge Discovery，2015，29（3）：626-688.
[12] GUPTA M，GAO J，AGGARWAL C，et al.Outlier detection for temporal data[J].Synthesis Lectures on Data Mining and Knowledge Discovery，2014，5（1）：1-129.
[13] RANSHOUS S，SHEN S，KOUTRA D，et al.Anomaly detection in dynamic networks：a survey[J].Wiley Interdisciplinary Reviews：Computational Statistics，2015，7（3）：223-247.
[14] SAVAGE D，ZHANG X Z，YU X G，et al.Anomaly detection in online social networks[J].Social Networks，2014，39：62-70.
[15] 李忠，靳小龙，庄传志，等.面向图的异常检测研究综述[J].软件学报，2021，32（1）：167-193.
LI Z，JIN X L，ZHUANG C Z，et al.Overview on graph based anomaly detection[J].Journal of Software，2021，32（1）：167-193.
[16] 苏江军，董一鸿，颜铭江，等.面向复杂网络的异常检测研究进展[J].控制与决策，2021，36（6）：1293-1310.
SU J J，DONG Y H，YAN M J，et al.Research progress of anomaly detection for complex networks[J].Control and Decision，2021，36（6）：1293-1310.
[17] 陈波冯，李靖东，卢兴见，等.基于深度学习的图异常检测技术综述[J].计算机研究与发展，2021，58（7）：1436-1455.
CHEN B F，LI J D，LU X J，et al.Survey of deep learning based graph anomaly detection methods[J].Journal of Computer Research and Development，2021，58（7）：1436-1455.
[18] PRASANTA G，BHATTACHARYYA D K，BORAH B，et al.A survey of outlier detection methods in network anomaly identification[J].Computer Journal，2011（4）：570-588.
[19] YU R，QIN H D，WEN Z，et al.A survey on social media anomaly detection[J].ACM SIGKDD Explorations Newsletter，2016，18（1）：1-14.
[20] ANAND K，KUMAR J，ANAND K.Anomaly detection in online social network：a survey[C]//2017 International Conference on Inventive Communication and Computational Technologies，Coimbatore，Mar 10-11，2017.Piscataway：IEEE，2017：456-459.
[21] PAGE L，BRIN S，MOTWANI R，et al.The PageRank citation ranking：bringing order to the web[Z].Stanford Digital Libraries Working Paper，1998：1-17.
[22] KLEINBERG J M.Authoritative sources in a hyperlinked environment[J].Journal of the ACM，1999，46（5）：604-632.
[23] FREEMAN L C.A set of measures of centrality based on betweenness[J].Sociometry，1977，40（1）：35-41.
[24] BONACICH P，LLOYD P.Eigenvector-like measures of centrality for asymmetric relations[J].Social Networks，2001，23（3）：191-201.
[25] DRE?EWSKI R，SEPIELAK J，FILIPKOWSKI W.The application of social network analysis algorithms in a system supporting money laundering detection[J].Information Sciences，2015，295：18-32.
[26] MCCARTY C.EgoNet：personal network software[D].Florida：University of Florida，2003.
[27] AKOGLU L，MCGLOHON M，FALOUTSOS C.Oddball：spotting anomalies in weighted graphs[C]//2010 Pacific-Asia Conference on Knowledge Discovery and Data Mining，Hyderabad，Jun 21-24，2010.Berlin：Springer，2010：410-421.
[28] WANG Y，WANG L M，YANG J.EgoNet based anomaly detection in E-bank transaction networks[C]//2019 IOP Conference Series：Materials Science and Engineering，Shanghai，Apr 26-28，2019.Bristol：IOP Publishing，2020：012038.
[29] WANG K，CHEN D.Graph structure based anomaly behavior detection[C]//2nd International Conference on Computer Engineering，Information Science & Application Technology，Beijing，Sep 8-11，2017.Amsterdam：Atlantis Press，2016：531-538.
[30] COLLADON A F，REMONDI E.Using social network analysis to prevent money laundering[J].Expert Systems with Applications，2017，67：49-58.
[31] MAHOOTIHA M，GOLPAYEGANI A H，SADEGHIAN B.Designing a new method for detecting money laundering based on social network analysis[C]//2021 26th International Computer Conference，Tehran，Mar 3-4，2021.Piscataway：IEEE，2021：1-7.
[32] ZHOU Y D，WANG X M，ZHANG J J，et al.Analyzing and detecting money-laundering accounts in online social networks[J].IEEE Network，2017，32（3）：115-121.
[33] SAVAGE D，WANG Q M，CHOU P，et al.Detection of money laundering groups using supervised learning in networks[J].arXiv：1608.00708，2016.
[34] SHAIKH A K，AL-SHAMLI M，NAZIR A.Designing a relational model to identify relationships between suspicious customers in anti-money laundering（AML） using social network analysis（SNA）[J].Journal of Big Data，2021，8（1）：1-22.
[35] LIU J，BIER E，WILSON A，et al.Graph analysis for detecting fraud，waste，and abuse in healthcare data[J].AI Magazine，2016，37（2）：33-46.
[36] PINHEIRO，CARLOS A R.Highlighting unusual behavior in insurance based on social network analysis[C]//SAS Global Forum 2011，Las Vegas，Apr 4-7，2011.Cary：SAS Institute Inc，2011：1-9.
[37] MOLLOY I，CHARI S，FINKLER U，et al.Graph analy-
tics for real-time scoring of cross-channel transactional fraud[C]//20th International Conference on Financial Cryptography and Data Security，Christ Church，Feb 22-26，2016.Berlin：Springer，2016：22-40.
[38] HAVELIWALA T H.Topic-sensitive PageRank：a context-sensitive ranking algorithm for web search[J].IEEE Transactions on Knowledge and Data Engineering，2003，15（4）：784-796.
[39] VAN VLASSELAER V，ELIASSI-RAD T，AKOGLU L，et al.GOTCHA! Network-based fraud detection for social security fraud[J].Management Science，2017，63（9）：3090-3110.
[40] HE X N，MING G，KAN M Y，et al.BiRank：towards ranking on bipartite graphs[J].IEEE Transactions on Knowledge and Data Engineering，2016，29（1）：57-71.
[41] óSKARSDóTTIR M，AHMED W，ANTONIO K，et al.Social network analytics for supervised fraud detection in insurance[J].Risk Analysis，2021，42（4）：1-21.
[42] BERSHTEIN L S，TSELYKH A A.A clique-based method for mining fuzzy graph patterns in anti-money laundering systems[C]//2013 International Conference on Security of Information & Networks，Aksaray，Nov 26-28，2013.New York：ACM，2013：384-387.
[43] 祁志卫，王笳辉，岳昆，等.图嵌入方法与应用：研究综述[J].电子学报，2020，48（4）：808-818.
QI Z W，WANG J H，YUE K，et al.Methods and applications of graph embedding：a survey[J].Acta Electonica Sinica，2020，48（4）：808-818.
[44] ROWEIS S T，SAUL L K.Nonlinear dimensionality reduction by locally linear embedding[J].Science，2000，290（5500）：2323-2326.
[45] BELKIN M，NIYOGI P.Laplacian eigenmaps for dimensionality reduction and data representation[J].Neural Computation，2003，15（6）：1373-1396.
[46] PEROZZI B，AL-RFOU R，SKIENA S.Deepwalk：Online learning of social representations[C]//20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，New York，Aug 24-27，2014.New York：ACM，2014：701-710.
[47] GROVER A，LESKOVEC J.Node2vec：scalable feature learning for networks[C]//22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，San Francisco，Aug 13-17，2016.New York：ACM，2016：855-864.
[48] TANG J，QU M，WANG M Z，et al.LINE：large-scale information network embedding[C]//24th International Conference on World Wide Web，Florence，May 18-22，2015.New York：ACM，2015：1067-1077.
[49] ZHOU H J，SUN G，FU S，et al.Internet financial fraud detection based on a distributed big data approach with Node2vec[J].IEEE Access，2021，9：43378-43386.
[50] VAN BELLE R，MITROVI? S，DE WEERDT J.Representation learning in graphs for credit card fraud detection[C]//Workshop on Mining Data for Financial Applications，Würzburg，Sep 16，2019.Cham：Springer，2019：32-46.
[51] HAMILTON W L，YING Z T，LESKOVEC J.Inductive representation learning on large graphs[C]//31st International Conference on Neural Information Processing Systems，Long Beach，Dec 4-9，2017.New York：Curran Associates，2017：1025-1035.
[52] SHI M，TANG Y F，ZHU X Q，et al.Multi-class imbalanced graph convolutional network learning[C]//29th International Joint Conference on Artificial Intelligence，Yokohama，Jul 11-17，2020.San Francisco：Morgan Kaufmann，2021：2879-2885.
[53] LIU Y，AO X，QIN Z D，et al.Pick and choose：a GNN-based imbalanced learning approach for fraud detection[C]//Web Conference 2021，Ljubljana Slovenia，Apr 19-23，2021.New York：ACM，2021：3168-3177.
[54] BANDYOPADHYAY S，LOKESH N，MURTY M N.Outlier aware network embedding for attributed networks[C]//33rd AAAI Conference on Artificial Intelligence，Honolulu，Jan 27-Feb 1，2019.Palo Alto：AAAI，2019：12-19.
[55] BANDYOPADHYAY S，VIVEK S V，MURTY M N.Outlier resistant unsupervised deep architectures for attributed network embedding[C]//13th ACM International Conference on Web Search and Data Mining，Houston，Feb 3-7，2020.New York：ACM，2020：25-33.
[56] DING K，LI J D，BHANUSHALI R，et al.Deep anomaly detection on attributed networks[C]//2019 SIAM International Conference on Data Mining，Calgary，May 2-4，2019.Philadelphia：SIAM，2019：594-602.
[57] SUN J M，QU H，CHAKRABARTI D，et al.Neighborhood formation and anomaly detection in bipartite graphs[C]//5th IEEE International Conference on Data Mining，Houston，Nov 27-30，2005.Piscataway：IEEE，2005：8.
[58] XU X W，Yuruk N，FENG Z D，et al.SCAN：a structural clustering algorithm for networks[C]//13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，San Jose，Aug 12-15，2007.New York：ACM，2007：824-833.
[59] AMBAI M，UTAMA N P，YOSHIDA Y.Dimensionality reduction for histogram features based on supervised non-negative matrix factorization[J].IEICE Transactions on Information and Systems，2011，94（10）：1870-1879.
[60] NIKULIN V，HUANG T H.Unsupervised dimensionality reduction via gradient-based matrix factorization with two adaptive learning rates[C]//2012 ICML Workshop on Unsupervised and Transfer Learning，Edinburgh，Jun 26-Jul 1，2012.Cambridge：MIT Press，2012：181-194.
[61] KUANG D，DING C，PARK H.Symmetric nonnegative matrix factorization for graph clustering[C]//2012 SIAM International Conference on Data Mining，Anaheim，Apr 26-28，2012.Philadelphia：SIAM，2012：106-117.
[62] SHANG F H，JIAO L C，WANG F.Graph dual regularization non-negative matrix factorization for co-clustering[J].Pattern Recognition，2012，45（6）：2237-2250.
[63] TONG H H，LIN C Y.Non-negative residual matrix factorization with application to graph anomaly detection[C]//2011 SIAM International Conference on Data Mining，Phoenix，Apr 28-30，2011.Philadelphia：SIAM，2011：143-153.
[64] JIANG M，CUI P，BEUTEL A，et al.Inferring lockstep behavior from connectivity pattern in large graphs[J].Knowledge and Information Systems，2016，48（2）：399-428.
[65] CHARIKAR M.Greedy approximation algorithms for finding dense components in a graph[C]//2000 International Workshop on Approximation Algorithms for Combinatorial Optimization，Saarbrücken，Sep 5-8，2000.Berlin：Springer，2000：84-95.
[66] HOOI B，SONG H A，BEUTEL A，et al.Fraudar：bounding graph fraud in the face of camouflage[C]//22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，San Francisco，Aug 13-17，2016.New York：ACM，2016：895-904.
[67] REN Y X，ZHU H，ZHANG J W，et al.EnsemFDet：an ensemble approach to fraud detection based on bipartite graph[C]//2021 IEEE 37th International Conference on Data Engineering，Chania，Apr 19-22，2021.Piscataway：IEEE，2021：2039-2044.
[68] JIANG M，BEUTEL A，CUI P，et al.A general suspiciousness metric for dense blocks in multimodal data[C]//2015 IEEE International Conference on Data Mining，Atlantic City，Nov 14-17，2015.Piscataway：IEEE，2015：781-786.
[69] SHIN K，HOOI B，FALOUTSOS C.M-Zoom：fast dense-block detection in tensors with quality guarantees[C]//Joint European Conference on Machine Learning and Knowledge Discovery in Databases，Riva del Garda，Sep 19-23，2016.Cham：Springer，2016：264-280.
[70] SHIN K，HOOI B，KIM J，et al.D-Cube：dense-block detection in terabyte-scale tensors[C]//10th ACM International Conference on Web Search and Data Mining，Cambridge，Feb 6-10，2017.New York：ACM，2017：681-689.
[71] JONES K S.A statistical interpretation of term specificity and its application in retrieval[J].Journal of Documentation，1972，28（1）：11-21.
[72] WANG H B，ZHOU C，WU J，et al.Deep structure learning for fraud detection[C]//2018 IEEE International Conference on Data Mining，Rio de Janeiro，Jul 8-13，2018.Piscataway：IEEE，2018：567-576.
[73] ZHENG M Y，ZHOU C，WU J，et al.FraudNE：a joint embedding approach for fraud detection[C]//2018 International Joint Conference on Neural Networks，Rio de Janeiro，Jul 8-13，2018.Piscataway：IEEE，2018：1-8.
[74] WEST J，BHATTACHARYA M.Intelligent financial fraud detection：a comprehensive review[J].Computers & Security，2016，57：47-66.
[75] NETTLETON D F.A synthetic data generator for online social network graphs[J].Social Network Analysis and Mining，2016，6（1）：1-33.
[76] GOIX N.How to evaluate the quality of unsupervised anomaly detection algorithms?[J].arXiv：1607.01152，2016.