一种基于客户行为时序分析的反洗钱异常交易识别方法

中国管理科学 ›› 2014, Vol. 22 ›› Issue (12): 102-108.

一种基于客户行为时序分析的反洗钱异常交易识别方法

刘卓军¹, 李晓明^1,2

1. 中国科学院数学与系统科学研究院, 北京 100190;
2. 中国科学院大学, 北京 100049

收稿日期:2012-05-30 修回日期:2013-07-01 出版日期:2014-12-20 发布日期:2014-12-23
作者简介:刘卓军(1958-),男(汉族),黑龙江人,中国科学院数学与系统科学研究院,研究员,研究方向:系统安全.
基金资助:
国家科技支撑计划项目(2013BAK04B02-02)

An Approach for Unusual Transaction Detection Based on Customer Behavior Time Series Analysis

LIU Zhuo-jun¹, LI Xiao-ming^1,2

1. Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2012-05-30 Revised:2013-07-01 Online:2014-12-20 Published:2014-12-23

摘要/Abstract

摘要： 可疑交易报告制度是打击洗钱活动的一项基本机制,如何有效甄别可疑交易是金融机构和金融情报中心面临的一个技术难点。为辅助反洗钱分析人员从海量金融交易信息中甄别客户异常交易,本文提出一种预测误差和统计处理综合法——CPEST,通过分析客户前后行为的一致性来发现异常。CPEST建立客户行为模型,根据预测误差对客户行为进行时点异常检验,并在此基础上构造一个窗口检验,以提高对涉嫌洗钱行为的识别能力。本文在支持向量回归和核密度估计等具体实现手段的基础上,运用CPEST对实际交易和仿真数据进行分析,结果表明该方法的有效性和可行性,具有应用推广价值。

关键词: 反洗钱, 异常点监测, 时序, 支持向量回归, 核密度估计

Abstract: The suspicious transaction reporting system is the principle mechanism to fight against money laundering, and it is a technical problem to detect suspicious transaction for financial institutions and the financial intelligence unit. To help anti-money laundering analysts screen customers' unusual transactions and behaviors in massive financial transaction information, a new method, composition of predictive error and statistic treatment(CPEST) is presented, which can be used to detect unusual behaviors from the inconsistency of customer behaviors. CPEST models a customer's behavior, tests a customer's behavior at a particular time using estimated errors, and uses a window test to improve the ability to identify suspected of money laundering. Applying the method based on support vector regression and kernel density estimation to real data examples and simulations, the experiment results suggest that the method,which is feasible and effective, has high value in popularization and application.

Key words: anti-money laundering, anomaly detection, time series, support vector regression, kernel density estimation

中图分类号:

C931

刘卓军, 李晓明. 一种基于客户行为时序分析的反洗钱异常交易识别方法[J]. 中国管理科学, 2014, 22(12): 102-108.

LIU Zhuo-jun, LI Xiao-ming. An Approach for Unusual Transaction Detection Based on Customer Behavior Time Series Analysis[J]. Chinese Journal of Management Science, 2014, 22(12): 102-108.

参考文献

[1] 欧阳卫民.正确理解新的大额和可疑资金交易识别标准[J]. 中国金融,2007,(16):64-65.

[2] 中国人民银行反洗钱局.中国反洗钱报告(2010)[M].北京:中国金融出版社,2011.

[3] 汤俊,熊前兴.基于时序相似度的离群模式检测模型[J]. 武汉大学学报(工学版), 2006, 39 (3):111-114.

[4] Liu Xuan, Zhang Pengzhu, Zeng Dajun. Sequence matching for suspicious activity detection in anti-money laundering[M]//Mehrotras,zeng DD,chen H C.Intelligence and Security Informatics. Berlin: Springer Verlag, 2008: 50-61.

[5] 喻炜,王建东.基于交易网络特征向量中心度量的可疑洗钱识别系统[J].计算机应用,2009,29(9):2581-2585.

[6] 汤俊.基于客户行为模式识别的反洗钱数据监测与分析系统[J].中南财经政法大学学报,2005,(4):62-67.

[7] 欧阳卫民.我国反洗钱若干重大问题(下)[J].财经理论与实践,2006,27(142):2-9.

[8] 苏宁.反洗钱法规实用手册[M].北京:中国金融出版社,2007.

[9] Alwan L C, Roberts H V. Time-series modeling for statistical process control[J]. Journal of Business and Economic Statistics, 1988, 6(1): 87-95.

[10] Tay F E, Cao L. Application of support vector machines in financial time series forecasting[J]. International Journal of Management Science, 2001, 29(4):309-317.

[11] Krollner B, Vanstone B, Finnie G. Financial time series forecasting with machine learning techniques: A survey[C].Proceedings of 18th European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning, Bruges(Belgium), April 28-30,2010.

[12] Packard N H, Crutchfield J P,Farmers J D, et al. Geometry from a time series[J]. Physical review letters, 1980, 45(9):712-716.

[13] Small M. Applied nonlinear time series analysis[M]. Singapore: World Scientific, 2005.

[14] Ma Junshui, Perkins S. Online novelty detection on temporal sequences[C]. Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington D C,OSA,August, 24-27,2003.

[15] Bishop C M. Pattern recognition and machine learning[M]. New York:Springer, 2006.

[16] Smola A J, Scholkopf B. A tutorial on support vector regression[J]. Statistics and Computing, 2004,14(3):199-222.

[17] Wand M P,Jones M C. Kernel smoothing[M]. London: Chapman and Hall, 1995.

[18] 孟庆芳.非线性动力系统时间序列分析方法及其应用研究[D].济南:山东大学,2008.

[19] Stone R, Taylor M. Time series models in statistical process control:Considerations of applicability[J]. The Statistician, 1995, 44(2): 227-234.

[20] Ma Junshui, Perkins S. Time-series novelty detection using one-class support vector machines[C]. Proceedings of the International Joint Conference on Neural Networks, IEEE, Portland,Oregon,USA,July 20-24,2003.