基于银行账户亲密度网络推理的团伙预测研究

doi:10.11959/j.issn.2096-109x.2019062

网络与信息安全学报 ›› 2019, Vol. 5 ›› Issue (6): 95-104.doi: 10.11959/j.issn.2096-109x.2019062

基于银行账户亲密度网络推理的团伙预测研究

吕芳,陆海博,王巍,黄俊恒,王佰玲()

哈尔滨工业大学（威海）计算机科学与技术学院，山东威海 264209

修回日期:2019-05-14 出版日期:2019-12-15 发布日期:2019-12-14
作者简介:吕芳（1990- ），女，山东阳谷人，哈尔滨工业大学（威海）博士生，主要研究方向为复杂网络、信息内容安全、数据掘|陆海博（1998- ），男，甘肃酒泉人，主要研究方向为金融安全。|王巍（1975- ），女，黑龙江齐齐哈尔人，博士，哈尔滨工业大学（威海）讲师、硕士生导师，主要研究方向为金融安全、数据挖掘、自然语言处理|黄俊恒（1966- ），男，河南新乡人，哈尔滨工业大学（威海）副教授，主要研究方向为数据挖掘、人工智能|王佰玲（1978- ），男，黑龙江哈尔滨人，哈尔滨工业大学（威海）教授、博士生导师，主要研究方向为信息对抗、信息安全、信息搜索、移动网络、金融安全
基金资助:
国家重点研发计划基金资助项目(2018YFB2004201);国家重点研发计划基金资助项目(2017YFB0801804);国家前沿科技创新专项(2016QY05X1002-2);国家区域创新中心科技专项(2017QYCX14);山东省重点研发计划基金资助项目(2017CXGC0706);中央高校基本科研业务费专项资金资助(HIT.NSRIF.2020098);2017威海市大学共建基金资助项目

Reasoning method for predicting crime partner by using intimacy network of bank accounts

Fang LYU,Haibo LU,Wei WANG,Junheng HUANG,Bailing WANG()

School of Computer Science and Technology,Harbin Institute of Technology,Weihai 264209,China

Revised:2019-05-14 Online:2019-12-15 Published:2019-12-14
Supported by:
The National Key Research and Development Program of China(2018YFB2004201);The National Key Research and Development Program of China(2017YFB0801804);Frontier Science and Technology in Notation of China(2016QY05X1002-2);National Regional Innovation Center Science and Technology Special Project of China(2017QYCX14);Key Research and Development Program of Shandong Province(2017CXGC0706);the Fundamental Research Funds for the Central Universities(HIT.NSRIF.2020098);2017 University Co-construction Project in Weihai City

摘要/Abstract

摘要：

近年来，针对涉众型非法金融活动在资金交易规律的研究引起了研究者的高度关注。为解决利用银行交易数据进行异常账户犯罪团伙主动发现的问题，提出一种基于银行账户非对称亲密度网络的团伙预测方法。首先，建立银行账户交易通用网络模型，将时序交易数据嵌入网络结构中。然后，利用节点的直接和间接交易关系信息，提出一种账户非对称亲密度计算方法。最终，利用节点在亲密度网络上的非对称交互信息，得到节点的异常倾向性指标。在包含传销团伙的真实数据上的实验结果表明，基于亲密度网络的团伙预测方法能有效发现潜在传销人员。

关键词: 银行账户交易网络, 亲密度网络, 直接亲密度, 间接亲密度, 团伙预测

Abstract:

In recent years,research on the law of capital transactions in the case of stakeholder-type illegal financial activities has attracted the attention of researchers.In order to solve the problem of using the bank transaction data to actively discover the abnormal account criminal crime partners,a crime partner prediction method based on the asymmetric intimacy network of the bank accounts was proposed.Firstly,a general network model for bank account transactions was established to embed time-series transaction data into the network structure.Then,using the direct and indirect transaction relationship information of the node,an account asymmetric intimacy calculation method was proposed.Finally,using the asymmetric interaction information of the nodes on the intimate network,the abnormal tendency index of the nodes is obtained.The experimental results on the actual data of the multi-level marketing group show that the crime partner prediction method based on the intimacy network can effectively find potential pyramid shelling members.

Key words: transaction network of bank accounts, intimacy network, direct intimacy, indirect intimacy

中图分类号:

TP391.4

吕芳,陆海博,王巍,黄俊恒,王佰玲. 基于银行账户亲密度网络推理的团伙预测研究[J]. 网络与信息安全学报, 2019, 5(6): 95-104.

Fang LYU,Haibo LU,Wei WANG,Junheng HUANG,Bailing WANG. Reasoning method for predicting crime partner by using intimacy network of bank accounts[J]. Chinese Journal of Network and Information Security, 2019, 5(6): 95-104.

图/表 11

图1

图2

图3

表1

图4

图5

图6

图7

图8

表2

图9

参考文献 19

[1]	陈鹏, 袁宏永 . 犯罪组织结构的社会网络分析[J]. 清华大学学报(自然科学版), 2011,51(8): 1097-1101.
	CHEN P , YUAN H Y . Social network analysis of crime organization structures[J]. Journal of Tsinghua University (Science and Technology), 2011,51(8): 1097-1101.
[2]	LIU J X . The research on detecting community structure of complex networks and its application in financial Networks[D]. Lanzhou:Lanzhou University of Technology, 2013.
[3]	韩华, 吴翎燕, 宋宁宁 . 基于随机矩阵的金融网络模型[J]. 物理学报, 2014,63(13): 431-440.
	HAN H , WU L Y , SONG N N . Financial networks model based on random matrix[J]. Acta Physica Sinica, 2014,63(13): 431-440,2014.
[4]	李琼婕, 薛耀文 . 最小费用最大流维度拓展及其在反洗钱中的应用研究[J]. 山西师范大学学报（自然科学版）, 2014,28(1): 28-32.
	LI Q J , XUE Y W . Dimension-expansion of minimum cost and maximum flow theory and its application research in anti-money laundering[J]. Journal of Shanxi Normal University (Science and Technology), 2014,28(1): 28-32.
[5]	ADAMIC L A , ADAR E . Friends and neighbors on the Web[J]. Social Networks, 2003,25(3): 211-230.
[6]	WU Z H , LIN Y F . Link prediction with node clustering coefficient[J]. Physica A:Statistical Mechanics and Its Applications, 2016,452: 1-8.
[7]	ZHOU T , LYU L Y , ZHANG Y C . Predicting missing links via local information[J]. The European Physical Journal B, 2009,71(4): 623-630.
[8]	LEICHT E A , HOLME P , NEWMAN M E J . Vertex similarity in networks[J]. Physical Review E Statistical Nonlinear and Soft Matter Physics, 2006,73(2): 1-10.
[9]	ZHU X Z , TIAN H , CAI S M . Predicting missing links via effective paths[J]. Physica A:Statistical Mechanics and Its Applications, 2014,413(11): 515-522.
[10]	PEROZZI B , RAMI A R , SKIENA S . DeepWalk:anline learning of social representations[C]// ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD’14). 2014: 701-710.
[11]	TANG J , QU M , WANG M ,et al. LINE:large-scale information network embedding[C]// International Conference on World Wide Web (WWW’15). 2015: 1067-1077.
[12]	WANG D X , CUI P , ZHU W W . Structural deep network embedding[C]// ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD’16). 2016: 1225-1234.
[13]	DONNAT C , MARINKA Z , HALLAC D ,et al. Learning structural node embeddings via diffusion wavelets[C]// ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD’18). 2018.
[14]	SUN Y , TAN W N , LI L X ,et al. A new method to identify collaborative partners in social service provider networks[J]. Information Systems Frontiers, 2016,18(3).
[15]	CHEN H , CHUNG W , XU J J ,et al. Crime data mining:a general framework and some examples[J]. Computer, 2004,37(4): 50-56.
[16]	杨莉莉, 杨永川 . 基于社会网络的犯罪组织关系挖掘[J]. 计算机工程, 2009,35(15): 91-93.
	YANG L L , YANG Y C . Crime organization relation mining based on social network[J]. Computer Engineering, 2009,35(15): 91-93.
[17]	高建强, 谭剑, 崔永发 . 一种基于通讯痕迹的社会网络团伙分析模型[J]. 计算机应用与软件, 2012,29(3): 206-208.
	GAO J Q , TAN J , CUI Y F . One social network clique analysis model based on communication trace[J]. Computer Applications and Software, 2012,29(3): 206-208.
[18]	李万彪, 余志, 龚峻峰 ,等. 基于关系数据模型的犯罪网络挖掘研究[J]. 中山大学学报（自然科学版）, 2014,53(5): 1-7.
	LI W B , YU Z , GONG J F ,et al. An approach of crime network analysis based on association data model[J]. Acta Scientiarum Anturalium Universitatis Sunyatseni, 2014,53(5): 1-7.
[19]	唐德权, 史伟奇, 凌志刚 . 有组织犯罪集团挖掘算法[J]. 计算机系统应用, 2015,24(9): 196-200.
	TANG D Q , SHI W Q , LING Z G . Algorithm for mining organized crime[J]. Computer Systems ＆ Applications, 2015,24(9): 196-200.

序号		节点对		金额	频次	共同对手数	间接路径	亲密度
1	298**44		824**86	17 105 600	175	1	12	0.97
2	294**28		824**86	5 203 070	92	0	12	0.89
3	927**63		123**84	13 139 300	53	0	10	0.84
4	871**02		399**00	4 057 180	32	2	10	0.74
5	570**07		111**95	3 795 940	18	4	0	0.69
6	256**62		442**25	1 051 580	76	2	2	0.54
7	318**34		686**67	1 033 870	73	1	1	0.46

预测算法	准确率	召回率	F1值
基于交易金额	0.90	0.12	0.21
基于交易频次	0.91	0.105	0.19
基于直接亲密度	0.92	0.12	0.22
本文算法	0.95	0.19	0.32

基于银行账户亲密度网络推理的团伙预测研究

Reasoning method for predicting crime partner by using intimacy network of bank accounts

在线阅读

pdf下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 19

相关文章 1

Metrics

推荐阅读 0