A Method of Mining Key Account from Internet Pyramid Selling Data
Internet pyramid selling has a variety of characteristics, such as involved large number of people, large amount of money and diversified operation mode.It is difficult to investigate and collect the evidence of pyramid selling crime.As most of internet pyramid selling often uses virtual coins to complete cash settlement, criminals can exchange virtual coins by controlling visual accounts to transfer illegally funds.In order to mine the abnormal accounts, trading behavior of virtual coins was characterized, and OCSVM classification model was used to classify trading behaviors.Then, correlation can be extracted from members information and pyramid selling hierarchical relationship after analyzing the massive data of pyramid selling platform.Finally, we can screen out the virtual accounts directly controlled by the pyramid selling organization, analyze the flow of funds, investigate and obtain evidence on amount of money involved in pyramid selling.The experimental results show that the classification model not only can establish the normal model for account transfer behavior, but also effectively identify abnormal transfer behavior, thus improving efficiency of investigation and evidence collection for economic investigation departments.
Internet Pyramid Selling OCSVM classification abnormal transaction electronic forensics
Jianying Xiong Min Tu
Collaborative Innovation Center for Economics Crime Investigation and Prevention Technology Jiangxi Police College Nanchang,China
国际会议
郑州
英文
148-155
2018-09-21（万方平台首次上网日期，不代表论文的发表时间）