Web挖掘在网络广告点击欺诈检测中的应用  

Application of web mining technology to click fraud detection

作　　者：李爱春[1] 滕少华[1] 

机构地区：[1]广东工业大学计算机学院,广东广州510006

出　　处：《计算机工程与设计》2012年第3期957-962,共6页Computer Engineering and Design

基　　金：广东省自然科学基金项目(06021484;9151009001000007;9451009001002777);广东省科技计划基金项目(2008A060201011);韶关市科技计划基金项目(2010CXY/C05)

摘　　要：为有效解决网络广告中存在的点击欺诈问题,提出了一种基于Web挖掘算法的解决方案,并设计了一套点击欺诈检测模型。该模型通过对点击流进行时序分析、离群点挖掘、非线性分析等操作,能有效检测或屏蔽各类点击欺诈,有效屏蔽无意识的无效点击,并且在不影响广告展示速度的基础上显著提高检测点击欺诈的效率。实验结果表明,该解决方案可以有效检测采用手动或者利用计算机程序的方法模仿正常用户进行点击欺诈的行为,表明了模型的可行性和方案的有效性。To solve the click fraud problem of online advertising industry, a scheme based web mining algorithm is proposed, and a click fraud detection model is designed. The model use the click stream to run time series analysis, outlier mining, nonlinear analysis and other operations, the model can detect or shield effectively various types of click fraud, shield effectively the uncon- scious invalid clicks, and improve significantly the efficiency of click fraud detection based on no affect of the rate of advertising showing. Experiments show that the proposed scheme could be effectively detected the click fraud of the persons who took manual or used computer program to imitate a legitimate user of web browser, the feasibility of the model and the effectiveness of the scheme is proved.

关 键 词：点击欺诈 WEB数据挖掘 离群点 预测 网络广告 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]