Jian Hu, etc., Demographic prediction based on user’s browsing behavior, (1)

Jian Hu, etc., Demographic prediction based on user’s browsing behavior, (1)

ID:39888409

大小:307.57 KB

页数:10页

时间:2019-07-14

Jian Hu, etc., Demographic prediction based on user’s browsing behavior, (1)_第1页
Jian Hu, etc., Demographic prediction based on user’s browsing behavior, (1)_第2页
Jian Hu, etc., Demographic prediction based on user’s browsing behavior, (1)_第3页
Jian Hu, etc., Demographic prediction based on user’s browsing behavior, (1)_第4页
Jian Hu, etc., Demographic prediction based on user’s browsing behavior, (1)_第5页
资源描述:

《Jian Hu, etc., Demographic prediction based on user’s browsing behavior, (1)》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、WWW2007/Track:DataMiningSession:PredictiveModelingofWebUsersDemographicPredictionBasedonUser’sBrowsingBehaviorJianHu,Hua-JunZeng,HuaLi,ChengNiu,ZhengChenMicrosoftResearchAsia49ZhichunRoadBeijing100080,P.R.China{jianh,hjzeng,huli,chengniu,zhengc}@microsoft.comABSTRACT

2、Yahoo!allowsuserstobuildtheirpreferencesexplicitlyandonlyshowsectionsanddetailswhichtheymaybeinterestedin.GoogleDemographicinformationplaysanimportantroleinpersonalizedPersonalorganizesusers’searchresultsaccordingtotheirsearchwebapplications.However,itisusuallynoteas

3、ytoobtainthishistoriesincludingtheirprevioussearchresultsandnewskindofpersonaldatasuchasageandgender.Inthispaper,weheadlinesclicked.Accompanywiththeprosperousofgeneralwebmadeafirstapproachtopredictusers’genderandagefromtheirservice,onlineadvertisingisgrowingrapidlyin

4、recentyears,inWebbrowsingbehaviors,inwhichtheWebpageviewwhichbehavioraltargetingisbecomingparticularlypopular[22].informationistreatedasahiddenvariabletopropagateBehaviortargetinghelpsadvertiserstotargetproperusersupondemographicinformationbetweendifferentusers.There

5、arethreetheirbehaviorswhilesurfingonline.Asreportedin[18],mainstepsinourapproach:First,learningfromtheWebpagecompanieslikeTacodaSystems,Claria,RevenueScienceandTMclick-thoughdata,Webpagesareassociatedwithusers’(known)Advertisingprovideadvertiserswithbehavioraltargeti

6、ngageandgendertendencythroughadiscriminativemodel;Second,technologies.AccordingtotherecentstudiesofTMAdvertising,users’(unknown)ageandgenderarepredictedfromthecomparedtosimplewebads,behavior-basedadsgain115%moredemographicinformationoftheassociatedWebpagesthroughabus

7、inesstrafficayear,andthetargetedconsumersalsoscored3%Bayesianframework;Third,basedonthefactthatWebpageshigherthantheaverageviewersinbrandawareness.Userprofilevisitedbysimilarusersmaybeassociatedwithsimilarwhichincludespriorsearchresults,demographicinformation,demogra

8、phictendency,anduserswithsimilardemographicgeographicinformationandinterestedtopicsplaysakeyroleininformationwouldvisitsimilarWebpa

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。