Flexible mixture model for collaborative filtering.pdf

Flexible mixture model for collaborative filtering.pdf

ID:33849720

大小:95.87 KB

頁(yè)數(shù):8頁(yè)

時(shí)間:2019-02-28

Flexible mixture model for collaborative filtering.pdf_第1頁(yè)
Flexible mixture model for collaborative filtering.pdf_第2頁(yè)
Flexible mixture model for collaborative filtering.pdf_第3頁(yè)
Flexible mixture model for collaborative filtering.pdf_第4頁(yè)
Flexible mixture model for collaborative filtering.pdf_第5頁(yè)
資源描述:

《Flexible mixture model for collaborative filtering.pdf》由會(huì)員上傳分享,免費(fèi)在線閱讀,更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫(kù)。

1、FlexibleMixtureModelforCollaborativeFilteringLuoSiLSI@CS.CMU.EDURongJinRONG@CS.CMU.EDUSchoolofComputerScience,CarnegieMellonUniversity,Pittsburgh,PA15232USAAbstractusersinthetrainingdatabasesimilartothetestuserandthen,predictthetestuser’sratingsbasedontheThispaperpresen

2、tsaflexiblemixturemodelcorrespondingratingsofthesesimilarusers.Onthe(FMM)forcollaborativefiltering.FMMextendscontrary,model-basedalgorithmsbuildmodelsthatareexistingpartitioning/clusteringalgorithmsforabletoexplainthetrainingexampleswellandpredictthecollaborativefilteri

3、ngbyclusteringbothusersratingsoftestusersusingtheestimatedmodels.Bothofanditemstogethersimultaneouslywithoutthememory-basedalgorithmsandthemodel-basedassumingthateachuseranditemshouldonlyalgorithmshavetheiradvantagesanddisadvantages.belongtoasinglecluster.Furthermore,wi

4、ththeMemory-basedalgorithmshavemuchlessoff-lineintroductionof‘preference’nodes,theproposedcomputationcostswhilethemodel-basedalgorithmsmayframeworkisabletoexplicitlymodelhowusershavelesson-linecomputationcosts.rateitems,whichcanvarydramatically,evenamongtheuserswithsimi

5、lartastesonitems.Thoughmemory-basedandmodel-basedapproachesEmpiricalstudyovertwodatasetsofmoviedifferfromeachotherinmanyaspects,bothofthemratingshasshownthatournewalgorithmassumethatuserswithsimilartastesshouldrateitemsoutperformsfiveothercollaborativefilteringsimilarly

6、andthereforetheideaofclusteringisusedinalgorithmssubstantially.bothapproacheseitherexplicitlyorimplicitly.Formemory-basedapproaches,traininguserssimilartothetestuseraregroupedtogetherandtheirratingsare1.Introductioncombinedtopredictratingsforthetestuser.Meanwhile,model-

7、basedapproachesclusteritemsand/ortrainingTherapidgrowthoftheinformationontheInternetusersintoclassesexplicitlyandpredictratingsofatestdemandsintelligentinformationagentthatcansiftuserbysimplyusingtheratingsofclassesthatfitinbestthroughalltheavailableinformationandfindou

8、tthewiththetestuserand/oritemstoberated.Thus,howtomostvaluabletous.Theseintelligentsystemscanbeclusterusersand

當(dāng)前文檔最多預(yù)覽五頁(yè),下載文檔查看全文

此文檔下載收益歸作者所有

當(dāng)前文檔最多預(yù)覽五頁(yè),下載文檔查看全文
溫馨提示:
1. 部分包含數(shù)學(xué)公式或PPT動(dòng)畫的文件,查看預(yù)覽時(shí)可能會(huì)顯示錯(cuò)亂或異常,文件下載后無(wú)此問題,請(qǐng)放心下載。
2. 本文檔由用戶上傳,版權(quán)歸屬用戶,天天文庫(kù)負(fù)責(zé)整理代發(fā)布。如果您對(duì)本文檔版權(quán)有爭(zhēng)議請(qǐng)及時(shí)聯(lián)系客服。
3. 下載前請(qǐng)仔細(xì)閱讀文檔內(nèi)容,確認(rèn)文檔內(nèi)容符合您的需求后進(jìn)行下載,若出現(xiàn)內(nèi)容與標(biāo)題不符可向本站投訴處理。
4. 下載文檔時(shí)可能由于網(wǎng)絡(luò)波動(dòng)等原因無(wú)法下載或下載錯(cuò)誤,付費(fèi)完成后未能成功下載的用戶請(qǐng)聯(lián)系客服處理。