The effect of rating variance on personalized recommendation

Recommender systems have made significant progress over the last decade and several industrial-strength systems have been developed. Typically, recommender systems try to predict people's preferences and use accuracy indices such as mean absolute error to judge the performance of the algorithms...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2010 5th International Conference on Computer Science and Education S. 366 - 370
Hauptverfasser: Yu-Xiao Zhu, Wei Zeng, Qian-Ming Zhang
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.08.2010
Schlagworte:
Accuracy
Collaboration
Collaborative Filtering
Diversity
Motion pictures
Prediction algorithms
Rating Variance
Recommender systems
Training
ISBN:1424460026, 9781424460021
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Recommender systems have made significant progress over the last decade and several industrial-strength systems have been developed. Typically, recommender systems try to predict people's preferences and use accuracy indices such as mean absolute error to judge the performance of the algorithms. Recently, the diversity index is widely accepted as another metric. However, the ability of a recommendation algorithm to gain both accuracy and diversity at the same time remains largely unexplored. Variance based collaborative filtering is proposed as an improvement to satisfy the two measures. In this paper, we give a detail discussion on the effect of rating variance of collaborative filtering (CF) and get some different results. We find that the variance-based algorithm has limited ability to overcome the accuracy-diversity tradeoff. In fact the improvement in diversity comes at the expense of the precision. How to solve the dilemma is still a problem deserved further researching.
AbstractList Recommender systems have made significant progress over the last decade and several industrial-strength systems have been developed. Typically, recommender systems try to predict people's preferences and use accuracy indices such as mean absolute error to judge the performance of the algorithms. Recently, the diversity index is widely accepted as another metric. However, the ability of a recommendation algorithm to gain both accuracy and diversity at the same time remains largely unexplored. Variance based collaborative filtering is proposed as an improvement to satisfy the two measures. In this paper, we give a detail discussion on the effect of rating variance of collaborative filtering (CF) and get some different results. We find that the variance-based algorithm has limited ability to overcome the accuracy-diversity tradeoff. In fact the improvement in diversity comes at the expense of the precision. How to solve the dilemma is still a problem deserved further researching.
Author Wei Zeng
Yu-Xiao Zhu
Qian-Ming Zhang
Author_xml – sequence: 1
  surname: Yu-Xiao Zhu
  fullname: Yu-Xiao Zhu
  email: zhuyuxiao1314@163.com
  organization: Web Sci. Center, Univ. of Electron. Sci. & Technol. of China, Chengdu, China
– sequence: 2
  surname: Wei Zeng
  fullname: Wei Zeng
  organization: Web Sci. Center, Univ. of Electron. Sci. & Technol. of China, Chengdu, China
– sequence: 3
  surname: Qian-Ming Zhang
  fullname: Qian-Ming Zhang
  organization: Web Sci. Center, Univ. of Electron. Sci. & Technol. of China, Chengdu, China
BookMark eNpFT81Kw0AYXLGCtvYF9LIvkPrtX5IFLxKqFgoemnv5uvlWV5rdsgmCPr0BC85hhoFhmJmzWUyRGLsTsBIC7MOmaXbrlYTJG2NVKeCCzYWWWpcAWl7-G1les-UwfMIEbaQR9oY9th_EyXtyI0-eZxxDfOdfmANGRzxFfqI8pIjH8EMdz-RS31PsplyKt-zK43Gg5VkXrH1et81rsX172TRP2yJYGAuJtdXSVHUnjMbaVRPDNFMYZRW5Q60VGHQWoVPCqoMAr0yFVekt1FhJtWD3f7WBiPanHHrM3_vzWfULJsVIvA
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICCSE.2010.5593610
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 1424460042
9781424460052
1424460050
9781424460045
EndPage 370
ExternalDocumentID 5593610
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ADFMO
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
IEGSK
IERZE
OCL
RIE
RIL
ID FETCH-LOGICAL-i90t-2a8942578d154a8c754a061015393ecb84305ac9a0d3193b10f357a76f908a723
IEDL.DBID RIE
ISBN 1424460026
9781424460021
IngestDate Wed Aug 27 03:07:07 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i90t-2a8942578d154a8c754a061015393ecb84305ac9a0d3193b10f357a76f908a723
PageCount 5
ParticipantIDs ieee_primary_5593610
PublicationCentury 2000
PublicationDate 2010-Aug.
PublicationDateYYYYMMDD 2010-08-01
PublicationDate_xml – month: 08
  year: 2010
  text: 2010-Aug.
PublicationDecade 2010
PublicationTitle 2010 5th International Conference on Computer Science and Education
PublicationTitleAbbrev ICCSE
PublicationYear 2010
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000452519
Score 1.4558014
Snippet Recommender systems have made significant progress over the last decade and several industrial-strength systems have been developed. Typically, recommender...
SourceID ieee
SourceType Publisher
StartPage 366
SubjectTerms Accuracy
Collaboration
Collaborative Filtering
Diversity
Motion pictures
Prediction algorithms
Rating Variance
Recommender systems
Training
Title The effect of rating variance on personalized recommendation
URI https://ieeexplore.ieee.org/document/5593610
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEB1q8eBJpRW_ycGjsdlm2yTgbWlRkFKwSG8lu8lKD-6Wuu3BX-_MfongxcuS3UNIdgjzMjPvDcAdovg4tU7yeBgLHoap5OjnPdcBBRlIr6VU-3x7UbOZXi7NvAP3LRfGe18Wn_kHGpa5fJcnOwqVDUbUfo74VAdKqYqr1cZTSBoc0UjD3aJ007iRdKrfg4Y0I8zgOYpeJ1VlVz3rr_YqpXeZHv9vXSfQ_6HpsXnrgE6h47MePKLhWVWlwfKUkYGzd7bHKzHZl-UZ2zT4-8s7RhfiD5y-aq3Uh8V0soieeN0iga-NKPjQalMeOodIyOpE4RMdNLp4aaRPYk2CXjYxVjg8ajIORCpHyqpxaoS2aijPoJvlmT8H5qzRBtGRH5kQf2VojXAIH0JpA-tSnVxAjza-2lQiGKt6z5d_f76CoyrNTpVy19Attjt_A4fJvlh_bm9Ly30DL4KS-Q
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEB1KFfSk0orf5uDRtdlNtpuAt1JpsZaCRXor2U1WenC31LYHf70z-1ERvHhZsnsIyQ5hXmbmvQG4QxQfp8YKLw5i7kmZCg_9vPOUT0EG0msp1D7fRtF4rGYzPWnA_Y4L45wris_cAw2LXL7Nkw2FyjohtZ8jPtVeKGXgl2ytXUSFxMERj9TsLUo4dWtRp-rdr2kzXHeGvd5rv6ztqub91WCl8C9PR_9b2TG0f4h6bLJzQSfQcFkLHtH0rKzTYHnKyMTZO9vipZgszPKMLWsE_uUsoyvxB05fNldqw_SpP-0NvKpJgrfQfO0FRuni2FnEQkYlET7RRaOTF1q4JFYk6WUSbbjFwyZin6cijEzUTTVXJgrEKTSzPHNnwKzRSiM-cqGW-Cul0dwigJDC-MamKjmHFm18vixlMObVni_-_nwLB4Ppy2g-Go6fL-GwTLpT3dwVNNerjbuG_WS7XnyubgorfgMM4pZA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2010+5th+International+Conference+on+Computer+Science+and+Education&rft.atitle=The+effect+of+rating+variance+on+personalized+recommendation&rft.au=Yu-Xiao+Zhu&rft.au=Wei+Zeng&rft.au=Qian-Ming+Zhang&rft.date=2010-08-01&rft.pub=IEEE&rft.isbn=9781424460021&rft.spage=366&rft.epage=370&rft_id=info:doi/10.1109%2FICCSE.2010.5593610&rft.externalDocID=5593610
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781424460021/lc.gif&client=summon&freeimage=true
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781424460021/mc.gif&client=summon&freeimage=true
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781424460021/sc.gif&client=summon&freeimage=true