Prediction strategies in a TV recommender system - Method and experiments

M.J. van Setten, M. Veenstra, Elisabeth M.A.G. van Dijk, Antinus Nijholt

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Predicting the interests of a user in information is an important process in personalized information systems. In this paper, we present a way to create prediction engines that allow prediction techniques to be easily combined into prediction strategies. Prediction strategies choose one or a combination of prediction techniques at the moment a prediction is required, taking into account the most up -to-date knowledge about the current user, other users, the information and the system itself. Results of two experiments show that prediction strategies improve both the accuracy and stability of prediction engines. One of these experiments involves a TV recommender system. This paper describes the method of prediction strategies, how they have been applied in the TV recommender system and results of the experiment in detail.
Original languageUndefined
Title of host publicationProceedings IADIS International Conference WWW/Internet 2003
EditorsP. Isaísas, N. Karmakar
Place of PublicationLisbon, Portugal
PublisherIADIS
Pages203-210
Number of pages8
ISBN (Print)972-98947-1-X
Publication statusPublished - 5 Nov 2003
EventIADIS International Conference WWW/Internet 2003 - Algarve, Portugal
Duration: 5 Nov 20038 Nov 2003

Publication series

Name
PublisherIADIS

Conference

ConferenceIADIS International Conference WWW/Internet 2003
CountryPortugal
CityAlgarve
Period5/11/038/11/03

Keywords

  • Recommender Systems
  • Personalization
  • User Modeling
  • METIS-217440
  • Adaptive Systems
  • IR-64050
  • HMI-IE: Information Engineering
  • EWI-9965

Cite this

van Setten, M. J., Veenstra, M., van Dijk, E. M. A. G., & Nijholt, A. (2003). Prediction strategies in a TV recommender system - Method and experiments. In P. Isaísas, & N. Karmakar (Eds.), Proceedings IADIS International Conference WWW/Internet 2003 (pp. 203-210). Lisbon, Portugal: IADIS.
van Setten, M.J. ; Veenstra, M. ; van Dijk, Elisabeth M.A.G. ; Nijholt, Antinus. / Prediction strategies in a TV recommender system - Method and experiments. Proceedings IADIS International Conference WWW/Internet 2003. editor / P. Isaísas ; N. Karmakar. Lisbon, Portugal : IADIS, 2003. pp. 203-210
@inproceedings{c2699cfdded94acfad23a59101b96201,
title = "Prediction strategies in a TV recommender system - Method and experiments",
abstract = "Predicting the interests of a user in information is an important process in personalized information systems. In this paper, we present a way to create prediction engines that allow prediction techniques to be easily combined into prediction strategies. Prediction strategies choose one or a combination of prediction techniques at the moment a prediction is required, taking into account the most up -to-date knowledge about the current user, other users, the information and the system itself. Results of two experiments show that prediction strategies improve both the accuracy and stability of prediction engines. One of these experiments involves a TV recommender system. This paper describes the method of prediction strategies, how they have been applied in the TV recommender system and results of the experiment in detail.",
keywords = "Recommender Systems, Personalization, User Modeling, METIS-217440, Adaptive Systems, IR-64050, HMI-IE: Information Engineering, EWI-9965",
author = "{van Setten}, M.J. and M. Veenstra and {van Dijk}, {Elisabeth M.A.G.} and Antinus Nijholt",
year = "2003",
month = "11",
day = "5",
language = "Undefined",
isbn = "972-98947-1-X",
publisher = "IADIS",
pages = "203--210",
editor = "P. Isa{\'i}sas and N. Karmakar",
booktitle = "Proceedings IADIS International Conference WWW/Internet 2003",

}

van Setten, MJ, Veenstra, M, van Dijk, EMAG & Nijholt, A 2003, Prediction strategies in a TV recommender system - Method and experiments. in P Isaísas & N Karmakar (eds), Proceedings IADIS International Conference WWW/Internet 2003. IADIS, Lisbon, Portugal, pp. 203-210, IADIS International Conference WWW/Internet 2003, Algarve, Portugal, 5/11/03.

Prediction strategies in a TV recommender system - Method and experiments. / van Setten, M.J.; Veenstra, M.; van Dijk, Elisabeth M.A.G.; Nijholt, Antinus.

Proceedings IADIS International Conference WWW/Internet 2003. ed. / P. Isaísas; N. Karmakar. Lisbon, Portugal : IADIS, 2003. p. 203-210.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Prediction strategies in a TV recommender system - Method and experiments

AU - van Setten, M.J.

AU - Veenstra, M.

AU - van Dijk, Elisabeth M.A.G.

AU - Nijholt, Antinus

PY - 2003/11/5

Y1 - 2003/11/5

N2 - Predicting the interests of a user in information is an important process in personalized information systems. In this paper, we present a way to create prediction engines that allow prediction techniques to be easily combined into prediction strategies. Prediction strategies choose one or a combination of prediction techniques at the moment a prediction is required, taking into account the most up -to-date knowledge about the current user, other users, the information and the system itself. Results of two experiments show that prediction strategies improve both the accuracy and stability of prediction engines. One of these experiments involves a TV recommender system. This paper describes the method of prediction strategies, how they have been applied in the TV recommender system and results of the experiment in detail.

AB - Predicting the interests of a user in information is an important process in personalized information systems. In this paper, we present a way to create prediction engines that allow prediction techniques to be easily combined into prediction strategies. Prediction strategies choose one or a combination of prediction techniques at the moment a prediction is required, taking into account the most up -to-date knowledge about the current user, other users, the information and the system itself. Results of two experiments show that prediction strategies improve both the accuracy and stability of prediction engines. One of these experiments involves a TV recommender system. This paper describes the method of prediction strategies, how they have been applied in the TV recommender system and results of the experiment in detail.

KW - Recommender Systems

KW - Personalization

KW - User Modeling

KW - METIS-217440

KW - Adaptive Systems

KW - IR-64050

KW - HMI-IE: Information Engineering

KW - EWI-9965

M3 - Conference contribution

SN - 972-98947-1-X

SP - 203

EP - 210

BT - Proceedings IADIS International Conference WWW/Internet 2003

A2 - Isaísas, P.

A2 - Karmakar, N.

PB - IADIS

CY - Lisbon, Portugal

ER -

van Setten MJ, Veenstra M, van Dijk EMAG, Nijholt A. Prediction strategies in a TV recommender system - Method and experiments. In Isaísas P, Karmakar N, editors, Proceedings IADIS International Conference WWW/Internet 2003. Lisbon, Portugal: IADIS. 2003. p. 203-210