A group preference-based item similarity model: comparison of clustering techniques in ambient and context-aware recommender systems

Yeongwook Yang, Danial Hooshyar, Jaechoon Jo, Heui Seok Lim

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

In the study of collaborative filtering, scholars and professionals alike have given much attention to user responses of the “one-class” type, feedback like online transactions or “likes”. Such behavior gauges have been integral to many ambient intelligent and context-aware recommendation systems, in which users are furnished with personalized lists of items according to their exhibited tastes. These one-class data, earlier studies have shown, are readily grasped by Bayesian personalized ranking, a pairwise preference assumption. Nevertheless, these works fail to make sufficient use of item similarity models using group preference. To improve performance, we argue in this paper, it is necessary to develop a model that yokes a User preference model to the Group Preference-based Similarity models (called UGPS). UCPG will produce a greater depth of interactions, we argue, because it takes on an entire set of items as opposed to the solitary item used previously. Moreover, a number of clustering methods have been put to work in group preference-based recommendation systems, but there is no consensus as to which offers superior accuracy. To gain clarity, we first built up a pair of versions of UGPS in order to assess the recommendation performances of different approaches to group generation: UGPS-1, which employed K-means, and UGPS-2, using K-NN—according to how efficiently they group their output. This comparison revealed that UGPS-1 tended to improve its recommendation performance as the number of groups and representative item sets grew. In contrast, UGPS-2 exhibited the opposite effect: recommendation performance declined as the number of groups and representative item sets expanded. Lastly, we consider how our UGPS system works with various sophisticated approaches on four real datasets, and demonstrate that UGPS produces more accurate recommendations.

Original languageEnglish
JournalJournal of Ambient Intelligence and Humanized Computing
DOIs
Publication statusAccepted/In press - 2018 Jan 1

Fingerprint

Recommender systems
Deflection yokes
Collaborative filtering
Gages
Feedback

Keywords

  • Ambient intelligent
  • Clustering algorithms
  • Context-aware
  • Group preference
  • Item similarity model
  • K-means
  • KNN
  • Recommender systems

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

@article{3e1ec8105d474781a7917dd16b9df53a,
title = "A group preference-based item similarity model: comparison of clustering techniques in ambient and context-aware recommender systems",
abstract = "In the study of collaborative filtering, scholars and professionals alike have given much attention to user responses of the “one-class” type, feedback like online transactions or “likes”. Such behavior gauges have been integral to many ambient intelligent and context-aware recommendation systems, in which users are furnished with personalized lists of items according to their exhibited tastes. These one-class data, earlier studies have shown, are readily grasped by Bayesian personalized ranking, a pairwise preference assumption. Nevertheless, these works fail to make sufficient use of item similarity models using group preference. To improve performance, we argue in this paper, it is necessary to develop a model that yokes a User preference model to the Group Preference-based Similarity models (called UGPS). UCPG will produce a greater depth of interactions, we argue, because it takes on an entire set of items as opposed to the solitary item used previously. Moreover, a number of clustering methods have been put to work in group preference-based recommendation systems, but there is no consensus as to which offers superior accuracy. To gain clarity, we first built up a pair of versions of UGPS in order to assess the recommendation performances of different approaches to group generation: UGPS-1, which employed K-means, and UGPS-2, using K-NN—according to how efficiently they group their output. This comparison revealed that UGPS-1 tended to improve its recommendation performance as the number of groups and representative item sets grew. In contrast, UGPS-2 exhibited the opposite effect: recommendation performance declined as the number of groups and representative item sets expanded. Lastly, we consider how our UGPS system works with various sophisticated approaches on four real datasets, and demonstrate that UGPS produces more accurate recommendations.",
keywords = "Ambient intelligent, Clustering algorithms, Context-aware, Group preference, Item similarity model, K-means, KNN, Recommender systems",
author = "Yeongwook Yang and Danial Hooshyar and Jaechoon Jo and Lim, {Heui Seok}",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/s12652-018-1039-1",
language = "English",
journal = "Journal of Ambient Intelligence and Humanized Computing",
issn = "1868-5137",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - A group preference-based item similarity model

T2 - comparison of clustering techniques in ambient and context-aware recommender systems

AU - Yang, Yeongwook

AU - Hooshyar, Danial

AU - Jo, Jaechoon

AU - Lim, Heui Seok

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In the study of collaborative filtering, scholars and professionals alike have given much attention to user responses of the “one-class” type, feedback like online transactions or “likes”. Such behavior gauges have been integral to many ambient intelligent and context-aware recommendation systems, in which users are furnished with personalized lists of items according to their exhibited tastes. These one-class data, earlier studies have shown, are readily grasped by Bayesian personalized ranking, a pairwise preference assumption. Nevertheless, these works fail to make sufficient use of item similarity models using group preference. To improve performance, we argue in this paper, it is necessary to develop a model that yokes a User preference model to the Group Preference-based Similarity models (called UGPS). UCPG will produce a greater depth of interactions, we argue, because it takes on an entire set of items as opposed to the solitary item used previously. Moreover, a number of clustering methods have been put to work in group preference-based recommendation systems, but there is no consensus as to which offers superior accuracy. To gain clarity, we first built up a pair of versions of UGPS in order to assess the recommendation performances of different approaches to group generation: UGPS-1, which employed K-means, and UGPS-2, using K-NN—according to how efficiently they group their output. This comparison revealed that UGPS-1 tended to improve its recommendation performance as the number of groups and representative item sets grew. In contrast, UGPS-2 exhibited the opposite effect: recommendation performance declined as the number of groups and representative item sets expanded. Lastly, we consider how our UGPS system works with various sophisticated approaches on four real datasets, and demonstrate that UGPS produces more accurate recommendations.

AB - In the study of collaborative filtering, scholars and professionals alike have given much attention to user responses of the “one-class” type, feedback like online transactions or “likes”. Such behavior gauges have been integral to many ambient intelligent and context-aware recommendation systems, in which users are furnished with personalized lists of items according to their exhibited tastes. These one-class data, earlier studies have shown, are readily grasped by Bayesian personalized ranking, a pairwise preference assumption. Nevertheless, these works fail to make sufficient use of item similarity models using group preference. To improve performance, we argue in this paper, it is necessary to develop a model that yokes a User preference model to the Group Preference-based Similarity models (called UGPS). UCPG will produce a greater depth of interactions, we argue, because it takes on an entire set of items as opposed to the solitary item used previously. Moreover, a number of clustering methods have been put to work in group preference-based recommendation systems, but there is no consensus as to which offers superior accuracy. To gain clarity, we first built up a pair of versions of UGPS in order to assess the recommendation performances of different approaches to group generation: UGPS-1, which employed K-means, and UGPS-2, using K-NN—according to how efficiently they group their output. This comparison revealed that UGPS-1 tended to improve its recommendation performance as the number of groups and representative item sets grew. In contrast, UGPS-2 exhibited the opposite effect: recommendation performance declined as the number of groups and representative item sets expanded. Lastly, we consider how our UGPS system works with various sophisticated approaches on four real datasets, and demonstrate that UGPS produces more accurate recommendations.

KW - Ambient intelligent

KW - Clustering algorithms

KW - Context-aware

KW - Group preference

KW - Item similarity model

KW - K-means

KW - KNN

KW - Recommender systems

UR - http://www.scopus.com/inward/record.url?scp=85053512673&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053512673&partnerID=8YFLogxK

U2 - 10.1007/s12652-018-1039-1

DO - 10.1007/s12652-018-1039-1

M3 - Article

AN - SCOPUS:85053512673

JO - Journal of Ambient Intelligence and Humanized Computing

JF - Journal of Ambient Intelligence and Humanized Computing

SN - 1868-5137

ER -