UPCV Distributed recommendation system based on token exchange

Ville Ollikainen, Aino Mensonen, M. Tavakolifard

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Most conventional recommendation systems are based on service-specific data repositories containing both user and item data. In this paper, we introduce an alternative approach called UPCV (Ubiquitous Personal Context Vectors) that inherently supports distributed computing and distributed data repositories. The principal idea is that each user-item interaction can update the data associated with both the user and the item. When updating, item data is made to slightly resemble user data and vice versa, leading to increasing similarity between them. Through interactions, similarity will spread from users to items, from items to users, making it possible to inherently provide user-item, item-item, item-user and user-user recommendations. The principle introduced in this paper can be used as a baseline for the design of different types of collaborative recommender systems. The main advantages of this method are that it requires no content analysis, preserves users’ privacy and supports scalability. The method was evaluated using data from 1575 book club members: the members were asked which books they had read and liked. The quantitative analysis indicates that the most promising results are obtained for active readers. However, even for less active readers and without content analysis, the recommendation list tends to be populated by the same authors and/or authors of the same genre that the readers have liked, leading to meaningful recommendations.
Original languageEnglish
Pages (from-to)195-201
Number of pages7
JournalJournal of Print and Media Technology Research
Volume2
Issue number3
Publication statusPublished - 2013
MoE publication typeA1 Journal article-refereed

Fingerprint

Recommender systems
Distributed computer systems
Scalability
Chemical analysis
content analysis
Distributed Systems
club member
book club
interaction
privacy
genre

Keywords

  • recommendation
  • collaborative filtering
  • distributed computing
  • cloud computing
  • scalability
  • privacy
  • deniability

Cite this

@article{01ed3344cdcd48afa52882944915f6c8,
title = "UPCV Distributed recommendation system based on token exchange",
abstract = "Most conventional recommendation systems are based on service-specific data repositories containing both user and item data. In this paper, we introduce an alternative approach called UPCV (Ubiquitous Personal Context Vectors) that inherently supports distributed computing and distributed data repositories. The principal idea is that each user-item interaction can update the data associated with both the user and the item. When updating, item data is made to slightly resemble user data and vice versa, leading to increasing similarity between them. Through interactions, similarity will spread from users to items, from items to users, making it possible to inherently provide user-item, item-item, item-user and user-user recommendations. The principle introduced in this paper can be used as a baseline for the design of different types of collaborative recommender systems. The main advantages of this method are that it requires no content analysis, preserves users’ privacy and supports scalability. The method was evaluated using data from 1575 book club members: the members were asked which books they had read and liked. The quantitative analysis indicates that the most promising results are obtained for active readers. However, even for less active readers and without content analysis, the recommendation list tends to be populated by the same authors and/or authors of the same genre that the readers have liked, leading to meaningful recommendations.",
keywords = "recommendation, collaborative filtering, distributed computing, cloud computing, scalability, privacy, deniability",
author = "Ville Ollikainen and Aino Mensonen and M. Tavakolifard",
year = "2013",
language = "English",
volume = "2",
pages = "195--201",
journal = "Journal of Print and Media Technology Research",
issn = "2223-8905",
publisher = "IARIGAI - International Association of Research Organizations for the Printing, Information and Communication Industries",
number = "3",

}

UPCV Distributed recommendation system based on token exchange. / Ollikainen, Ville; Mensonen, Aino; Tavakolifard, M.

In: Journal of Print and Media Technology Research, Vol. 2, No. 3, 2013, p. 195-201.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - UPCV Distributed recommendation system based on token exchange

AU - Ollikainen, Ville

AU - Mensonen, Aino

AU - Tavakolifard, M.

PY - 2013

Y1 - 2013

N2 - Most conventional recommendation systems are based on service-specific data repositories containing both user and item data. In this paper, we introduce an alternative approach called UPCV (Ubiquitous Personal Context Vectors) that inherently supports distributed computing and distributed data repositories. The principal idea is that each user-item interaction can update the data associated with both the user and the item. When updating, item data is made to slightly resemble user data and vice versa, leading to increasing similarity between them. Through interactions, similarity will spread from users to items, from items to users, making it possible to inherently provide user-item, item-item, item-user and user-user recommendations. The principle introduced in this paper can be used as a baseline for the design of different types of collaborative recommender systems. The main advantages of this method are that it requires no content analysis, preserves users’ privacy and supports scalability. The method was evaluated using data from 1575 book club members: the members were asked which books they had read and liked. The quantitative analysis indicates that the most promising results are obtained for active readers. However, even for less active readers and without content analysis, the recommendation list tends to be populated by the same authors and/or authors of the same genre that the readers have liked, leading to meaningful recommendations.

AB - Most conventional recommendation systems are based on service-specific data repositories containing both user and item data. In this paper, we introduce an alternative approach called UPCV (Ubiquitous Personal Context Vectors) that inherently supports distributed computing and distributed data repositories. The principal idea is that each user-item interaction can update the data associated with both the user and the item. When updating, item data is made to slightly resemble user data and vice versa, leading to increasing similarity between them. Through interactions, similarity will spread from users to items, from items to users, making it possible to inherently provide user-item, item-item, item-user and user-user recommendations. The principle introduced in this paper can be used as a baseline for the design of different types of collaborative recommender systems. The main advantages of this method are that it requires no content analysis, preserves users’ privacy and supports scalability. The method was evaluated using data from 1575 book club members: the members were asked which books they had read and liked. The quantitative analysis indicates that the most promising results are obtained for active readers. However, even for less active readers and without content analysis, the recommendation list tends to be populated by the same authors and/or authors of the same genre that the readers have liked, leading to meaningful recommendations.

KW - recommendation

KW - collaborative filtering

KW - distributed computing

KW - cloud computing

KW - scalability

KW - privacy

KW - deniability

UR - http://iarigai.com/publications/journals/3-2013/

M3 - Article

VL - 2

SP - 195

EP - 201

JO - Journal of Print and Media Technology Research

JF - Journal of Print and Media Technology Research

SN - 2223-8905

IS - 3

ER -