A switching multi-level method for the long tail recommendation problem

Gharbi Alshammari, Jose Luis Jorro Aragoneses, Nikolaos Polatidis, Stelios Kapetanakis, Elias Pimenidis, Miltos Petridis

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Recommender systems are decision support systems that play an important part in generating a list of product or service recommendations for users based on the past experiences and interactions. The most popular recommendation method is Collaborative Filtering (CF) that is based on the users’ rating history to generate the recommendation. Although, recommender systems have been applied successfully in different areas such as e-Commerce and Social Networks, the popularity bias is still one of the challenges that needs to be further researched. Therefore, we propose a multi-level method that is based on a switching approach which solves the long tail recommendation problem (LTRP) when CF fails to find the target case. We have evaluated our method using two public datasets and the results show that it outperforms a number of bases lines and state-of-the-art alternatives with a further reduce of the recommendation error rates for items found in the long tail.
Original languageEnglish
Pages (from-to)1-10
JournalJournal of Intelligent and Fuzzy Systems
DOIs
Publication statusPublished - 15 Jul 2019

Fingerprint

Collaborative filtering
Recommender systems
Decision support systems
History

Bibliographical note

The final publication is available at IOS Press through http://dx.doi.org/10.3233/JIFS-179331

Cite this

Alshammari, Gharbi ; Jorro Aragoneses, Jose Luis ; Polatidis, Nikolaos ; Kapetanakis, Stelios ; Pimenidis, Elias ; Petridis, Miltos. / A switching multi-level method for the long tail recommendation problem. In: Journal of Intelligent and Fuzzy Systems. 2019 ; pp. 1-10.
@article{724c5d6921e34494990d84f2d04850eb,
title = "A switching multi-level method for the long tail recommendation problem",
abstract = "Recommender systems are decision support systems that play an important part in generating a list of product or service recommendations for users based on the past experiences and interactions. The most popular recommendation method is Collaborative Filtering (CF) that is based on the users’ rating history to generate the recommendation. Although, recommender systems have been applied successfully in different areas such as e-Commerce and Social Networks, the popularity bias is still one of the challenges that needs to be further researched. Therefore, we propose a multi-level method that is based on a switching approach which solves the long tail recommendation problem (LTRP) when CF fails to find the target case. We have evaluated our method using two public datasets and the results show that it outperforms a number of bases lines and state-of-the-art alternatives with a further reduce of the recommendation error rates for items found in the long tail.",
author = "Gharbi Alshammari and {Jorro Aragoneses}, {Jose Luis} and Nikolaos Polatidis and Stelios Kapetanakis and Elias Pimenidis and Miltos Petridis",
note = "The final publication is available at IOS Press through http://dx.doi.org/10.3233/JIFS-179331",
year = "2019",
month = "7",
day = "15",
doi = "10.3233/JIFS-179331",
language = "English",
pages = "1--10",
journal = "Journal of Intelligent and Fuzzy Systems",
issn = "1064-1246",

}

A switching multi-level method for the long tail recommendation problem. / Alshammari, Gharbi; Jorro Aragoneses, Jose Luis; Polatidis, Nikolaos; Kapetanakis, Stelios; Pimenidis, Elias; Petridis, Miltos.

In: Journal of Intelligent and Fuzzy Systems, 15.07.2019, p. 1-10.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A switching multi-level method for the long tail recommendation problem

AU - Alshammari, Gharbi

AU - Jorro Aragoneses, Jose Luis

AU - Polatidis, Nikolaos

AU - Kapetanakis, Stelios

AU - Pimenidis, Elias

AU - Petridis, Miltos

N1 - The final publication is available at IOS Press through http://dx.doi.org/10.3233/JIFS-179331

PY - 2019/7/15

Y1 - 2019/7/15

N2 - Recommender systems are decision support systems that play an important part in generating a list of product or service recommendations for users based on the past experiences and interactions. The most popular recommendation method is Collaborative Filtering (CF) that is based on the users’ rating history to generate the recommendation. Although, recommender systems have been applied successfully in different areas such as e-Commerce and Social Networks, the popularity bias is still one of the challenges that needs to be further researched. Therefore, we propose a multi-level method that is based on a switching approach which solves the long tail recommendation problem (LTRP) when CF fails to find the target case. We have evaluated our method using two public datasets and the results show that it outperforms a number of bases lines and state-of-the-art alternatives with a further reduce of the recommendation error rates for items found in the long tail.

AB - Recommender systems are decision support systems that play an important part in generating a list of product or service recommendations for users based on the past experiences and interactions. The most popular recommendation method is Collaborative Filtering (CF) that is based on the users’ rating history to generate the recommendation. Although, recommender systems have been applied successfully in different areas such as e-Commerce and Social Networks, the popularity bias is still one of the challenges that needs to be further researched. Therefore, we propose a multi-level method that is based on a switching approach which solves the long tail recommendation problem (LTRP) when CF fails to find the target case. We have evaluated our method using two public datasets and the results show that it outperforms a number of bases lines and state-of-the-art alternatives with a further reduce of the recommendation error rates for items found in the long tail.

U2 - 10.3233/JIFS-179331

DO - 10.3233/JIFS-179331

M3 - Article

SP - 1

EP - 10

JO - Journal of Intelligent and Fuzzy Systems

T2 - Journal of Intelligent and Fuzzy Systems

JF - Journal of Intelligent and Fuzzy Systems

SN - 1064-1246

ER -