A knowledge reuse framework for improving novelty and diversity in recommendations

Apurva Pathak, Bidyut Kr. Patra

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

7 Citations (Scopus)

Abstract

Recommender system (RS) is an important instrument in e-commerce, which provides personalized recommendations to individual user. Classical algorithms in recommender system mainly emphasize on recommendation accuracy in order to match individual user's past profile. However, recent study shows that novelty and diversity in recommendations are equally important factors from both user and business view points. In this paper, we introduce a knowledge reuse framework to increase novelty and diversity in the recommended items of individual users while compromising very little recommendation accuracy. The proposed framework uses features information which have already been extracted by an existing collaborative filtering. Experimental results with real datasets show that our approach outperforms state-of-the-art solutions in providing novel and diverse recommended items to individual users and aggregate diversity gain achieved by our approach is on par with recently proposed rank based approach.
Original languageEnglish
Title of host publicationCoDS '15 Proceedings of the Second ACM IKDD Conference on Data Sciences
PublisherAssociation for Computing Machinery ACM
Pages11-19
ISBN (Print)978-1-4503-3436-5
DOIs
Publication statusPublished - 2015
MoE publication typeA4 Article in a conference publication
Event2nd IKDD Conference on Data Sciences, CoDS 2015 - Bangalore, India
Duration: 18 Mar 201521 Mar 2015
Conference number: 2

Conference

Conference2nd IKDD Conference on Data Sciences, CoDS 2015
Abbreviated titleCoDS 2015
CountryIndia
CityBangalore
Period18/03/1521/03/15

Fingerprint

Recommender systems
Collaborative filtering
Industry

Keywords

  • collaborative filtering
  • novelty
  • diversity
  • clustering
  • knowledge reuse framework

Cite this

Pathak, A., & Patra, B. K. (2015). A knowledge reuse framework for improving novelty and diversity in recommendations. In CoDS '15 Proceedings of the Second ACM IKDD Conference on Data Sciences (pp. 11-19). Association for Computing Machinery ACM. https://doi.org/10.1145/2732587.2732590
Pathak, Apurva ; Patra, Bidyut Kr. / A knowledge reuse framework for improving novelty and diversity in recommendations. CoDS '15 Proceedings of the Second ACM IKDD Conference on Data Sciences. Association for Computing Machinery ACM, 2015. pp. 11-19
@inproceedings{a77cc40aa2e64c67b626497ba1fd59e0,
title = "A knowledge reuse framework for improving novelty and diversity in recommendations",
abstract = "Recommender system (RS) is an important instrument in e-commerce, which provides personalized recommendations to individual user. Classical algorithms in recommender system mainly emphasize on recommendation accuracy in order to match individual user's past profile. However, recent study shows that novelty and diversity in recommendations are equally important factors from both user and business view points. In this paper, we introduce a knowledge reuse framework to increase novelty and diversity in the recommended items of individual users while compromising very little recommendation accuracy. The proposed framework uses features information which have already been extracted by an existing collaborative filtering. Experimental results with real datasets show that our approach outperforms state-of-the-art solutions in providing novel and diverse recommended items to individual users and aggregate diversity gain achieved by our approach is on par with recently proposed rank based approach.",
keywords = "collaborative filtering, novelty, diversity, clustering, knowledge reuse framework",
author = "Apurva Pathak and Patra, {Bidyut Kr.}",
year = "2015",
doi = "10.1145/2732587.2732590",
language = "English",
isbn = "978-1-4503-3436-5",
pages = "11--19",
booktitle = "CoDS '15 Proceedings of the Second ACM IKDD Conference on Data Sciences",
publisher = "Association for Computing Machinery ACM",
address = "United States",

}

Pathak, A & Patra, BK 2015, A knowledge reuse framework for improving novelty and diversity in recommendations. in CoDS '15 Proceedings of the Second ACM IKDD Conference on Data Sciences. Association for Computing Machinery ACM, pp. 11-19, 2nd IKDD Conference on Data Sciences, CoDS 2015, Bangalore, India, 18/03/15. https://doi.org/10.1145/2732587.2732590

A knowledge reuse framework for improving novelty and diversity in recommendations. / Pathak, Apurva; Patra, Bidyut Kr.

CoDS '15 Proceedings of the Second ACM IKDD Conference on Data Sciences. Association for Computing Machinery ACM, 2015. p. 11-19.

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

TY - GEN

T1 - A knowledge reuse framework for improving novelty and diversity in recommendations

AU - Pathak, Apurva

AU - Patra, Bidyut Kr.

PY - 2015

Y1 - 2015

N2 - Recommender system (RS) is an important instrument in e-commerce, which provides personalized recommendations to individual user. Classical algorithms in recommender system mainly emphasize on recommendation accuracy in order to match individual user's past profile. However, recent study shows that novelty and diversity in recommendations are equally important factors from both user and business view points. In this paper, we introduce a knowledge reuse framework to increase novelty and diversity in the recommended items of individual users while compromising very little recommendation accuracy. The proposed framework uses features information which have already been extracted by an existing collaborative filtering. Experimental results with real datasets show that our approach outperforms state-of-the-art solutions in providing novel and diverse recommended items to individual users and aggregate diversity gain achieved by our approach is on par with recently proposed rank based approach.

AB - Recommender system (RS) is an important instrument in e-commerce, which provides personalized recommendations to individual user. Classical algorithms in recommender system mainly emphasize on recommendation accuracy in order to match individual user's past profile. However, recent study shows that novelty and diversity in recommendations are equally important factors from both user and business view points. In this paper, we introduce a knowledge reuse framework to increase novelty and diversity in the recommended items of individual users while compromising very little recommendation accuracy. The proposed framework uses features information which have already been extracted by an existing collaborative filtering. Experimental results with real datasets show that our approach outperforms state-of-the-art solutions in providing novel and diverse recommended items to individual users and aggregate diversity gain achieved by our approach is on par with recently proposed rank based approach.

KW - collaborative filtering

KW - novelty

KW - diversity

KW - clustering

KW - knowledge reuse framework

U2 - 10.1145/2732587.2732590

DO - 10.1145/2732587.2732590

M3 - Conference article in proceedings

SN - 978-1-4503-3436-5

SP - 11

EP - 19

BT - CoDS '15 Proceedings of the Second ACM IKDD Conference on Data Sciences

PB - Association for Computing Machinery ACM

ER -

Pathak A, Patra BK. A knowledge reuse framework for improving novelty and diversity in recommendations. In CoDS '15 Proceedings of the Second ACM IKDD Conference on Data Sciences. Association for Computing Machinery ACM. 2015. p. 11-19 https://doi.org/10.1145/2732587.2732590