Contextual information based recommender system using Singular Value Decomposition

Rahul Gupta, Arpit Jain, Satakshi Rana, Sanjay Singh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

The web contains a large collection of data, this is where the need for recommender system arises. A recommender system helps user to come to a decision quickly. In the conventional recommendation system only the reviewer's ratings are taken into consideration. However, contextual information pertaining to each user should be incorporated in the recommendation system, making the recommendation personalized. As some features can enhance the performance of a recommendation system and also certain irrelevant features might degrade it, feature selection becomes an essential aspect of context aware recommendation system. In our paper we have devised a novel approach which first selects relevant contextual variables based on the contextual information of the reviewers and their ratings for a class of entities, with naive Bayes classifier. Once the relevant contextual variables are extracted, Singular Value Decomposition (SVD) is applied for extracting most significant features corresponding to each entity. This information is used by the recommendation system in analyzing the contextual information of the user in recommending him entities that are of interest to him. The proposed method also determines the best contextual variable and feature space for each entity. This enables the context aware recommendation system more efficient and personalized. Moreover, with the proposed method an overall increase in F-score of 30% was obtained thereby improving the reliability of the recommender system.

Original languageEnglish
Title of host publicationProceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013
Pages2084-2089
Number of pages6
DOIs
Publication statusPublished - 01-12-2013
Event2013 2nd International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013 - Mysore, India
Duration: 22-08-201325-08-2013

Conference

Conference2013 2nd International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013
CountryIndia
CityMysore
Period22-08-1325-08-13

Fingerprint

Recommender systems
Singular value decomposition
Feature extraction
Classifiers

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems

Cite this

Gupta, R., Jain, A., Rana, S., & Singh, S. (2013). Contextual information based recommender system using Singular Value Decomposition. In Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013 (pp. 2084-2089). [6637502] https://doi.org/10.1109/ICACCI.2013.6637502
Gupta, Rahul ; Jain, Arpit ; Rana, Satakshi ; Singh, Sanjay. / Contextual information based recommender system using Singular Value Decomposition. Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013. 2013. pp. 2084-2089
@inproceedings{c3bf57c50e9f4c0f912b653ef8393c0a,
title = "Contextual information based recommender system using Singular Value Decomposition",
abstract = "The web contains a large collection of data, this is where the need for recommender system arises. A recommender system helps user to come to a decision quickly. In the conventional recommendation system only the reviewer's ratings are taken into consideration. However, contextual information pertaining to each user should be incorporated in the recommendation system, making the recommendation personalized. As some features can enhance the performance of a recommendation system and also certain irrelevant features might degrade it, feature selection becomes an essential aspect of context aware recommendation system. In our paper we have devised a novel approach which first selects relevant contextual variables based on the contextual information of the reviewers and their ratings for a class of entities, with naive Bayes classifier. Once the relevant contextual variables are extracted, Singular Value Decomposition (SVD) is applied for extracting most significant features corresponding to each entity. This information is used by the recommendation system in analyzing the contextual information of the user in recommending him entities that are of interest to him. The proposed method also determines the best contextual variable and feature space for each entity. This enables the context aware recommendation system more efficient and personalized. Moreover, with the proposed method an overall increase in F-score of 30{\%} was obtained thereby improving the reliability of the recommender system.",
author = "Rahul Gupta and Arpit Jain and Satakshi Rana and Sanjay Singh",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/ICACCI.2013.6637502",
language = "English",
isbn = "9781467362153",
pages = "2084--2089",
booktitle = "Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013",

}

Gupta, R, Jain, A, Rana, S & Singh, S 2013, Contextual information based recommender system using Singular Value Decomposition. in Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013., 6637502, pp. 2084-2089, 2013 2nd International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013, Mysore, India, 22-08-13. https://doi.org/10.1109/ICACCI.2013.6637502

Contextual information based recommender system using Singular Value Decomposition. / Gupta, Rahul; Jain, Arpit; Rana, Satakshi; Singh, Sanjay.

Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013. 2013. p. 2084-2089 6637502.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Contextual information based recommender system using Singular Value Decomposition

AU - Gupta, Rahul

AU - Jain, Arpit

AU - Rana, Satakshi

AU - Singh, Sanjay

PY - 2013/12/1

Y1 - 2013/12/1

N2 - The web contains a large collection of data, this is where the need for recommender system arises. A recommender system helps user to come to a decision quickly. In the conventional recommendation system only the reviewer's ratings are taken into consideration. However, contextual information pertaining to each user should be incorporated in the recommendation system, making the recommendation personalized. As some features can enhance the performance of a recommendation system and also certain irrelevant features might degrade it, feature selection becomes an essential aspect of context aware recommendation system. In our paper we have devised a novel approach which first selects relevant contextual variables based on the contextual information of the reviewers and their ratings for a class of entities, with naive Bayes classifier. Once the relevant contextual variables are extracted, Singular Value Decomposition (SVD) is applied for extracting most significant features corresponding to each entity. This information is used by the recommendation system in analyzing the contextual information of the user in recommending him entities that are of interest to him. The proposed method also determines the best contextual variable and feature space for each entity. This enables the context aware recommendation system more efficient and personalized. Moreover, with the proposed method an overall increase in F-score of 30% was obtained thereby improving the reliability of the recommender system.

AB - The web contains a large collection of data, this is where the need for recommender system arises. A recommender system helps user to come to a decision quickly. In the conventional recommendation system only the reviewer's ratings are taken into consideration. However, contextual information pertaining to each user should be incorporated in the recommendation system, making the recommendation personalized. As some features can enhance the performance of a recommendation system and also certain irrelevant features might degrade it, feature selection becomes an essential aspect of context aware recommendation system. In our paper we have devised a novel approach which first selects relevant contextual variables based on the contextual information of the reviewers and their ratings for a class of entities, with naive Bayes classifier. Once the relevant contextual variables are extracted, Singular Value Decomposition (SVD) is applied for extracting most significant features corresponding to each entity. This information is used by the recommendation system in analyzing the contextual information of the user in recommending him entities that are of interest to him. The proposed method also determines the best contextual variable and feature space for each entity. This enables the context aware recommendation system more efficient and personalized. Moreover, with the proposed method an overall increase in F-score of 30% was obtained thereby improving the reliability of the recommender system.

UR - http://www.scopus.com/inward/record.url?scp=84891950232&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891950232&partnerID=8YFLogxK

U2 - 10.1109/ICACCI.2013.6637502

DO - 10.1109/ICACCI.2013.6637502

M3 - Conference contribution

SN - 9781467362153

SP - 2084

EP - 2089

BT - Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013

ER -

Gupta R, Jain A, Rana S, Singh S. Contextual information based recommender system using Singular Value Decomposition. In Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013. 2013. p. 2084-2089. 6637502 https://doi.org/10.1109/ICACCI.2013.6637502