RECATHON: A Middleware for Context-Aware Recommendation in Database Systems

Mohamed Sarwat, James L. Avery, Mohamed Mokbel

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

2 Citations (Scopus)

Abstract

This paper presents RECATHON, a context-aware recommender system built entirely inside a database system. Unlike traditional recommender systems that are context-free where they support the general query of Recommend movies for a certain user, RECATHON users can request recommendations based on their age, location, gender, or any other contextual/demographical/preferential user attribute. A main challenge of supporting such kind of recommenders is the difficulty of deciding what attributes to build recommenders on. RECATHON addresses this challenge as it supports building recommenders in database systems in an analogous way to building index structures. Users can decide to create recommenders on selected attributes, e.g., Age and/or gender, and then entertain efficient support of multidimensional recommenders on the selected attributes. RECATHON employs a multi-dimensional index structure for each built recommender that can be accessed using novel query execution algorithms to support efficient retrieval for recommender queries. Experimental results based on an actual prototype of RECATHON, built inside Postgre SQL, using real Movie Lens and Foursquare data show that RECATHON exhibits real time performance for large-scale multidimensional recommendation.

Original languageEnglish
Title of host publicationProceedings - 2015 IEEE 16th International Conference on Mobile Data Management, MDM 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages54-63
Number of pages10
Volume1
ISBN (Electronic)9781479999729
DOIs
Publication statusPublished - 11 Sep 2015
Externally publishedYes
Event16th IEEE International Conference on Mobile Data Management, MDM 2015 - Pittsburgh, United States
Duration: 15 Jun 201518 Jun 2015

Other

Other16th IEEE International Conference on Mobile Data Management, MDM 2015
CountryUnited States
CityPittsburgh
Period15/6/1518/6/15

Fingerprint

Recommender systems
Middleware
Lenses

Keywords

  • Context
  • Database
  • Recommender

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Sarwat, M., Avery, J. L., & Mokbel, M. (2015). RECATHON: A Middleware for Context-Aware Recommendation in Database Systems. In Proceedings - 2015 IEEE 16th International Conference on Mobile Data Management, MDM 2015 (Vol. 1, pp. 54-63). [7264304] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MDM.2015.63

RECATHON : A Middleware for Context-Aware Recommendation in Database Systems. / Sarwat, Mohamed; Avery, James L.; Mokbel, Mohamed.

Proceedings - 2015 IEEE 16th International Conference on Mobile Data Management, MDM 2015. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 2015. p. 54-63 7264304.

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

Sarwat, M, Avery, JL & Mokbel, M 2015, RECATHON: A Middleware for Context-Aware Recommendation in Database Systems. in Proceedings - 2015 IEEE 16th International Conference on Mobile Data Management, MDM 2015. vol. 1, 7264304, Institute of Electrical and Electronics Engineers Inc., pp. 54-63, 16th IEEE International Conference on Mobile Data Management, MDM 2015, Pittsburgh, United States, 15/6/15. https://doi.org/10.1109/MDM.2015.63
Sarwat M, Avery JL, Mokbel M. RECATHON: A Middleware for Context-Aware Recommendation in Database Systems. In Proceedings - 2015 IEEE 16th International Conference on Mobile Data Management, MDM 2015. Vol. 1. Institute of Electrical and Electronics Engineers Inc. 2015. p. 54-63. 7264304 https://doi.org/10.1109/MDM.2015.63
Sarwat, Mohamed ; Avery, James L. ; Mokbel, Mohamed. / RECATHON : A Middleware for Context-Aware Recommendation in Database Systems. Proceedings - 2015 IEEE 16th International Conference on Mobile Data Management, MDM 2015. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 2015. pp. 54-63
@inproceedings{57f46191c06a4ea0bd1ed0ba12421518,
title = "RECATHON: A Middleware for Context-Aware Recommendation in Database Systems",
abstract = "This paper presents RECATHON, a context-aware recommender system built entirely inside a database system. Unlike traditional recommender systems that are context-free where they support the general query of Recommend movies for a certain user, RECATHON users can request recommendations based on their age, location, gender, or any other contextual/demographical/preferential user attribute. A main challenge of supporting such kind of recommenders is the difficulty of deciding what attributes to build recommenders on. RECATHON addresses this challenge as it supports building recommenders in database systems in an analogous way to building index structures. Users can decide to create recommenders on selected attributes, e.g., Age and/or gender, and then entertain efficient support of multidimensional recommenders on the selected attributes. RECATHON employs a multi-dimensional index structure for each built recommender that can be accessed using novel query execution algorithms to support efficient retrieval for recommender queries. Experimental results based on an actual prototype of RECATHON, built inside Postgre SQL, using real Movie Lens and Foursquare data show that RECATHON exhibits real time performance for large-scale multidimensional recommendation.",
keywords = "Context, Database, Recommender",
author = "Mohamed Sarwat and Avery, {James L.} and Mohamed Mokbel",
year = "2015",
month = "9",
day = "11",
doi = "10.1109/MDM.2015.63",
language = "English",
volume = "1",
pages = "54--63",
booktitle = "Proceedings - 2015 IEEE 16th International Conference on Mobile Data Management, MDM 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - RECATHON

T2 - A Middleware for Context-Aware Recommendation in Database Systems

AU - Sarwat, Mohamed

AU - Avery, James L.

AU - Mokbel, Mohamed

PY - 2015/9/11

Y1 - 2015/9/11

N2 - This paper presents RECATHON, a context-aware recommender system built entirely inside a database system. Unlike traditional recommender systems that are context-free where they support the general query of Recommend movies for a certain user, RECATHON users can request recommendations based on their age, location, gender, or any other contextual/demographical/preferential user attribute. A main challenge of supporting such kind of recommenders is the difficulty of deciding what attributes to build recommenders on. RECATHON addresses this challenge as it supports building recommenders in database systems in an analogous way to building index structures. Users can decide to create recommenders on selected attributes, e.g., Age and/or gender, and then entertain efficient support of multidimensional recommenders on the selected attributes. RECATHON employs a multi-dimensional index structure for each built recommender that can be accessed using novel query execution algorithms to support efficient retrieval for recommender queries. Experimental results based on an actual prototype of RECATHON, built inside Postgre SQL, using real Movie Lens and Foursquare data show that RECATHON exhibits real time performance for large-scale multidimensional recommendation.

AB - This paper presents RECATHON, a context-aware recommender system built entirely inside a database system. Unlike traditional recommender systems that are context-free where they support the general query of Recommend movies for a certain user, RECATHON users can request recommendations based on their age, location, gender, or any other contextual/demographical/preferential user attribute. A main challenge of supporting such kind of recommenders is the difficulty of deciding what attributes to build recommenders on. RECATHON addresses this challenge as it supports building recommenders in database systems in an analogous way to building index structures. Users can decide to create recommenders on selected attributes, e.g., Age and/or gender, and then entertain efficient support of multidimensional recommenders on the selected attributes. RECATHON employs a multi-dimensional index structure for each built recommender that can be accessed using novel query execution algorithms to support efficient retrieval for recommender queries. Experimental results based on an actual prototype of RECATHON, built inside Postgre SQL, using real Movie Lens and Foursquare data show that RECATHON exhibits real time performance for large-scale multidimensional recommendation.

KW - Context

KW - Database

KW - Recommender

UR - http://www.scopus.com/inward/record.url?scp=84958230889&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958230889&partnerID=8YFLogxK

U2 - 10.1109/MDM.2015.63

DO - 10.1109/MDM.2015.63

M3 - Conference contribution

AN - SCOPUS:84958230889

VL - 1

SP - 54

EP - 63

BT - Proceedings - 2015 IEEE 16th International Conference on Mobile Data Management, MDM 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -