LARS

A location-aware recommender system

Justin J. Levandoski, Mohamed Sarwat, Ahmed Eldawy, Mohamed Mokbel

Research output: Contribution to journalConference article

251 Citations (Scopus)

Abstract

This paper proposes LARS, a location-aware recommender system that uses location-based ratings to produce recommendations. Traditional recommender systems do not consider spatial properties of users nor items, LARS, on the other hand, supports a taxonomy of three novel classes of location-based ratings, namely, spatial ratings for non-spatial items, non-spatial ratings for spatial items, and spatial ratings for spatial items. LARS exploits user rating locations through user partitioning, a technique that influences recommendations with ratings spatially close to querying users in a manner that maximizes system scalability while not sacrificing recommendation quality. LARS exploits item locations using travel penalty, a technique that favors recommendation candidates closer in travel distance to querying users in a way that avoids exhaustive access to all spatial items. LARS can apply these techniques separately, or in concert, depending on the type of location-based rating available. Experimental evidence using large-scale real-world data from both the Foursquare location-based social network and the Movie Lens movie recommendation system reveals that LARS is efficient, scalable, and capable of producing recommendations twice as accurate compared to existing recommendation approaches.

Original languageEnglish
Article number6228105
Pages (from-to)450-461
Number of pages12
JournalProceedings - International Conference on Data Engineering
DOIs
Publication statusPublished - 30 Jul 2012
Externally publishedYes

Fingerprint

Recommender systems
Personnel rating
Taxonomies
Scalability
Lenses

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Information Systems

Cite this

LARS : A location-aware recommender system. / Levandoski, Justin J.; Sarwat, Mohamed; Eldawy, Ahmed; Mokbel, Mohamed.

In: Proceedings - International Conference on Data Engineering, 30.07.2012, p. 450-461.

Research output: Contribution to journalConference article

Levandoski, Justin J. ; Sarwat, Mohamed ; Eldawy, Ahmed ; Mokbel, Mohamed. / LARS : A location-aware recommender system. In: Proceedings - International Conference on Data Engineering. 2012 ; pp. 450-461.
@article{29dd19d9fc3b4b489321b3544d28be55,
title = "LARS: A location-aware recommender system",
abstract = "This paper proposes LARS, a location-aware recommender system that uses location-based ratings to produce recommendations. Traditional recommender systems do not consider spatial properties of users nor items, LARS, on the other hand, supports a taxonomy of three novel classes of location-based ratings, namely, spatial ratings for non-spatial items, non-spatial ratings for spatial items, and spatial ratings for spatial items. LARS exploits user rating locations through user partitioning, a technique that influences recommendations with ratings spatially close to querying users in a manner that maximizes system scalability while not sacrificing recommendation quality. LARS exploits item locations using travel penalty, a technique that favors recommendation candidates closer in travel distance to querying users in a way that avoids exhaustive access to all spatial items. LARS can apply these techniques separately, or in concert, depending on the type of location-based rating available. Experimental evidence using large-scale real-world data from both the Foursquare location-based social network and the Movie Lens movie recommendation system reveals that LARS is efficient, scalable, and capable of producing recommendations twice as accurate compared to existing recommendation approaches.",
author = "Levandoski, {Justin J.} and Mohamed Sarwat and Ahmed Eldawy and Mohamed Mokbel",
year = "2012",
month = "7",
day = "30",
doi = "10.1109/ICDE.2012.54",
language = "English",
pages = "450--461",
journal = "Proceedings - International Conference on Data Engineering",
issn = "1084-4627",

}

TY - JOUR

T1 - LARS

T2 - A location-aware recommender system

AU - Levandoski, Justin J.

AU - Sarwat, Mohamed

AU - Eldawy, Ahmed

AU - Mokbel, Mohamed

PY - 2012/7/30

Y1 - 2012/7/30

N2 - This paper proposes LARS, a location-aware recommender system that uses location-based ratings to produce recommendations. Traditional recommender systems do not consider spatial properties of users nor items, LARS, on the other hand, supports a taxonomy of three novel classes of location-based ratings, namely, spatial ratings for non-spatial items, non-spatial ratings for spatial items, and spatial ratings for spatial items. LARS exploits user rating locations through user partitioning, a technique that influences recommendations with ratings spatially close to querying users in a manner that maximizes system scalability while not sacrificing recommendation quality. LARS exploits item locations using travel penalty, a technique that favors recommendation candidates closer in travel distance to querying users in a way that avoids exhaustive access to all spatial items. LARS can apply these techniques separately, or in concert, depending on the type of location-based rating available. Experimental evidence using large-scale real-world data from both the Foursquare location-based social network and the Movie Lens movie recommendation system reveals that LARS is efficient, scalable, and capable of producing recommendations twice as accurate compared to existing recommendation approaches.

AB - This paper proposes LARS, a location-aware recommender system that uses location-based ratings to produce recommendations. Traditional recommender systems do not consider spatial properties of users nor items, LARS, on the other hand, supports a taxonomy of three novel classes of location-based ratings, namely, spatial ratings for non-spatial items, non-spatial ratings for spatial items, and spatial ratings for spatial items. LARS exploits user rating locations through user partitioning, a technique that influences recommendations with ratings spatially close to querying users in a manner that maximizes system scalability while not sacrificing recommendation quality. LARS exploits item locations using travel penalty, a technique that favors recommendation candidates closer in travel distance to querying users in a way that avoids exhaustive access to all spatial items. LARS can apply these techniques separately, or in concert, depending on the type of location-based rating available. Experimental evidence using large-scale real-world data from both the Foursquare location-based social network and the Movie Lens movie recommendation system reveals that LARS is efficient, scalable, and capable of producing recommendations twice as accurate compared to existing recommendation approaches.

UR - http://www.scopus.com/inward/record.url?scp=84864272135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864272135&partnerID=8YFLogxK

U2 - 10.1109/ICDE.2012.54

DO - 10.1109/ICDE.2012.54

M3 - Conference article

SP - 450

EP - 461

JO - Proceedings - International Conference on Data Engineering

JF - Proceedings - International Conference on Data Engineering

SN - 1084-4627

M1 - 6228105

ER -