The PackRec system for travel package recommendation

Roberto Interdonato, Salvatore Romeo, Andrea Tagarelli

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

Abstract

An emerging trend in research on recommender systems is the design of methods capable of recommending packages instead of single items. Most existing works on the topic have focused on a specific application domain, thus often providing ad-hoc solutions that cannot be adapted to other domains. By contrast, in this paper we discuss a versatile package recommendation approach that is substantially independent of the peculiarities of a particular application domain. A key aspect in our framework is the exploitation of prior knowledge on the content type models of the packages being generated that express what the users expect from the recommendation task. Packages are learned for every package model, while the recommendation stage is accomplished by performing a PageRank-style method personalized w.r.t. the target user's preferences, possibly including a limited budget. Our developed method has been tested on the travel package domain using a TripAdvisor dataset.

Original languageEnglish
Title of host publication22nd Italian Symposium on Advanced Database Systems, SEBD 2014
PublisherUniversita Reggio Calabria and Centro di Competenza (ICT-SUD)
Pages327-334
Number of pages8
ISBN (Electronic)9781634391450
Publication statusPublished - 1 Jan 2014
Externally publishedYes
Event22nd Italian Symposium on Advanced Database Systems, SEBD 2014 - Castellammare di Stabia, Italy
Duration: 16 Jun 201418 Jun 2014

Other

Other22nd Italian Symposium on Advanced Database Systems, SEBD 2014
CountryItaly
CityCastellammare di Stabia
Period16/6/1418/6/14

Fingerprint

Recommender systems

ASJC Scopus subject areas

  • Software

Cite this

Interdonato, R., Romeo, S., & Tagarelli, A. (2014). The PackRec system for travel package recommendation. In 22nd Italian Symposium on Advanced Database Systems, SEBD 2014 (pp. 327-334). Universita Reggio Calabria and Centro di Competenza (ICT-SUD).

The PackRec system for travel package recommendation. / Interdonato, Roberto; Romeo, Salvatore; Tagarelli, Andrea.

22nd Italian Symposium on Advanced Database Systems, SEBD 2014. Universita Reggio Calabria and Centro di Competenza (ICT-SUD), 2014. p. 327-334.

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

Interdonato, R, Romeo, S & Tagarelli, A 2014, The PackRec system for travel package recommendation. in 22nd Italian Symposium on Advanced Database Systems, SEBD 2014. Universita Reggio Calabria and Centro di Competenza (ICT-SUD), pp. 327-334, 22nd Italian Symposium on Advanced Database Systems, SEBD 2014, Castellammare di Stabia, Italy, 16/6/14.
Interdonato R, Romeo S, Tagarelli A. The PackRec system for travel package recommendation. In 22nd Italian Symposium on Advanced Database Systems, SEBD 2014. Universita Reggio Calabria and Centro di Competenza (ICT-SUD). 2014. p. 327-334
Interdonato, Roberto ; Romeo, Salvatore ; Tagarelli, Andrea. / The PackRec system for travel package recommendation. 22nd Italian Symposium on Advanced Database Systems, SEBD 2014. Universita Reggio Calabria and Centro di Competenza (ICT-SUD), 2014. pp. 327-334
@inproceedings{a82b859be93a4502846b11fd58b22395,
title = "The PackRec system for travel package recommendation",
abstract = "An emerging trend in research on recommender systems is the design of methods capable of recommending packages instead of single items. Most existing works on the topic have focused on a specific application domain, thus often providing ad-hoc solutions that cannot be adapted to other domains. By contrast, in this paper we discuss a versatile package recommendation approach that is substantially independent of the peculiarities of a particular application domain. A key aspect in our framework is the exploitation of prior knowledge on the content type models of the packages being generated that express what the users expect from the recommendation task. Packages are learned for every package model, while the recommendation stage is accomplished by performing a PageRank-style method personalized w.r.t. the target user's preferences, possibly including a limited budget. Our developed method has been tested on the travel package domain using a TripAdvisor dataset.",
author = "Roberto Interdonato and Salvatore Romeo and Andrea Tagarelli",
year = "2014",
month = "1",
day = "1",
language = "English",
pages = "327--334",
booktitle = "22nd Italian Symposium on Advanced Database Systems, SEBD 2014",
publisher = "Universita Reggio Calabria and Centro di Competenza (ICT-SUD)",

}

TY - GEN

T1 - The PackRec system for travel package recommendation

AU - Interdonato, Roberto

AU - Romeo, Salvatore

AU - Tagarelli, Andrea

PY - 2014/1/1

Y1 - 2014/1/1

N2 - An emerging trend in research on recommender systems is the design of methods capable of recommending packages instead of single items. Most existing works on the topic have focused on a specific application domain, thus often providing ad-hoc solutions that cannot be adapted to other domains. By contrast, in this paper we discuss a versatile package recommendation approach that is substantially independent of the peculiarities of a particular application domain. A key aspect in our framework is the exploitation of prior knowledge on the content type models of the packages being generated that express what the users expect from the recommendation task. Packages are learned for every package model, while the recommendation stage is accomplished by performing a PageRank-style method personalized w.r.t. the target user's preferences, possibly including a limited budget. Our developed method has been tested on the travel package domain using a TripAdvisor dataset.

AB - An emerging trend in research on recommender systems is the design of methods capable of recommending packages instead of single items. Most existing works on the topic have focused on a specific application domain, thus often providing ad-hoc solutions that cannot be adapted to other domains. By contrast, in this paper we discuss a versatile package recommendation approach that is substantially independent of the peculiarities of a particular application domain. A key aspect in our framework is the exploitation of prior knowledge on the content type models of the packages being generated that express what the users expect from the recommendation task. Packages are learned for every package model, while the recommendation stage is accomplished by performing a PageRank-style method personalized w.r.t. the target user's preferences, possibly including a limited budget. Our developed method has been tested on the travel package domain using a TripAdvisor dataset.

UR - http://www.scopus.com/inward/record.url?scp=84914132385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84914132385&partnerID=8YFLogxK

M3 - Conference contribution

SP - 327

EP - 334

BT - 22nd Italian Symposium on Advanced Database Systems, SEBD 2014

PB - Universita Reggio Calabria and Centro di Competenza (ICT-SUD)

ER -