A versatile graph-based approach to package recommendation

Roberto Interdonato, Salvatore Romeo, Andrea Tagarelli, George Karypis

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

15 Citations (Scopus)

Abstract

An emerging trend in research on recommender systems is the design of methods capable of recommending packages instead of single items. The problem is challenging due to a variety of critical aspects, including context-based and user-provided constraints for the items constituting a package, but also the high sparsity and limited accessibility of the primary data used to solve the problem. Most existing works on the topic have focused on a specific application domain (e.g., travel package recommendation), thus often providing ad-hoc solutions that cannot be adapted to other domains. By contrast, in this paper we propose 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 each 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 a TripAdvisor dataset and compared with a recently proposed method for learning composite recommendations.

Original languageEnglish
Title of host publicationProceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013
Pages857-864
Number of pages8
DOIs
Publication statusPublished - 1 Dec 2013
Externally publishedYes
Event25th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2013 - Washington, DC
Duration: 4 Nov 20136 Nov 2013

Other

Other25th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2013
CityWashington, DC
Period4/11/136/11/13

Fingerprint

Recommender systems
Composite materials

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Science Applications

Cite this

Interdonato, R., Romeo, S., Tagarelli, A., & Karypis, G. (2013). A versatile graph-based approach to package recommendation. In Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013 (pp. 857-864). [6735341] https://doi.org/10.1109/ICTAI.2013.130

A versatile graph-based approach to package recommendation. / Interdonato, Roberto; Romeo, Salvatore; Tagarelli, Andrea; Karypis, George.

Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013. 2013. p. 857-864 6735341.

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

Interdonato, R, Romeo, S, Tagarelli, A & Karypis, G 2013, A versatile graph-based approach to package recommendation. in Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013., 6735341, pp. 857-864, 25th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2013, Washington, DC, 4/11/13. https://doi.org/10.1109/ICTAI.2013.130
Interdonato R, Romeo S, Tagarelli A, Karypis G. A versatile graph-based approach to package recommendation. In Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013. 2013. p. 857-864. 6735341 https://doi.org/10.1109/ICTAI.2013.130
Interdonato, Roberto ; Romeo, Salvatore ; Tagarelli, Andrea ; Karypis, George. / A versatile graph-based approach to package recommendation. Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013. 2013. pp. 857-864
@inproceedings{1ccbe5a113fd4972afbbba51df467666,
title = "A versatile graph-based approach to package recommendation",
abstract = "An emerging trend in research on recommender systems is the design of methods capable of recommending packages instead of single items. The problem is challenging due to a variety of critical aspects, including context-based and user-provided constraints for the items constituting a package, but also the high sparsity and limited accessibility of the primary data used to solve the problem. Most existing works on the topic have focused on a specific application domain (e.g., travel package recommendation), thus often providing ad-hoc solutions that cannot be adapted to other domains. By contrast, in this paper we propose 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 each 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 a TripAdvisor dataset and compared with a recently proposed method for learning composite recommendations.",
author = "Roberto Interdonato and Salvatore Romeo and Andrea Tagarelli and George Karypis",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/ICTAI.2013.130",
language = "English",
isbn = "9781479929719",
pages = "857--864",
booktitle = "Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013",

}

TY - GEN

T1 - A versatile graph-based approach to package recommendation

AU - Interdonato, Roberto

AU - Romeo, Salvatore

AU - Tagarelli, Andrea

AU - Karypis, George

PY - 2013/12/1

Y1 - 2013/12/1

N2 - An emerging trend in research on recommender systems is the design of methods capable of recommending packages instead of single items. The problem is challenging due to a variety of critical aspects, including context-based and user-provided constraints for the items constituting a package, but also the high sparsity and limited accessibility of the primary data used to solve the problem. Most existing works on the topic have focused on a specific application domain (e.g., travel package recommendation), thus often providing ad-hoc solutions that cannot be adapted to other domains. By contrast, in this paper we propose 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 each 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 a TripAdvisor dataset and compared with a recently proposed method for learning composite recommendations.

AB - An emerging trend in research on recommender systems is the design of methods capable of recommending packages instead of single items. The problem is challenging due to a variety of critical aspects, including context-based and user-provided constraints for the items constituting a package, but also the high sparsity and limited accessibility of the primary data used to solve the problem. Most existing works on the topic have focused on a specific application domain (e.g., travel package recommendation), thus often providing ad-hoc solutions that cannot be adapted to other domains. By contrast, in this paper we propose 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 each 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 a TripAdvisor dataset and compared with a recently proposed method for learning composite recommendations.

UR - http://www.scopus.com/inward/record.url?scp=84897729813&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897729813&partnerID=8YFLogxK

U2 - 10.1109/ICTAI.2013.130

DO - 10.1109/ICTAI.2013.130

M3 - Conference contribution

SN - 9781479929719

SP - 857

EP - 864

BT - Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013

ER -