Where to go on your next trip?: Optimizing travel destinations based on user preferences

Y. Kiseleva, M.J.I. Mueller, L. Bernardi, C. Davis, I. Kovacek, M.S. Einarsen, J. Kamps, A. Tuzhilin, D. Hiemstra

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

8 Citations (Scopus)
1 Downloads (Pure)

Abstract

Recommendation based on user preferences is a common task for e-commerce websites. New recommendation algorithms are often evaluated by offline comparison to baseline algorithms such as recommending random or the most popular items. Here, we investigate how these algorithms themselves perform and compare to the operational production system in large scale online experiments in a real-world application. Specifically, we focus on recommending travel destinations at Booking.com, a major online travel site, to users searching for their preferred vacation activities. To build ranking models we use multi-criteria rating data provided by previous users after their stay at a destination. We implement three methods and compare them to the current baseline in Booking.com: random, most popular, and Naive Bayes. Our general conclusion is that, in an online A/B test with live users, our Naive-Bayes based ranker increased user engagement significantly over the current online system.
Original languageEnglish
Title of host publication38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'15, Santiago, Chile, August 9-13, 2015)
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Pages1097-1100
ISBN (Print)978-1-4503-3621-5
DOIs
Publication statusPublished - 2015

Fingerprint

Online systems
Websites
Experiments

Cite this

Kiseleva, Y., Mueller, M. J. I., Bernardi, L., Davis, C., Kovacek, I., Einarsen, M. S., ... Hiemstra, D. (2015). Where to go on your next trip?: Optimizing travel destinations based on user preferences. In 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'15, Santiago, Chile, August 9-13, 2015) (pp. 1097-1100). New York: Association for Computing Machinery, Inc. https://doi.org/10.1145/2766462.2776777
Kiseleva, Y. ; Mueller, M.J.I. ; Bernardi, L. ; Davis, C. ; Kovacek, I. ; Einarsen, M.S. ; Kamps, J. ; Tuzhilin, A. ; Hiemstra, D. / Where to go on your next trip?: Optimizing travel destinations based on user preferences. 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'15, Santiago, Chile, August 9-13, 2015). New York : Association for Computing Machinery, Inc, 2015. pp. 1097-1100
@inproceedings{7649d94a52d94a82847f55f9a506882f,
title = "Where to go on your next trip?: Optimizing travel destinations based on user preferences",
abstract = "Recommendation based on user preferences is a common task for e-commerce websites. New recommendation algorithms are often evaluated by offline comparison to baseline algorithms such as recommending random or the most popular items. Here, we investigate how these algorithms themselves perform and compare to the operational production system in large scale online experiments in a real-world application. Specifically, we focus on recommending travel destinations at Booking.com, a major online travel site, to users searching for their preferred vacation activities. To build ranking models we use multi-criteria rating data provided by previous users after their stay at a destination. We implement three methods and compare them to the current baseline in Booking.com: random, most popular, and Naive Bayes. Our general conclusion is that, in an online A/B test with live users, our Naive-Bayes based ranker increased user engagement significantly over the current online system.",
author = "Y. Kiseleva and M.J.I. Mueller and L. Bernardi and C. Davis and I. Kovacek and M.S. Einarsen and J. Kamps and A. Tuzhilin and D. Hiemstra",
year = "2015",
doi = "10.1145/2766462.2776777",
language = "English",
isbn = "978-1-4503-3621-5",
pages = "1097--1100",
booktitle = "38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'15, Santiago, Chile, August 9-13, 2015)",
publisher = "Association for Computing Machinery, Inc",
address = "United States",

}

Kiseleva, Y, Mueller, MJI, Bernardi, L, Davis, C, Kovacek, I, Einarsen, MS, Kamps, J, Tuzhilin, A & Hiemstra, D 2015, Where to go on your next trip?: Optimizing travel destinations based on user preferences. in 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'15, Santiago, Chile, August 9-13, 2015). Association for Computing Machinery, Inc, New York, pp. 1097-1100. https://doi.org/10.1145/2766462.2776777

Where to go on your next trip?: Optimizing travel destinations based on user preferences. / Kiseleva, Y.; Mueller, M.J.I.; Bernardi, L.; Davis, C.; Kovacek, I.; Einarsen, M.S.; Kamps, J.; Tuzhilin, A.; Hiemstra, D.

38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'15, Santiago, Chile, August 9-13, 2015). New York : Association for Computing Machinery, Inc, 2015. p. 1097-1100.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Where to go on your next trip?: Optimizing travel destinations based on user preferences

AU - Kiseleva, Y.

AU - Mueller, M.J.I.

AU - Bernardi, L.

AU - Davis, C.

AU - Kovacek, I.

AU - Einarsen, M.S.

AU - Kamps, J.

AU - Tuzhilin, A.

AU - Hiemstra, D.

PY - 2015

Y1 - 2015

N2 - Recommendation based on user preferences is a common task for e-commerce websites. New recommendation algorithms are often evaluated by offline comparison to baseline algorithms such as recommending random or the most popular items. Here, we investigate how these algorithms themselves perform and compare to the operational production system in large scale online experiments in a real-world application. Specifically, we focus on recommending travel destinations at Booking.com, a major online travel site, to users searching for their preferred vacation activities. To build ranking models we use multi-criteria rating data provided by previous users after their stay at a destination. We implement three methods and compare them to the current baseline in Booking.com: random, most popular, and Naive Bayes. Our general conclusion is that, in an online A/B test with live users, our Naive-Bayes based ranker increased user engagement significantly over the current online system.

AB - Recommendation based on user preferences is a common task for e-commerce websites. New recommendation algorithms are often evaluated by offline comparison to baseline algorithms such as recommending random or the most popular items. Here, we investigate how these algorithms themselves perform and compare to the operational production system in large scale online experiments in a real-world application. Specifically, we focus on recommending travel destinations at Booking.com, a major online travel site, to users searching for their preferred vacation activities. To build ranking models we use multi-criteria rating data provided by previous users after their stay at a destination. We implement three methods and compare them to the current baseline in Booking.com: random, most popular, and Naive Bayes. Our general conclusion is that, in an online A/B test with live users, our Naive-Bayes based ranker increased user engagement significantly over the current online system.

U2 - 10.1145/2766462.2776777

DO - 10.1145/2766462.2776777

M3 - Conference contribution

SN - 978-1-4503-3621-5

SP - 1097

EP - 1100

BT - 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'15, Santiago, Chile, August 9-13, 2015)

PB - Association for Computing Machinery, Inc

CY - New York

ER -

Kiseleva Y, Mueller MJI, Bernardi L, Davis C, Kovacek I, Einarsen MS et al. Where to go on your next trip?: Optimizing travel destinations based on user preferences. In 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'15, Santiago, Chile, August 9-13, 2015). New York: Association for Computing Machinery, Inc. 2015. p. 1097-1100 https://doi.org/10.1145/2766462.2776777