The continuous cold start problem in e-commerce recommender systems

L. Bernardi, J. Kamps, Y. Kiseleva, M.J.I. Mueller

Research output: Book/ReportReportAcademic

11 Citations (Scopus)
4 Downloads (Pure)

Abstract

Many e-commerce websites use recommender systems to recommend items to users. When a user or item is new, the system may fail because not enough information is available on this user or item. Various solutions to this `cold-start problem' have been proposed in the literature. However, many real-life e-commerce applications suffer from an aggravated, recurring version of cold-start even for known users or items, since many users visit the website rarely, change their interests over time, or exhibit different personas. This paper exposes the `Continuous Cold Start' (CoCoS) problem and its consequences for content- and context-based recommendation from the viewpoint of typical e-commerce applications, illustrated with examples from a major travel recommendation website, Booking.com.
Original languageEnglish
Publishers.n.
Number of pages6
Publication statusPublished - 2015

Publication series

NamearXiv
Volume1508.01177 [cs.IR]

Fingerprint

Recommender systems
Websites

Cite this

Bernardi, L., Kamps, J., Kiseleva, Y., & Mueller, M. J. I. (2015). The continuous cold start problem in e-commerce recommender systems. (arXiv; Vol. 1508.01177 [cs.IR]). s.n.
Bernardi, L. ; Kamps, J. ; Kiseleva, Y. ; Mueller, M.J.I. / The continuous cold start problem in e-commerce recommender systems. s.n., 2015. 6 p. (arXiv).
@book{c2a027f35da64d9184a89187ee84ed6d,
title = "The continuous cold start problem in e-commerce recommender systems",
abstract = "Many e-commerce websites use recommender systems to recommend items to users. When a user or item is new, the system may fail because not enough information is available on this user or item. Various solutions to this `cold-start problem' have been proposed in the literature. However, many real-life e-commerce applications suffer from an aggravated, recurring version of cold-start even for known users or items, since many users visit the website rarely, change their interests over time, or exhibit different personas. This paper exposes the `Continuous Cold Start' (CoCoS) problem and its consequences for content- and context-based recommendation from the viewpoint of typical e-commerce applications, illustrated with examples from a major travel recommendation website, Booking.com.",
author = "L. Bernardi and J. Kamps and Y. Kiseleva and M.J.I. Mueller",
year = "2015",
language = "English",
series = "arXiv",
publisher = "s.n.",

}

Bernardi, L, Kamps, J, Kiseleva, Y & Mueller, MJI 2015, The continuous cold start problem in e-commerce recommender systems. arXiv, vol. 1508.01177 [cs.IR], s.n.

The continuous cold start problem in e-commerce recommender systems. / Bernardi, L.; Kamps, J.; Kiseleva, Y.; Mueller, M.J.I.

s.n., 2015. 6 p. (arXiv; Vol. 1508.01177 [cs.IR]).

Research output: Book/ReportReportAcademic

TY - BOOK

T1 - The continuous cold start problem in e-commerce recommender systems

AU - Bernardi, L.

AU - Kamps, J.

AU - Kiseleva, Y.

AU - Mueller, M.J.I.

PY - 2015

Y1 - 2015

N2 - Many e-commerce websites use recommender systems to recommend items to users. When a user or item is new, the system may fail because not enough information is available on this user or item. Various solutions to this `cold-start problem' have been proposed in the literature. However, many real-life e-commerce applications suffer from an aggravated, recurring version of cold-start even for known users or items, since many users visit the website rarely, change their interests over time, or exhibit different personas. This paper exposes the `Continuous Cold Start' (CoCoS) problem and its consequences for content- and context-based recommendation from the viewpoint of typical e-commerce applications, illustrated with examples from a major travel recommendation website, Booking.com.

AB - Many e-commerce websites use recommender systems to recommend items to users. When a user or item is new, the system may fail because not enough information is available on this user or item. Various solutions to this `cold-start problem' have been proposed in the literature. However, many real-life e-commerce applications suffer from an aggravated, recurring version of cold-start even for known users or items, since many users visit the website rarely, change their interests over time, or exhibit different personas. This paper exposes the `Continuous Cold Start' (CoCoS) problem and its consequences for content- and context-based recommendation from the viewpoint of typical e-commerce applications, illustrated with examples from a major travel recommendation website, Booking.com.

M3 - Report

T3 - arXiv

BT - The continuous cold start problem in e-commerce recommender systems

PB - s.n.

ER -

Bernardi L, Kamps J, Kiseleva Y, Mueller MJI. The continuous cold start problem in e-commerce recommender systems. s.n., 2015. 6 p. (arXiv).