CB2CF: A neural multiview content-to-collaborative filtering model for completely cold item recommendations

Oren Barkan; Noam Koenigstein; Eylon Yogev; Ori Katz

doi:10.1145/3298689.3347038

CB2CF: A neural multiview content-to-collaborative filtering model for completely cold item recommendations

Oren Barkan, Noam Koenigstein, Eylon Yogev, Ori Katz

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In Recommender Systems research, algorithms are often characterized as either Collaborative Filtering (CF) or Content Based (CB). CF algorithms are trained using a dataset of user preferences while CB algorithms are typically based on item profiles. These approaches harness different data sources and therefore the resulting recommended items are generally very different. This paper presents the CB2CF, a deep neural multiview model that serves as a bridge from items content into their CF representations. CB2CF is a “real-world” algorithm designed for Microsoft Store services that handle around a billion users worldwide. CB2CF is demonstrated on movies and apps recommendations, where it is shown to outperform an alternative CB model on completely cold items.

Original language	English
Title of host publication	RecSys 2019 - 13th ACM Conference on Recommender Systems
Publisher	Association for Computing Machinery, Inc
Pages	228-236
Number of pages	9
ISBN (Electronic)	9781450362436
DOIs	https://doi.org/10.1145/3298689.3347038
State	Published - 10 Sep 2019
Externally published	Yes
Event	13th ACM Conference on Recommender Systems, RecSys 2019 - Copenhagen, Denmark Duration: 16 Sep 2019 → 20 Sep 2019

Publication series

Name	RecSys 2019 - 13th ACM Conference on Recommender Systems

Conference

Conference	13th ACM Conference on Recommender Systems, RecSys 2019
Country/Territory	Denmark
City	Copenhagen
Period	16/09/19 → 20/09/19

Bibliographical note

Publisher Copyright:
© 2019 Copyright is held by the owner/author(s).

Keywords

Cold item recommendations
Multiview Representation Learning

Access to Document

10.1145/3298689.3347038

Cite this

Barkan, O., Koenigstein, N., Yogev, E., & Katz, O. (2019). CB2CF: A neural multiview content-to-collaborative filtering model for completely cold item recommendations. In RecSys 2019 - 13th ACM Conference on Recommender Systems (pp. 228-236). (RecSys 2019 - 13th ACM Conference on Recommender Systems). Association for Computing Machinery, Inc. https://doi.org/10.1145/3298689.3347038

@inproceedings{bf4c4b7bd9e2435da9e5a6aaf865d910,

title = "CB2CF: A neural multiview content-to-collaborative filtering model for completely cold item recommendations",

abstract = "In Recommender Systems research, algorithms are often characterized as either Collaborative Filtering (CF) or Content Based (CB). CF algorithms are trained using a dataset of user preferences while CB algorithms are typically based on item profiles. These approaches harness different data sources and therefore the resulting recommended items are generally very different. This paper presents the CB2CF, a deep neural multiview model that serves as a bridge from items content into their CF representations. CB2CF is a “real-world” algorithm designed for Microsoft Store services that handle around a billion users worldwide. CB2CF is demonstrated on movies and apps recommendations, where it is shown to outperform an alternative CB model on completely cold items.",

keywords = "Cold item recommendations, Multiview Representation Learning",

author = "Oren Barkan and Noam Koenigstein and Eylon Yogev and Ori Katz",

note = "Publisher Copyright: {\textcopyright} 2019 Copyright is held by the owner/author(s).; 13th ACM Conference on Recommender Systems, RecSys 2019 ; Conference date: 16-09-2019 Through 20-09-2019",

year = "2019",

month = sep,

day = "10",

doi = "10.1145/3298689.3347038",

language = "אנגלית",

series = "RecSys 2019 - 13th ACM Conference on Recommender Systems",

publisher = "Association for Computing Machinery, Inc",

pages = "228--236",

booktitle = "RecSys 2019 - 13th ACM Conference on Recommender Systems",

}

Barkan, O, Koenigstein, N, Yogev, E & Katz, O 2019, CB2CF: A neural multiview content-to-collaborative filtering model for completely cold item recommendations. in RecSys 2019 - 13th ACM Conference on Recommender Systems. RecSys 2019 - 13th ACM Conference on Recommender Systems, Association for Computing Machinery, Inc, pp. 228-236, 13th ACM Conference on Recommender Systems, RecSys 2019, Copenhagen, Denmark, 16/09/19. https://doi.org/10.1145/3298689.3347038

CB2CF: A neural multiview content-to-collaborative filtering model for completely cold item recommendations. / Barkan, Oren; Koenigstein, Noam; Yogev, Eylon et al.
RecSys 2019 - 13th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2019. p. 228-236 (RecSys 2019 - 13th ACM Conference on Recommender Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - CB2CF

T2 - 13th ACM Conference on Recommender Systems, RecSys 2019

AU - Barkan, Oren

AU - Koenigstein, Noam

AU - Yogev, Eylon

AU - Katz, Ori

PY - 2019/9/10

Y1 - 2019/9/10

N2 - In Recommender Systems research, algorithms are often characterized as either Collaborative Filtering (CF) or Content Based (CB). CF algorithms are trained using a dataset of user preferences while CB algorithms are typically based on item profiles. These approaches harness different data sources and therefore the resulting recommended items are generally very different. This paper presents the CB2CF, a deep neural multiview model that serves as a bridge from items content into their CF representations. CB2CF is a “real-world” algorithm designed for Microsoft Store services that handle around a billion users worldwide. CB2CF is demonstrated on movies and apps recommendations, where it is shown to outperform an alternative CB model on completely cold items.

AB - In Recommender Systems research, algorithms are often characterized as either Collaborative Filtering (CF) or Content Based (CB). CF algorithms are trained using a dataset of user preferences while CB algorithms are typically based on item profiles. These approaches harness different data sources and therefore the resulting recommended items are generally very different. This paper presents the CB2CF, a deep neural multiview model that serves as a bridge from items content into their CF representations. CB2CF is a “real-world” algorithm designed for Microsoft Store services that handle around a billion users worldwide. CB2CF is demonstrated on movies and apps recommendations, where it is shown to outperform an alternative CB model on completely cold items.

KW - Cold item recommendations

KW - Multiview Representation Learning

UR - http://www.scopus.com/inward/record.url?scp=85073371298&partnerID=8YFLogxK

U2 - 10.1145/3298689.3347038

DO - 10.1145/3298689.3347038

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85073371298

T3 - RecSys 2019 - 13th ACM Conference on Recommender Systems

SP - 228

EP - 236

BT - RecSys 2019 - 13th ACM Conference on Recommender Systems

PB - Association for Computing Machinery, Inc

Y2 - 16 September 2019 through 20 September 2019

ER -

CB2CF: A neural multiview content-to-collaborative filtering model for completely cold item recommendations

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this