A multistakeholder recommender systems algorithm for allocating sponsored recommendations

Edward Carl Malthouse, Khadija Ali Vakeel, Yasaman Kamyab Hessary, Robin Burke, Morana Fudurić

Research output: Contribution to journalConference article

Abstract

Retailing and social media platforms recommend two types of items to their users: sponsored items that generate ad revenue and non-sponsored ones that do not. The platform selects sponsored items to maximize ad revenue, often through some form of programmatic auction, and non-sponsored items to maximize user utility with a recommender system (RS). We develop a multiobjective binary integer programming model to allocate sponsored recommendations considering a dual objective of maximizing ad revenue and user utility. We propose an algorithm to solve it in a computationally efficient way. Our method can be applied as a form of post processing to an existing RS, making it widely applicable. We apply the model to data from an online grocery retailer and show that user utility for the recommended items can be improved while reducing ad revenue by a small amount. This multiobjective approach, which unifies programmatic advertising and RS, opens a new frontier for advertising and RS research and we therefore provide an extended discussion of future research topics.

Original languageEnglish (US)
JournalCEUR Workshop Proceedings
Volume2440
StatePublished - Jan 1 2019
Event2019 Workshop on Recommendation in Multi-Stakeholder Environments, RMSE 2019 - Copenhagen, Denmark
Duration: Sep 20 2019 → …

Fingerprint

Recommender systems
Marketing
Integer programming
Processing

Keywords

  • Multistakeholder
  • Platforms
  • Recommender systems
  • Sponsored content
  • Sponsored recommendations

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Malthouse, Edward Carl ; Vakeel, Khadija Ali ; Hessary, Yasaman Kamyab ; Burke, Robin ; Fudurić, Morana. / A multistakeholder recommender systems algorithm for allocating sponsored recommendations. In: CEUR Workshop Proceedings. 2019 ; Vol. 2440.
@article{994ec7208d234c049f4ce1de9763798f,
title = "A multistakeholder recommender systems algorithm for allocating sponsored recommendations",
abstract = "Retailing and social media platforms recommend two types of items to their users: sponsored items that generate ad revenue and non-sponsored ones that do not. The platform selects sponsored items to maximize ad revenue, often through some form of programmatic auction, and non-sponsored items to maximize user utility with a recommender system (RS). We develop a multiobjective binary integer programming model to allocate sponsored recommendations considering a dual objective of maximizing ad revenue and user utility. We propose an algorithm to solve it in a computationally efficient way. Our method can be applied as a form of post processing to an existing RS, making it widely applicable. We apply the model to data from an online grocery retailer and show that user utility for the recommended items can be improved while reducing ad revenue by a small amount. This multiobjective approach, which unifies programmatic advertising and RS, opens a new frontier for advertising and RS research and we therefore provide an extended discussion of future research topics.",
keywords = "Multistakeholder, Platforms, Recommender systems, Sponsored content, Sponsored recommendations",
author = "Malthouse, {Edward Carl} and Vakeel, {Khadija Ali} and Hessary, {Yasaman Kamyab} and Robin Burke and Morana Fudurić",
year = "2019",
month = "1",
day = "1",
language = "English (US)",
volume = "2440",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

A multistakeholder recommender systems algorithm for allocating sponsored recommendations. / Malthouse, Edward Carl; Vakeel, Khadija Ali; Hessary, Yasaman Kamyab; Burke, Robin; Fudurić, Morana.

In: CEUR Workshop Proceedings, Vol. 2440, 01.01.2019.

Research output: Contribution to journalConference article

TY - JOUR

T1 - A multistakeholder recommender systems algorithm for allocating sponsored recommendations

AU - Malthouse, Edward Carl

AU - Vakeel, Khadija Ali

AU - Hessary, Yasaman Kamyab

AU - Burke, Robin

AU - Fudurić, Morana

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Retailing and social media platforms recommend two types of items to their users: sponsored items that generate ad revenue and non-sponsored ones that do not. The platform selects sponsored items to maximize ad revenue, often through some form of programmatic auction, and non-sponsored items to maximize user utility with a recommender system (RS). We develop a multiobjective binary integer programming model to allocate sponsored recommendations considering a dual objective of maximizing ad revenue and user utility. We propose an algorithm to solve it in a computationally efficient way. Our method can be applied as a form of post processing to an existing RS, making it widely applicable. We apply the model to data from an online grocery retailer and show that user utility for the recommended items can be improved while reducing ad revenue by a small amount. This multiobjective approach, which unifies programmatic advertising and RS, opens a new frontier for advertising and RS research and we therefore provide an extended discussion of future research topics.

AB - Retailing and social media platforms recommend two types of items to their users: sponsored items that generate ad revenue and non-sponsored ones that do not. The platform selects sponsored items to maximize ad revenue, often through some form of programmatic auction, and non-sponsored items to maximize user utility with a recommender system (RS). We develop a multiobjective binary integer programming model to allocate sponsored recommendations considering a dual objective of maximizing ad revenue and user utility. We propose an algorithm to solve it in a computationally efficient way. Our method can be applied as a form of post processing to an existing RS, making it widely applicable. We apply the model to data from an online grocery retailer and show that user utility for the recommended items can be improved while reducing ad revenue by a small amount. This multiobjective approach, which unifies programmatic advertising and RS, opens a new frontier for advertising and RS research and we therefore provide an extended discussion of future research topics.

KW - Multistakeholder

KW - Platforms

KW - Recommender systems

KW - Sponsored content

KW - Sponsored recommendations

UR - http://www.scopus.com/inward/record.url?scp=85072737058&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072737058&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85072737058

VL - 2440

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -