Multistakeholder recommendation with provider constraints

Özge Sürer, Robin Burke, Edward Carl Malthouse

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

4 Citations (Scopus)

Abstract

Recommender systems are typically designed to optimize the utility of the end user. In many settings, however, the end user is not the only stakeholder and this exclusive focus may produce unsatisfactory results for other stakeholders. One such setting is found in multisided platforms, which bring together buyers and sellers. In such platforms, it may be necessary to jointly optimize the value for both buyers and sellers. This paper proposes a constraint-based integer programming optimization model, in which different sets of constraints are used to reflect the goals of the different stakeholders. This model is applied as a post-processing step, so it can easily be added onto an existing recommendation system to make it multistakeholder aware. For computational tractability with larger data sets, we reformulate the integer problem using the Lagrangian dual and use subgradient optimization. In experiments with two data sets, we evaluate empirically the interaction between the utilities of buyers and sellers and show that our approximation can achieve good upper and lower bounds in practical situations.

Original languageEnglish (US)
Title of host publicationRecSys 2018 - 12th ACM Conference on Recommender Systems
PublisherAssociation for Computing Machinery, Inc
Pages54-62
Number of pages9
ISBN (Electronic)9781450359016
DOIs
StatePublished - Sep 27 2018
Event12th ACM Conference on Recommender Systems, RecSys 2018 - Vancouver, Canada
Duration: Oct 2 2018Oct 7 2018

Publication series

NameRecSys 2018 - 12th ACM Conference on Recommender Systems

Other

Other12th ACM Conference on Recommender Systems, RecSys 2018
CountryCanada
CityVancouver
Period10/2/1810/7/18

Fingerprint

Recommender systems
Integer programming
Processing
Experiments

Keywords

  • Constraint-based Recommendation
  • Multisided Platforms
  • Multistakeholder Recommendation

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software

Cite this

Sürer, Ö., Burke, R., & Malthouse, E. C. (2018). Multistakeholder recommendation with provider constraints. In RecSys 2018 - 12th ACM Conference on Recommender Systems (pp. 54-62). (RecSys 2018 - 12th ACM Conference on Recommender Systems). Association for Computing Machinery, Inc. https://doi.org/10.1145/3240323.3240350
Sürer, Özge ; Burke, Robin ; Malthouse, Edward Carl. / Multistakeholder recommendation with provider constraints. RecSys 2018 - 12th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2018. pp. 54-62 (RecSys 2018 - 12th ACM Conference on Recommender Systems).
@inproceedings{6b88db20a0d74ccb968a3023edec6be0,
title = "Multistakeholder recommendation with provider constraints",
abstract = "Recommender systems are typically designed to optimize the utility of the end user. In many settings, however, the end user is not the only stakeholder and this exclusive focus may produce unsatisfactory results for other stakeholders. One such setting is found in multisided platforms, which bring together buyers and sellers. In such platforms, it may be necessary to jointly optimize the value for both buyers and sellers. This paper proposes a constraint-based integer programming optimization model, in which different sets of constraints are used to reflect the goals of the different stakeholders. This model is applied as a post-processing step, so it can easily be added onto an existing recommendation system to make it multistakeholder aware. For computational tractability with larger data sets, we reformulate the integer problem using the Lagrangian dual and use subgradient optimization. In experiments with two data sets, we evaluate empirically the interaction between the utilities of buyers and sellers and show that our approximation can achieve good upper and lower bounds in practical situations.",
keywords = "Constraint-based Recommendation, Multisided Platforms, Multistakeholder Recommendation",
author = "{\"O}zge S{\"u}rer and Robin Burke and Malthouse, {Edward Carl}",
year = "2018",
month = "9",
day = "27",
doi = "10.1145/3240323.3240350",
language = "English (US)",
series = "RecSys 2018 - 12th ACM Conference on Recommender Systems",
publisher = "Association for Computing Machinery, Inc",
pages = "54--62",
booktitle = "RecSys 2018 - 12th ACM Conference on Recommender Systems",

}

Sürer, Ö, Burke, R & Malthouse, EC 2018, Multistakeholder recommendation with provider constraints. in RecSys 2018 - 12th ACM Conference on Recommender Systems. RecSys 2018 - 12th ACM Conference on Recommender Systems, Association for Computing Machinery, Inc, pp. 54-62, 12th ACM Conference on Recommender Systems, RecSys 2018, Vancouver, Canada, 10/2/18. https://doi.org/10.1145/3240323.3240350

Multistakeholder recommendation with provider constraints. / Sürer, Özge; Burke, Robin; Malthouse, Edward Carl.

RecSys 2018 - 12th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2018. p. 54-62 (RecSys 2018 - 12th ACM Conference on Recommender Systems).

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

TY - GEN

T1 - Multistakeholder recommendation with provider constraints

AU - Sürer, Özge

AU - Burke, Robin

AU - Malthouse, Edward Carl

PY - 2018/9/27

Y1 - 2018/9/27

N2 - Recommender systems are typically designed to optimize the utility of the end user. In many settings, however, the end user is not the only stakeholder and this exclusive focus may produce unsatisfactory results for other stakeholders. One such setting is found in multisided platforms, which bring together buyers and sellers. In such platforms, it may be necessary to jointly optimize the value for both buyers and sellers. This paper proposes a constraint-based integer programming optimization model, in which different sets of constraints are used to reflect the goals of the different stakeholders. This model is applied as a post-processing step, so it can easily be added onto an existing recommendation system to make it multistakeholder aware. For computational tractability with larger data sets, we reformulate the integer problem using the Lagrangian dual and use subgradient optimization. In experiments with two data sets, we evaluate empirically the interaction between the utilities of buyers and sellers and show that our approximation can achieve good upper and lower bounds in practical situations.

AB - Recommender systems are typically designed to optimize the utility of the end user. In many settings, however, the end user is not the only stakeholder and this exclusive focus may produce unsatisfactory results for other stakeholders. One such setting is found in multisided platforms, which bring together buyers and sellers. In such platforms, it may be necessary to jointly optimize the value for both buyers and sellers. This paper proposes a constraint-based integer programming optimization model, in which different sets of constraints are used to reflect the goals of the different stakeholders. This model is applied as a post-processing step, so it can easily be added onto an existing recommendation system to make it multistakeholder aware. For computational tractability with larger data sets, we reformulate the integer problem using the Lagrangian dual and use subgradient optimization. In experiments with two data sets, we evaluate empirically the interaction between the utilities of buyers and sellers and show that our approximation can achieve good upper and lower bounds in practical situations.

KW - Constraint-based Recommendation

KW - Multisided Platforms

KW - Multistakeholder Recommendation

UR - http://www.scopus.com/inward/record.url?scp=85056759733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056759733&partnerID=8YFLogxK

U2 - 10.1145/3240323.3240350

DO - 10.1145/3240323.3240350

M3 - Conference contribution

T3 - RecSys 2018 - 12th ACM Conference on Recommender Systems

SP - 54

EP - 62

BT - RecSys 2018 - 12th ACM Conference on Recommender Systems

PB - Association for Computing Machinery, Inc

ER -

Sürer Ö, Burke R, Malthouse EC. Multistakeholder recommendation with provider constraints. In RecSys 2018 - 12th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc. 2018. p. 54-62. (RecSys 2018 - 12th ACM Conference on Recommender Systems). https://doi.org/10.1145/3240323.3240350