TY - JOUR

T1 - Toward Fair Recommendation in Two-sided Platforms

AU - Biswas, Arpita

AU - Patro, Gourab K.

AU - Ganguly, Niloy

AU - Gummadi, Krishna P.

AU - Chakraborty, Abhijnan

N1 - Funding Information: Arpita Biswas and Gourab K. Patro equally contributed to the work. This work was conducted when A. Biswas was a PhD student at the Indian Institute of Science. She gratefully acknowledges the support of a Google PhD Fellowship Award. G. K. Patro acknowledges the support by TCS Research Fellowship. This research was supported in part by an European Research Council (ERC) Advanced Grant for the project “Foundations for Fair Social Computing” (Grant Agreement No. 789373), and an European Research Council (ERC) Marie Sklodowska-Curie grant for the project “NoBIAS—Artificial Intelligence without Bias” (Grant Agreement No. 860630), both funded under the EU’s Horizon 2020. Authors’ addresses: A. Biswas, Harvard University, Science and Engineering Complex, 150 Western Ave, Boston, MA 02134, USA; email: arpita.biswas@live.in; G. K. Patro and N. Ganguly, Indian Institute of Technology Kharagpur, India and L3S Research Center, Appelstrasse 4, Hannover 30167, Germany; emails: patrogourab@gmail.com, ganguly.niloy@gmail.com; K. P. Gummadi, Max Planck Institute for Software Systems, MPI-SWS, Campus E1 5, D-66123 Saarbrücken, Germany; email: gummadi@mpi-sws.org; A. Chakraborty, Indian Institute of Technology, Hauz Khas, New Delhi - 110016, India; email: abhijnan@iitd.ac.in. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. © 2021 Copyright held by the owner/author(s). Publication rights licensed to ACM. 1559-1131/2021/12-ART8 $15.00 https://doi.org/10.1145/3503624

PY - 2022/5

Y1 - 2022/5

N2 - Many online platforms today (such as Amazon, Netflix, Spotify, LinkedIn, and AirBnB) can be thought of as two-sided markets with producers and customers of goods and services. Traditionally, recommendation services in these platforms have focused on maximizing customer satisfaction by tailoring the results according to the personalized preferences of individual customers. However, our investigation reinforces the fact that such customer-centric design of these services may lead to unfair distribution of exposure to the producers, which may adversely impact their well-being. However, a pure producer-centric design might become unfair to the customers. As more and more people are depending on such platforms to earn a living, it is important to ensure fairness to both producers and customers. In this work, by mapping a fair personalized recommendation problem to a constrained version of the problem of fairly allocating indivisible goods, we propose to provide fairness guarantees for both sides. Formally, our proposed FairRec algorithm guarantees Maxi-Min Share of exposure for the producers, and Envy-Free up to One Item fairness for the customers. Extensive evaluations over multiple real-world datasets show the effectiveness of FairRec in ensuring two-sided fairness while incurring a marginal loss in overall recommendation quality. Finally, we present a modification of FairRec (named as FairRecPlus) that at the cost of additional computation time, improves the recommendation performance for the customers, while maintaining the same fairness guarantees.

AB - Many online platforms today (such as Amazon, Netflix, Spotify, LinkedIn, and AirBnB) can be thought of as two-sided markets with producers and customers of goods and services. Traditionally, recommendation services in these platforms have focused on maximizing customer satisfaction by tailoring the results according to the personalized preferences of individual customers. However, our investigation reinforces the fact that such customer-centric design of these services may lead to unfair distribution of exposure to the producers, which may adversely impact their well-being. However, a pure producer-centric design might become unfair to the customers. As more and more people are depending on such platforms to earn a living, it is important to ensure fairness to both producers and customers. In this work, by mapping a fair personalized recommendation problem to a constrained version of the problem of fairly allocating indivisible goods, we propose to provide fairness guarantees for both sides. Formally, our proposed FairRec algorithm guarantees Maxi-Min Share of exposure for the producers, and Envy-Free up to One Item fairness for the customers. Extensive evaluations over multiple real-world datasets show the effectiveness of FairRec in ensuring two-sided fairness while incurring a marginal loss in overall recommendation quality. Finally, we present a modification of FairRec (named as FairRecPlus) that at the cost of additional computation time, improves the recommendation performance for the customers, while maintaining the same fairness guarantees.

KW - Envy-freeness

KW - Fair allocation

KW - Fair recommendation

KW - Maximin share

KW - Multi-stakeholder recommendation

KW - Two-sided markets

UR - http://www.scopus.com/inward/record.url?scp=85131116759&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2201.01180

DO - 10.48550/arXiv.2201.01180

M3 - Article

AN - SCOPUS:85131116759

VL - 16

JO - ACM transactions on the web

JF - ACM transactions on the web

SN - 1559-1131

IS - 2

M1 - 8

ER -