FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided Platforms

Abstract

We investigate the problem of fair recommendation in the context of two-sided online platforms, comprising customers on one side and producers on the other. 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 reveals that such customer-centric design may lead to unfair distribution of exposure among the producers, which may adversely impact their well-being. On the other hand, a producer-centric design might become unfair to the customers. Thus, we consider fairness issues that span both customers and producers. Our approach involves a novel mapping of the fair recommendation problem to a constrained version of the problem of fairly allocating indivisible goods. Our proposed FairRec algorithm guarantees at least Maximin Share (MMS) of exposure for most of the producers and Envy-Free up to One item (EF1) fairness for every customer. Extensive evaluations over multiple real-world datasets show the effectiveness of FairRec in ensuring two-sided fairness while incurring a marginal loss in the overall recommendation quality. CCS CONCEPTS• Information systems → Recommender systems.

Interplay between upsampling and regularization for provider fairness in recommender systems

“…This will ensure that at least two and one ranking prefixes are used by the re-ranking, where two and one should be the minority items in a top-10 ranking for the datasets, respectively, according to their C a min values. -fair-rec (Patro et al 2020) is a fairness criterion that, while maximizing utility and consumer fairness, aims to guarantee a uniform exposure distribution across providers. The first phase ensures user fairness among all the customers and tries to provide a minimum guarantee on exposure of the providers.…”

“…This percentage increases to 78.7% with fa*ir and to 80.2% with fa*ir fed with the relevance scores returned by real+reg. Finally, given that the total exposure of the platform remains limited to k * |U| , Patro et al (Patro et al 2020) aimed to guarantee that the items of each provider are recommended at least (k * |U|)∕|P| (i.e., this goal refers to the maximin marginal score value for the providers). Under a baseline setting, the percentage of providers that satisfy this criterion is 23.3% .…”

“…Furthermore, Patro et al (Patro et al 2020) account for uniform exposure over providers, while we deal with a relevance proportional to the providers' group contribution. Moreover, their definition assumes that items are not shareable, i.e., no item is allocated to multiple providers.…”

“…Biega et al (Biega et al 2018) solve an integer linear program. Patro et al (Patro et al 2020) implement a greedy-round-robin strategy. Similarly to us, Zehlike and Castillo (Zehlike and Castillo 2020) use stochastic gradient descent, but they operationalize it in a list-wise manner.…”

Towards responsible media recommendation

“…In addition, a dissimilarity metric was proposed to measure the level of diversification and the effectiveness of the underlying algorithm. Another notable work is [78], where the authors proposed a technique that can positively enhance the diversity of a recommender system for different stakeholders, i.e., users (consumers of items) and business (suppliers of items). The technique sets a minimum threshold for the exposure of different items, ensuring that a wider range of suppliers are listed in the recommendations generated for users.…”