Incremental Fairness in Two-Sided Market Platforms: On Smoothly Updating Recommendations

Abstract

Major online platforms today can be thought of as two-sided markets with producers and customers of goods and services. There have been concerns that over-emphasis on customer satisfaction by the platforms may affect the well-being of the producers. To counter such issues, few recent works have attempted to incorporate fairness for the producers. However, these studies have overlooked an important issue in such platforms -- to supposedly improve customer utility, the underlying algorithms are frequently updated, causing abrupt changes in the exposure of producers. In this work, we focus on the fairness issues arising out of such frequent updates, and argue for incremental updates of the platform algorithms so that the producers have enough time to adjust (both logistically and mentally) to the change. However, naive incremental updates may become unfair to the customers. Thus focusing on recommendations deployed on two-sided platforms, we formulate an ILP based online optimization to deploy changes incrementally in η steps, where we can ensure smooth transition of the exposure of items while guaranteeing a minimum utility for every customer. Evaluations over multiple real world datasets show that our proposed mechanism for platform updates can be efficient and fair to both the producers and the customers in two-sided platforms.

Fair Outlier Detection

“…The vast majority of fair machine learning work has focused on supervised learning, especially on classification (e.g., [17,31]). There has also been some recent interest in ensuring fairness within unsupervised learning tasks such as clustering [1], retrieval [32] and recommendations [24]. In this paper, we explore the task of fairness in outlier detection, an analytics task of wide applicability in myriad scenarios.…”

Subgroup Fairness in Two-Sided Markets

“…For instance, travel time prediction [61][62][63], recommendation systems [64][65][66][67]. While the traditional way is to focus on the satisfaction of passengers, drivers' experience in ride hailing platforms is attracting increasing attention, such as discrimination against minorities [13], frequent updates leaving no room for the producers to adjust [68]. To balance between efficiency and fairness, [69] discuss multi-objective ranking and recommendation techniques.…”

Fairness in Network-Friendly Recommendations

“…is the total variation distance between the two distributions, i.e., the average (absolute) change in the content demand [30]. It allows more flexibility than F max in shaping the demand, since it does not impose a constraint for every single content; e.g., a large difference in a content demand can be compensated by small demand differences in other contents.…”