Fair ranking: a critical review, challenges, and future directions

Abstract

Ranking, recommendation, and retrieval systems are widely used in online platforms and other societal systems, including e-commerce, media-streaming, admissions, gig platforms, and hiring. In the recent past, a large "fair ranking" research literature has been developed around making these systems fair to the individuals, providers, or content that are being ranked. Most of this literature defines fairness for a single instance of retrieval, or as a simple additive notion for multiple instances of retrievals over time. This work provides a critical overview of this literature, detailing the often context-specific concerns that such an approach misses: the gap between high ranking placements and true provider utility, spillovers and compounding effects over time, induced strategic incentives, and the effect of statistical uncertainty. We then provide a path forward for a more holistic and impact-oriented fair ranking research agenda, including methodological lessons from other fields and the role of the broader stakeholder community in overcoming data bottlenecks and designing effective regulatory environments.

Online Ranking System Effects on Perceived Fairness: Gender, Income and Education

“…In addition to the issue of bias in online rating systems, there has also been research on the overall fairness of ranking systems on online work platform marketplaces. Some studies have found that the ranking algorithms used by these platforms may favor certain sellers or providers over others, leading to unequal opportunities and outcomes (Elbassuoni et al, 2020a;Patro et al, 2022).…”

“…For example, a study by Patro et al (2022) examined the effects of seller characteristics, such as the seller's reputation and the price of their products or services, on search rankings in an online marketplace. The authors found that these characteristics had a significant impact on search rankings, with sellers with higher reputations and lower prices receiving higher positions in the rankings.…”

“…In addition to the potential for bias in ratings, there are also concerns about the overall fairness of rating systems on online work platform marketplaces (Elbassuoni et al, 2020b). For example, a study by Patro et al (2022) found that the ranking algorithms used by some online marketplaces may favor certain sellers or providers over others, leading to unequal opportunities and outcomes. Another study by Li et al (2021) found that the use of artificial intelligence (AI) in ranking systems can also result in unintended consequences and discrimination, particularly if the training data used to develop the AI algorithms is biased.…”