Research

Honest Ratings Aren’t Enough: How Rater Mix Variation Impacts Suppliers and Hurts Platforms (with Tristan Botelho, K. Sudhir)

Customer reviews and ratings are critical for the success of online platforms in that they help consumers make choices by reducing uncertainty and motivate supplier (worker) incentives. Existing literature has shown that rating systems face problems primarily due to fake or discriminatory reviews. However, customers also differ in their rating styles – some are generous and others are harsh. In this paper, we introduce the novel idea: even if raters are honest and unbiased, differences in the early rater mix (of generous and harsh raters) for a supplier can lead to biased ratings and unfair outcomes for suppliers. This is because platforms display past ratings to customers whose own ratings and acceptance of suppliers are impacted by it; and platform uses the past ratings for its prioritization and recommendations. These lead to the path dependence. Using data from a gig-economy platform, we estimate a structural model to analyze how early ratings affect long-term worker ratings and earnings. Our findings reveal that early ratings significantly impact future ratings leading to persistent advantages for early lucky workers and disadvantages for unlucky ones. Further, the use of these ratings in the platform’s prioritization algorithms magnify these effects. We propose a neutral adjusted rating metric that can mitigate these effects. Counterfactuals show that using the metric enhances the accuracy of rating systems for customers, fairness in earnings for workers, and better retention of high quality workers for the platform. The resulting supplier turnover can lead to lower quality supplier mix on platforms.



Can Customer Ratings Amplify Discrimination? Evidence from a Gig Economy Platform (with Tristan Botelho, K. Sudhir)

This paper investigates the conjecture that rating systems can lead to discriminatory spillovers and become  "discrimination amplifiers". Because rating systems memorialize differences in individual ratings (impacted by group-based statistical or taste-based discrimination) as differences in worker quality, displaying average ratings on a platform can lead to discrimination spillovers for customers who do not discriminate and amplify discrimination for those who do, leading to greater inequity. After demonstrating the idea using a stylized analytical model, we investigate the question of discrimination amplification empirically using data from an online labor market platform that connects service workers with customer jobs. Using a model of customer's job cancellations and rating choice and allowing for unobserved heterogeneity in discriminatory behaviors, we identify three segments: one shows no difference in behavior towards minority and White workers; the second cancels minority workers at higher rates, hurting minority earnings; a third cancels minorities more and rates them lower than Whites. We find that customer discrimination increases sub-5 star ratings (5 is the highest rating) for the average minority worker by 23%  and decreases earnings by 4%. Displaying ratings amplifies discrimination and increases the minority rating gap in 5 star ratings by 22% and the minority earnings gap by 115% relative to not displaying ratings.

Spatial Distribution of Access to Service: Theory and Evidence from Ride Sharing  (with Soheil Ghili, Vineet Kumar)

This paper studies access to services across geographical regions, using both theoretical and empirical analyses. We model and examine the effects of economies of density in ridesharing markets. Our model predicts that (i) economies of density skew access to rideshareing service away from less dense regions, (ii) the skew will be more pronounced for smaller platforms (i.e., "thinner  markets"), and (iii) rideshare platforms do not find this skew efficient and thus use prices and wages to mitigate (but not eliminate) it. We show that these insights are robust to whether the source of economies of density is the supply-side or the demand-side. We then calibrate our model using ride-level Uber data from New York City. We devise an identification strategy based on relative flows of rides among regions which allows us to infer unobsrevable potential demand in different boroughs. We use the model to simulate counterfactual scenarios providing insights on platform optimal pricing with and without spatial price discrimination, the role of market thickness, the impact of prices/wages on access to rides, and the effects of minimum-wage  regulations on access equity across regions.