Personalized Recommendations Without Inducing Congestion: Mitigating Disparities in the NYC High School Match

2026-10-06

AI Summary

This study addresses the problem that recommendation systems in capacity-constrained markets can induce congestion and exacerbate inequality. Using New York City high school matching as a case study, this work formally defines the phenomenon of recommendation-induced congestion for the first time and proposes a congestion-aware bilevel optimization framework. By integrating market simulation with safety-equilibrium strategies, the approach generates personalized recommendations of programs with high admission probabilities for students, with its effectiveness validated through a randomized controlled trial. The proposed method achieves a 57% increase in recommendation ranking rates and a 71% improvement in match rates, while ensuring no applicant is rejected by any recommended program. These results demonstrate that the framework significantly enhances allocation efficiency while preserving fairness across the market.

Abstract

Algorithmic recommendations can help participants navigate large matching markets. For example, recommendations for school and college choices may reduce information frictions and disparities in access to high-performing programs. At scale, however, recommenders in capacity-constrained settings can be self-defeating: if they steer too many users toward the same items, then even users who were originally predicted to have a high chance of matching to an item may not, due to increased competition. In this paper, we formalize this phenomenon of recommendation-induced congestion; motivated by the NYC high school match, we show that naive recommendations can cause sharp decreases in program acceptance rates, most affecting applicants with the fewest nearby options. Next, we propose and theoretically analyze a congestion-aware, bilevel optimize-and-simulate approach to allocate recommendations and improve match outcomes safely, in equilibrium. Finally, we deploy this approach in the 2025-26 admissions cycle of the NYC high school match, aiming to reduce disparities by highlighting personalized lists of nearby, high-performing programs where an applicant has a high predicted offer likelihood. In a randomized controlled trial, we find that 16.4% of treatment applicants ranked a recommended program, versus 10.5% of control applicants who ranked a program they would have been recommended (57% relative increase; $p$=0.011); 5.6% of treatment applicants matched to such a program, versus 3.3% of control applicants (71% relative increase; $p$=0.071); further, no treatment applicant was rejected from a recommended program. Our findings suggest that recommenders should be analyzed and designed as market-shaping interventions.

Problem

• recommendation-induced congestion
• matching markets
• personalized recommendations
• disparities
• capacity constraints

Innovation

• recommendation-induced congestion
• bilevel optimization
• matching markets
• algorithmic fairness
• randomized controlled trial