[UTMD-124] Integrating Predictive Models into Two-Sided Recommendations: A Matching-Theoretic Approach (by Kazuki Sekiya, Suguru Otani, Yuki Komatsu, Sachio Ohkawa, Shunya Noda)

Kazuki Sekiya, Suguru Otani, Yuki Komatsu, Sachio Ohkawa, Shunya Noda

Two-sided platforms must recommend users to users, where matches (termed dates in this paper) require mutual interest and activity on both sides. Naive ranking by predicted dating probabilities concentrates exposure on a small subset of highly responsive users, generating congestion and overstating efficiency. We model recommendation as a many-to-many matching problem and design integrators that map predicted login, like, and reciprocation probabilities into recommendations under attention constraints. We introduce effective dates, a congestion-adjusted metric that discounts matches involving overloaded receivers. We then propose exposure-constrained deferred acceptance (ECDA), which limits receiver exposure in terms of expected likes or dates rather than headcount. Using production-grade predictions from a large Japanese dating platform, we show in calibrated simulations that ECDA increases effective dates and receiver-side dating probability despite reducing total dates. A large-scale regional field experiment confirms these effects in practice, indicating that exposure control improves equity and early-stage matching efficiency without harming downstream engagement.