Beyond Match Maximization and Fairness: Retention-Optimized Two-Sided Matching

TL;DR

This paper introduces MRet, a dynamic learning-to-rank algorithm designed to maximize user retention on two-sided matching platforms by modeling personalized retention curves and jointly optimizing recommendations.

Contribution

It proposes a novel retention-focused optimization framework and a dynamic algorithm that adapts recommendations to improve overall user retention, surpassing traditional match maximization methods.

Findings

MRet achieves higher user retention in synthetic and real-world datasets.

Traditional methods focusing on match maximization or fairness are less effective for retention.

Empirical results demonstrate the effectiveness of the proposed approach.

Abstract

On two-sided matching platforms such as online dating and recruiting, recommendation algorithms often aim to maximize the total number of matches. However, this objective creates an imbalance, where some users receive far too many matches while many others receive very few and eventually abandon the platform. Retaining users is crucial for many platforms, such as those that depend heavily on subscriptions. Some may use fairness objectives to solve the problem of match maximization. However, fairness in itself is not the ultimate objective for many platforms, as users do not suddenly reward the platform simply because exposure is equalized. In practice, where user retention is often the ultimate goal, casually relying on fairness will leave the optimization of retention up to luck. In this work, instead of maximizing matches or axiomatically defining fairness, we formally define the new problem setting of maximizing user retention in two-sided matching platforms. To this end, we introduce a dynamic learning-to-rank (LTR) algorithm called Matching for Retention (MRet). Unlike conventional algorithms for two-sided matching, our approach models user retention by learning personalized retention curves from each user's profile and interaction history. Based on these curves, MRet dynamically adapts recommendations by jointly considering the retention gains of both the user receiving recommendations and those who are being recommended, so that limited matching opportunities can be allocated where they most improve overall retention. Naturally but importantly, empirical evaluations on synthetic and real-world datasets from a major online dating platform show that MRet achieves higher user retention, since conventional methods optimize matches or fairness rather than retention.