Fair Reciprocal Recommendation in Matching Markets

TL;DR

This paper explores reciprocal recommendation in two-sided matching markets, aiming to balance maximizing matches with fairness of opportunity using envy-freeness and Nash social welfare, validated on synthetic and real data.

Contribution

It introduces a novel method to approximate envy-free recommendations in reciprocal matching markets, balancing match maximization and fairness.

Findings

Heuristic algorithms often cause unfairness despite high match rates.

The proposed approach improves fairness while maintaining high expected matches.

Experimental results confirm effectiveness on synthetic and real datasets.

Abstract

Recommender systems play an increasingly crucial role in shaping people's opportunities, particularly in online dating platforms. It is essential from the user's perspective to increase the probability of matching with a suitable partner while ensuring an appropriate level of fairness in the matching opportunities. We investigate reciprocal recommendation in two-sided matching markets between agents divided into two sides. In our model, a match is considered successful only when both individuals express interest in each other. Additionally, we assume that agents prefer to appear prominently in the recommendation lists presented to those on the other side. We define each agent's opportunity to be recommended and introduce its fairness criterion, envy-freeness, from the perspective of fair division theory. The recommendations that approximately maximize the expected number of matches, empirically obtained by heuristic algorithms, are likely to result in significant unfairness of opportunity. Therefore, there can be a trade-off between maximizing the expected matches and ensuring fairness of opportunity. To address this challenge, we propose a method to find a policy that is close to being envy-free by leveraging the Nash social welfare function. Experiments on synthetic and real-world datasets demonstrate the effectiveness of our approach in achieving both relatively high expected matches and fairness for opportunities of both sides in reciprocal recommender systems.