Optimizing Matching Markets with Graph Neural Networks and Reinforcement Learning
Keywords: Graph Neural Networks, Reinforcement Learning, Matching Market, Reciprocal Recommendation Systems
Abstract: This study introduces a novel recommendation system designed for matching markets, such as job placement and online dating, which goes beyond the traditional focus on individual user preferences. Traditional Reciprocal Recommendation Systems in these markets often fail to consider the overall market dynamics, leading to a narrow focus on specific popular choices and neglecting the diversity of user needs. To address this, our approach conceptualizes the market as a network, utilizing Graph Neural Networks to analyze the intricate connections within this network. We also incorporate Reinforcement Learning to optimize outcomes for the entire market, not just individual users. Furthermore, to address the issue of sparse user-item interactions in matching markets, our approach incorporates a novel graph data augmentation technique. This method enriches the network by adding labeled edges, enhancing the market's representation. This augmentation facilitates more effective and varied recommendations, leading to a noticeable increase in successful matches in various market scenarios, as evidenced by our offline experiments with both synthetic and real-world data.
Submission Number: 10
Loading