Online Dating Recommendations: Matching Markets and Learning Preferences

TL;DR

This paper introduces a two-sided matching framework for online dating recommendations, utilizing an LDA model to learn user preferences, resulting in significantly improved matching success rates and accurate preference capture.

Contribution

It presents a novel two-sided matching approach combined with an LDA-based preference learning model for online dating systems.

Findings

Two-sided matching increases successful match rate by up to 45%.

LDA model accurately captures user preferences.

Preference learning enhances recommendation effectiveness.

Abstract

Recommendation systems for online dating have recently attracted much attention from the research community. In this paper we proposed a two-side matching framework for online dating recommendations and design an LDA model to learn the user preferences from the observed user messaging behavior and user profile features. Experimental results using data from a large online dating website shows that two-sided matching improves significantly the rate of successful matches by as much as 45%. Finally, using simulated matchings we show that the the LDA model can correctly capture user preferences.