CUPID: A Real-Time Session-Based Reciprocal Recommendation System for a One-on-One Social Discovery Platform

TL;DR

CUPID is a real-time reciprocal recommendation system for social discovery platforms that reduces latency and computational costs by decoupling session modeling from matching and employing a two-phase training strategy.

Contribution

It introduces a novel decoupled, two-phase training approach for session-based reciprocal recommendations in real-time social platforms.

Findings

Reduces response latency by over 76% in real-world tests

Significantly decreases computational burden during training

Improves user engagement in a large-scale social discovery platform

Abstract

This study introduces CUPID, a novel approach to session-based reciprocal recommendation systems designed for a real-time one-on-one social discovery platform. In such platforms, low latency is critical to enhance user experiences. However, conventional session-based approaches struggle with high latency due to the demands of modeling sequential user behavior for each recommendation process. Additionally, given the reciprocal nature of the platform, where users act as items for each other, training recommendation models on large-scale datasets is computationally prohibitive using conventional methods. To address these challenges, CUPID decouples the time-intensive user session modeling from the real-time user matching process to reduce inference time. Furthermore, CUPID employs a two-phase training strategy that separates the training of embedding and prediction layers, significantly reducing the computational burden by decreasing the number of sequential model inferences by several hundredfold. Extensive experiments on large-scale Azar datasets demonstrate CUPID's effectiveness in a real-world production environment. Notably, CUPID reduces response latency by more than 76% compared to non-asynchronous systems, while significantly improving user engagement.