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

TL;DR

This study introduces CUPID, a novel approach to session-based reciprocal recommendation systems designed for a real-time one-on-one social discovery platform that reduces response latency by more than 76% compared to non-asynchronous systems, while significantly improving user engagement.

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.

Figures (5)

• Figure 1: Difference between (a) conventional session-based recommendations and (b) session-based reciprocal recommendations for real-time social discovery. The representation of the earmuffs remains unchanged for both Alice and Bob. In contrast, on real-time platforms, user representations continuously evolve with each session. For instance, after Carol interacts with both Alice and Bob, her representation changes based on the timing of these interactions. When Bob pairs with Carol, her representation now reflects her previous interaction with Alice.
• Figure 2: System design consideration. (a) The overall latency of the session-based recommendation pipeline largely depends on the computational time of user session modeling (session embedding layer). (b) Our recommendation system, Cupid, reduces the latency of the recommendation pipeline by asynchronously conducting user session modeling in parallel with the pipeline.
• Figure 3: An overview of Cupid architecture. The user $u_i$'s features $X_i$ and session information $S_i$ are modeled into the user feature representation $\mathbf{e}^u_i$ and the session representation $\mathbf{e}^s_i$ via the user feature embedding layer $f_u$ and the session embedding layer $f_s$, respectively. The session representation is asynchronously computed and stored in the embedding memory $E$.
• Figure 4: (Left): True chat duration distribution. (Right): Predicted chat duration with and without exponential transform.
• Figure 5: Offline evaluation results on four types of matches.