STCRank: Spatio-temporal Collaborative Ranking for Interactive Recommender System at Kuaishou E-shop

TL;DR

STCRank addresses the challenge of integrating multiple objectives (view, swipe-down, conversion) within an immersive interactive recommender system, and the temporal greedy trap across sequential slots. It introduces two modules: Multi-Objective Collaboration (MOC) to mitigate overlaps between $vtr$, $sdr$, and $cvr$ within a slot, and Multi-Slot Collaboration (MSC) to optimize across sequential slots with cross-stage and single-stage look-ahead rankings. The ranking uses an MMOE-based model with a loss $L(\Theta)$ and a linear ensemble $v[j] = w_1 vtr + w_2 cvr + w_3 sdr$. Empirical results on A/B tests show the framework improves IPV and DAU, leading to better engagement and conversions, and the system has been deployed since 2025.6.

Abstract

As a popular e-commerce platform, Kuaishou E-shop provides precise personalized product recommendations to tens of millions of users every day. To better respond real-time user feedback, we have deployed an interactive recommender system (IRS) alongside our core homepage recommender system. This IRS is triggered by user click on homepage, and generates a series of highly relevant recommendations based on the clicked item to meet focused browsing demands. Different from traditional e-commerce RecSys, the full-screen UI and immersive swiping down functionality present two distinct challenges for regular ranking system. First, there exists explicit interference (overlap or conflicts) between ranking objectives, i.e., conversion, view and swipe down. This is because there are intrinsic behavioral co-occurrences under the premise of immersive browsing and swiping down functionality. Second, the ranking system is prone to temporal greedy traps in sequential recommendation slot transitions, which is caused by full-screen UI design. To alleviate these challenges, we propose a novel Spatio-temporal collaborative ranking (STCRank) framework to achieve collaboration between multi-objectives within one slot (spatial) and between multiple sequential recommondation slots. In multi-objective collaboration (MOC) module, we push Pareto frontier by mitigating the objective overlaps and conflicts. In multi-slot collaboration (MSC) module, we achieve global optima on overall sequential slots by dual-stage look-ahead ranking mechanism. Extensive experiments demonstrate our proposed method brings about purchase and DAU co-growth. The proposed system has been already deployed at Kuaishou E-shop since 2025.6.

Figures (2)

• Figure 1: Overview of our interactive e-commerce recommender systems and STCRank framework.
• Figure 2: Overview of MOC module and MSC module.