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

2026-01-15

AI Summary

This work addresses the challenges of conflicting multi-objective optimization—spanning conversion, browsing, and scrolling—and short-sighted temporal dynamics in full-screen immersive recommendation scenarios within Kuaishou’s e-commerce platform. To this end, we propose STCRank, a novel framework that integrates spatial multi-objective coordination (MOC) with temporal multi-slot coordination (MSC). By leveraging Pareto-front optimization and a two-stage look-ahead ranking mechanism, STCRank enables global ranking optimization across recommendation slots. The proposed method achieves significant improvements in both purchase conversion rate and daily active users, and has been fully deployed across Kuaishou’s e-commerce platform since June 2025.

Technology Category

• Search and Optimization: Algorithm Configuration
• Machine Learning: Learning Preferences or Rankings
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Personalized content ranking and presentation
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems

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.

Problem

• interactive recommender system
• multi-objective conflict
• temporal greedy trap
• spatio-temporal ranking
• sequential recommendation

Innovation

• Spatio-temporal Collaborative Ranking
• Multi-objective Collaboration
• Multi-slot Collaboration
• Interactive Recommender System
• Pareto Frontier Optimization