Behavioral Feature Boosting via Substitute Relationships for E-commerce Search

2026-02-16

AI Summary

This work addresses the cold-start problem faced by new products on e-commerce platforms, where sparse user interaction data leads to poor search visibility and suboptimal relevance ranking. To mitigate this challenge, the authors propose a behavior-aware feature augmentation method based on substitute product relationships. By identifying substitute items that fulfill similar user needs, the approach aggregates behavioral signals—including clicks, add-to-cart actions, purchases, and ratings—from these substitutes to construct enriched features for new products. These enhanced features are then integrated into the relevance ranking model. Extensive offline and online experiments on a large-scale e-commerce platform demonstrate significant improvements in both search relevance and exposure for cold-start items. The method has been deployed in production since 2025, effectively enhancing product discoverability and strengthening the platform’s competitive edge.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Search and Optimization: Algorithm Configuration
• Data Mining & Knowledge Management: Recommender Systems

Application Category

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

Abstract

On E-commerce platforms, new products often suffer from the cold-start problem: limited interaction data reduces their search visibility and hurts relevance ranking. To address this, we propose a simple yet effective behavior feature boosting method that leverages substitute relationships among products (BFS). BFS identifies substitutes-products that satisfy similar user needs-and aggregates their behavioral signals (e.g., clicks, add-to-carts, purchases, and ratings) to provide a warm start for new items. Incorporating these enriched signals into ranking models mitigates cold-start effects and improves relevance and competitiveness. Experiments on a large E-commerce platform, both offline and online, show that BFS significantly improves search relevance and product discovery for cold-start products. BFS is scalable and practical, improving user experience while increasing exposure for newly launched items in E-commerce search. The BFS-enhanced ranking model has been launched in production and has served customers since 2025.

Problem

• cold-start
• e-commerce search
• behavioral features
• product visibility
• relevance ranking

Innovation

• cold-start
• substitute relationships
• behavioral feature boosting
• e-commerce search
• relevance ranking