Behavioral Feature Boosting via Substitute Relationships for E-commerce Search

TL;DR

This paper introduces a behavior feature boosting method using substitute relationships among products to improve search relevance for new items in e-commerce, effectively mitigating cold-start issues by aggregating behavioral signals from similar products.

Contribution

The paper proposes BFS, a novel method that leverages substitute relationships to enrich behavioral features for cold-start products, enhancing ranking performance.

Findings

Significant offline and online improvements in search relevance.

Enhanced exposure and discovery of new products.

Scalable and practical for large e-commerce platforms.

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.