SMILE: SeMantic Ids Enhanced CoLd Item Representation for Click-through Rate Prediction in E-commerce SEarch
This addresses the challenge of platform diversity and the Matthew effect for e-commerce platforms by improving cold-start item recommendations, representing an incremental advancement over existing methods.
The paper tackled the problem of insufficient collaborative information for cold-start items in e-commerce search, proposing SMILE to enhance item representation through fused alignment of semantic IDs, which achieved statistically significant improvements including a 1.66% increase in item CTR, 1.57% in buyers, and 2.17% in order volume.
With the rise of modern search and recommendation platforms, insufficient collaborative information of cold-start items exacerbates the Matthew effect of existing platform items, challenging platform diversity and becoming a longstanding issue. Existing methods align items' side content with collaborative information to transfer collaborative signals from high-popularity items to cold-start items. However, these methods fail to account for the asymmetry between collaboration and content, nor the fine-grained differences among items. To address these issues, we propose SMILE, an item representation enhancement approach based on fused alignment of semantic IDs. Specifically, we use RQ-OPQ encoding to quantize item content and collaborative information, followed by a two-step alignment: RQ encoding transfers shared collaborative signals across items, while OPQ encoding learns differentiated information of items. Comprehensive offline experiments on large-scale industrial datasets demonstrate superiority of SMILE, and rigorous online A/B tests confirm statistically significant improvements: item CTR +1.66%, buyers +1.57%, and order volume +2.17%.