Personalized Context-aware Re-ranking for E-commerce Recommender Systems

Ranking is a core task in E-commerce recommender systems, which aims at providing an ordered list of items to users. Typically, a ranking function is learned from the labeled dataset to optimize the global performance, which produces a ranking score for each individual item. However, it may be sub-optimal because the scoring function applies to each item individually and does not explicitly consider the mutual inƒuence between items, as well as the differences of users’ preferences or intents. Œerefore, we propose a personalized context-aware re-ranking model for E-commerce recommender systems. Œe proposed re-ranking model can be easily deployed as a follow-up modular a‰er ranking by directly using the existing feature vectors of ranking. It directly optimizes the whole recommendation list by employing a transformer structure to eciently encode the information of all items in the list. Specifically, the Transformer applies a self-aŠention mechanism that directly models the global relationships between any pair of items in the whole list. Besides, we introduce the personalized embedding to model the di‚erences between feature distributions for di‚erent users. Experimental results on both o„ine benchmarks and real-world online E-commerce systems demonstrate the signi€cant improvements of the proposed re-ranking model.