Centrality-aware Product Retrieval and Ranking

TL;DR

This paper introduces a user-centric product ranking method that improves e-commerce search relevance by optimizing for user intent and centrality, using curated datasets and a dual-loss training approach.

Contribution

It proposes a novel User-intent Centrality Optimization (UCO) method that enhances product ranking by focusing on buyer intent, with curated challenging datasets and dual-loss training.

Findings

Significant improvements in ranking efficiency metrics.

Effective handling of hard negatives in product search.

Enhanced alignment of rankings with user intent.

Abstract

This paper addresses the challenge of improving user experience on e-commerce platforms by enhancing product ranking relevant to users' search queries. Ambiguity and complexity of user queries often lead to a mismatch between the user's intent and retrieved product titles or documents. Recent approaches have proposed the use of Transformer-based models, which need millions of annotated query-title pairs during the pre-training stage, and this data often does not take user intent into account. To tackle this, we curate samples from existing datasets at eBay, manually annotated with buyer-centric relevance scores and centrality scores, which reflect how well the product title matches the users' intent. We introduce a User-intent Centrality Optimization (UCO) approach for existing models, which optimises for the user intent in semantic product search. To that end, we propose a dual-loss based optimisation to handle hard negatives, i.e., product titles that are semantically relevant but do not reflect the user's intent. Our contributions include curating challenging evaluation sets and implementing UCO, resulting in significant product ranking efficiency improvements observed for different evaluation metrics. Our work aims to ensure that the most buyer-centric titles for a query are ranked higher, thereby, enhancing the user experience on e-commerce platforms.