A Usage-centric Take on Intent Understanding in E-Commerce
This work addresses the problem of improving product recommendations and user profiling in e-commerce, though it appears incremental as it builds on and critiques existing methods.
The paper tackles the problem of inconsistent definitions and benchmarks for user intent understanding in e-commerce by proposing a natural language reasoning approach independent of product ontologies. It identifies weaknesses in the state-of-the-art FolkScope knowledge graph and introduces a Product Recovery Benchmark with a novel evaluation framework and dataset to validate these issues.
Identifying and understanding user intents is a pivotal task for E-Commerce. Despite its essential role in product recommendation and business user profiling analysis, intent understanding has not been consistently defined or accurately benchmarked. In this paper, we focus on predicative user intents as "how a customer uses a product", and pose intent understanding as a natural language reasoning task, independent of product ontologies. We identify two weaknesses of FolkScope, the SOTA E-Commerce Intent Knowledge Graph: category-rigidity and property-ambiguity. They limit its ability to strongly align user intents with products having the most desirable property, and to recommend useful products across diverse categories. Following these observations, we introduce a Product Recovery Benchmark featuring a novel evaluation framework and an example dataset. We further validate the above FolkScope weaknesses on this benchmark. Our code and dataset are available at https://github.com/stayones/Usgae-Centric-Intent-Understanding.