Rethinking E-Commerce Search
This approach addresses inefficiencies in e-commerce search systems, potentially reducing costs and improving quality, though it appears incremental as it rethinks data handling rather than introducing a new paradigm.
The paper tackles the problem of costly and low-quality conversion of unstructured data for e-commerce search by proposing to convert structured product data into text for integration into LLMs, enabling search and recommendation through Q/A mechanisms instead of traditional methods.
E-commerce search and recommendation usually operate on structured data such as product catalogs and taxonomies. However, creating better search and recommendation systems often requires a large variety of unstructured data including customer reviews and articles on the web. Traditionally, the solution has always been converting unstructured data into structured data through information extraction, and conducting search over the structured data. However, this is a costly approach that often has low quality. In this paper, we envision a solution that does entirely the opposite. Instead of converting unstructured data (web pages, customer reviews, etc) to structured data, we instead convert structured data (product inventory, catalogs, taxonomies, etc) into textual data, which can be easily integrated into the text corpus that trains LLMs. Then, search and recommendation can be performed through a Q/A mechanism through an LLM instead of using traditional information retrieval methods over structured data.