Rethinking E-Commerce Search

TL;DR

This paper proposes a novel approach for e-commerce search by converting structured data into text to leverage large language models for improved search and recommendation, bypassing traditional structured data methods.

Contribution

It introduces a paradigm shift by transforming structured data into textual form to enable LLM-based search and recommendation in e-commerce.

Findings

Enables search via LLMs without traditional IR methods

Improves integration of unstructured data in e-commerce search

Reduces costs associated with data structuring

Abstract

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.