Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Information Discovery in e-Commerce

Zhaochun Ren, Xiangnan He, Dawei Yin, Maarten de Rijke

TL;DR

This survey comprehensively maps Information Discovery in e-commerce, detailing how search, recommendation, QA, and conversational AI collaborate with user modeling and interface design to enable efficient product discovery. It presents a unified framework covering data modalities, evaluation metrics, and a two-stage pipeline for recommendation, while highlighting emerging directions such as graph-based user modeling, multi-modal and generative retrieval, and large language model integration. Its contributions include a systematic taxonomy of tasks, standardized notation for cross-model comparisons, and an extensive dataset inventory to support reproducible research. The work is significant for practitioners and researchers aiming to optimize GMV-driven e-commerce experiences through integrated IR and language technologies, with emphasis on fairness, explainability, and privacy in future deployments.

Abstract

Electronic commerce, or e-commerce, is the buying and selling of goods and services, or the transmitting of funds or data online. E-commerce platforms come in many kinds, with global players such as Amazon, Airbnb, Alibaba, eBay and platforms targeting specific geographic regions. Information retrieval has a natural role to play in e-commerce, especially in connecting people to goods and services. Information discovery in e-commerce concerns different types of search (e.g., exploratory search vs. lookup tasks), recommender systems, and natural language processing in e-commerce portals. The rise in popularity of e-commerce sites has made research on information discovery in e-commerce an increasingly active research area. This is witnessed by an increase in publications and dedicated workshops in this space. Methods for information discovery in e-commerce largely focus on improving the effectiveness of e-commerce search and recommender systems, on enriching and using knowledge graphs to support e-commerce, and on developing innovative question answering and bot-based solutions that help to connect people to goods and services. In this survey, an overview is given of the fundamental infrastructure, algorithms, and technical solutions for information discovery in e-commerce. The topics covered include user behavior and profiling, search, recommendation, and language technology in e-commerce.

Information Discovery in e-Commerce

TL;DR

This survey comprehensively maps Information Discovery in e-commerce, detailing how search, recommendation, QA, and conversational AI collaborate with user modeling and interface design to enable efficient product discovery. It presents a unified framework covering data modalities, evaluation metrics, and a two-stage pipeline for recommendation, while highlighting emerging directions such as graph-based user modeling, multi-modal and generative retrieval, and large language model integration. Its contributions include a systematic taxonomy of tasks, standardized notation for cross-model comparisons, and an extensive dataset inventory to support reproducible research. The work is significant for practitioners and researchers aiming to optimize GMV-driven e-commerce experiences through integrated IR and language technologies, with emphasis on fairness, explainability, and privacy in future deployments.

Abstract

Electronic commerce, or e-commerce, is the buying and selling of goods and services, or the transmitting of funds or data online. E-commerce platforms come in many kinds, with global players such as Amazon, Airbnb, Alibaba, eBay and platforms targeting specific geographic regions. Information retrieval has a natural role to play in e-commerce, especially in connecting people to goods and services. Information discovery in e-commerce concerns different types of search (e.g., exploratory search vs. lookup tasks), recommender systems, and natural language processing in e-commerce portals. The rise in popularity of e-commerce sites has made research on information discovery in e-commerce an increasingly active research area. This is witnessed by an increase in publications and dedicated workshops in this space. Methods for information discovery in e-commerce largely focus on improving the effectiveness of e-commerce search and recommender systems, on enriching and using knowledge graphs to support e-commerce, and on developing innovative question answering and bot-based solutions that help to connect people to goods and services. In this survey, an overview is given of the fundamental infrastructure, algorithms, and technical solutions for information discovery in e-commerce. The topics covered include user behavior and profiling, search, recommendation, and language technology in e-commerce.
Paper Structure (106 sections, 24 equations, 41 figures, 1 table)

This paper contains 106 sections, 24 equations, 41 figures, 1 table.

Table of Contents

  1. Introduction
  2. Motivation
  3. Aims of this survey
  4. Outline
  5. Topics covered
  6. Topics not covered
  7. Structure of the survey
  8. Our readers
  9. Definitions and background
  10. Background
  11. User modeling
  12. Information retrieval in e-commerce
  13. Conversational AI
  14. E-commerce presentations and users
  15. E-commerce presentations
  16. ...and 91 more sections

Figures (41)

  • Figure 1: Four types of e-commerce businesses examples. Image sources: Alibaba.com, Amazon.com, UpWork.com, and EBay.com.
  • Figure 2: Illustration of a sample search session in an e-commerce platform. The query is "rosy wedding dress," and the search result page is shown on the left and a portion of the item page for two items is shown on the right. This search session consists of two stages: (i) selecting an item to click from a ranked list, and (ii) deciding whether to purchase the item by reading its detailed description. Image source: wu2018turning.
  • Figure 3: E-commerce recommendation scenarios in Taobao. The areas highlighted with dashed rectangles are personalized for users. Images and textual descriptions are also generated for better user experience. Image source: wang2018billion.
  • Figure 4: Recommendation results exposed to users in three e-commerce platforms. Image sources: JD.com, Amazon.com, and Tmall.com.
  • Figure 5: Given a query "floral-dress long sleeve women" on Tmall, the complete title cannot be displayed in the search result page unless the user proceeds to the detail page further. Image source: wang2018multi.
  • ...and 36 more figures