KDD 2018 Conventional Tutorial

Data Science in Retail-as-a-Service (RaaS)

Zuo-Jun (Max) Shen, Rong Yuan, Di Wu, Jian Pei
{max.shen, rong.yuan, di.wu, peijian}@jd.com

ABSTRACT

E-commerce has been growing exponentially during the last couple of centuries around the world due to expanding access to the Internet and, more recently, mobile technology. The ability to shop online has transformed how consumers interact with brands and retailers, and how global commerce operates. Recently, more and more companies, including those with strong focuses on technology and AI, are promoting Retail-as-a-Service (RaaS) as a solution to offer customers more intimate and personalized shopping experience. This is achieved by creating a boundaryless shopping experience where customers, goods and shopping environments are more tightly integrated. Data mining and data science are among the core techniques in RaaS. In this tutorial, we will provide an overview of the current best practices of RaaS, and highlight the key contributions that data science has made in the field. We will use real world application examples to demonstrate how data science has changed the shopping experience both online and offline ,and what the future of shopping might be.

TUTOR

Zuo-Jun (Max) Shen(max.shen@jd.com) Chief Scientist, JD.COM American Technologies Corporation Rong Yuan (rong.yuan@jd.com) Research Scientist, JD.COM American Technologies Corporation Di Wu (di.wu@jd.com) Principle Scientist, JD.COM American Technologies Corporation Jian Pei (jian.pei@jd.com) Vice President and Head of Big Data and Smart Supply Chain JD.com
  • Zuo-Jun (Max) Shen
    Zuo-Jun (Max) Shen is the Chief Scientist for supply chain management at JD.com Silicon Valley R&D Center. He is a Professor in the Department of Industrial Engineering and Operations Research and the Department of Civil and Environmental Engineering at University of California, Berkeley. He is also an honorary professor at Tsinghua University and a Center Director at the Tsinghua-Berkeley Institute at Shenzhen. He received his Ph.D. from Northwestern University. He has been active in the following research areas: integrated supply chain design and management, design and analysis of optimization algorithms, energy systems, and transportation system planning and optimization. Dr. Shen has published more than 100 papers in top supply chain management and operations research journals, and is currently on the editorial/advisory board for several leading journals, including Operations Research, Management Science, Manufacturing & Service Operations Management, Production and Operations Management. Dr. Shen received the CAREER award from the National Science Foundation in 2003.
  • Di Wu
    Di Wu is currently a Principal Scientist at JD.com Silicon Valley R&D Center, leading the team in supply chain research. His research covers a variety of key areas in supply chain management such as inventory management, revenue management, fulfillment optimization, contract optimization, and. more. Prior to JD.com, Di gained extensive experience working as research scientist in Amazon.com, with applications in forecasting, transportation network design, fulfillment optimization and pricing optimization. Di received his Ph.D. from University of Florida in Transportation Engineering.
  • Rong Yuan
    Rong Yuan is currently a Research Scientist at JD.com Silicon Valley R&D Center. His focus is on applying optimization and machine learning techniques to various challenges in JD’s supply chain. Prior to JD.com, Rong worked on inventory control and order fulfillment problems at Walmart for its e-commerce business, and warehouse automation at Amazon.com. Rong received his Ph.D. in Operations Research from Massachusetts Institute of Technology. His Ph.D. thesis was among the finalists in George B. Dantzig Dissertation Award 2017.
  • Jian Pei
    Jian Pei is a Vice President of JD.com and head of Big Data and Smart Supply Chain. He has more than 25 years of academic expertise in data research and application, technology industry leadership and corporate management experience. As a professor of Simon Fraser University (on leave), he is a Canada Research Chair (Tier 1) in Big Data Science. Recognized as an ACM Fellow and an IEEE Fellow, he published over 200 technical publications, which have been cited more than 77,000 times, and over 33,900 in the last 5 years. Dr. Pei’s research has generated substantive impact beyond academia, and he has received several prestigious awards, such as the SIGKDD Innovation Award and Service Award, and the ICDM Research Award. He is a Distinguished Visiting Professor of Tsinghua University.

OUTLINE

  • Introduction
    • Retail-as-a-Service: data, algorithms, technologies, scenarios, and services
  • Understand Customers
    • Scenarios of understanding customers
    • Demand forecast in e-commerce
      • Forecast with traditional statistical methods
      • Forecast with machine learning methods
      • Forecast with deep learning methods
    • Deep learning mini-lecture
    • Case Study: JD.com’s multi-horizon probabilistic forecast
  • Connect to Customers
    • Scenarios of connecting to customers
    • Evolution of customer connection
    • Personalization in product recommendation
    • Embedding techniques
    • Case Study: JD.com’s deep online ranking system
  • Serve Customers
    • Scenarios of serving customers
    • Supply chain management under boundaryless retail
      • Inventory placement
      • Inventory replenishment
      • Order fulfillment
    • Case Study: 7Fresh integrated services
  • Conclusion: Data-Driven Retail-as-a-Service
Download