Demand Prediction in Retail

1. Front Matter

   Pages i-xvii

   PDF

2. Introduction

   • Maxime C. Cohen, Paul-Emile Gras, Arthur Pentecoste, Renyu Zhang

   Pages 1-12

3. Data Pre-Processing and Modeling Factors

   • Maxime C. Cohen, Paul-Emile Gras, Arthur Pentecoste, Renyu Zhang

   Pages 13-27

4. Common Demand Prediction Methods

   • Maxime C. Cohen, Paul-Emile Gras, Arthur Pentecoste, Renyu Zhang

   Pages 29-67

5. Tree-Based Methods

   • Maxime C. Cohen, Paul-Emile Gras, Arthur Pentecoste, Renyu Zhang

   Pages 69-92

6. Clustering Techniques

   • Maxime C. Cohen, Paul-Emile Gras, Arthur Pentecoste, Renyu Zhang

   Pages 93-114

7. Evaluation and Visualization

   • Maxime C. Cohen, Paul-Emile Gras, Arthur Pentecoste, Renyu Zhang

   Pages 115-127

8. More Advanced Methods

   • Maxime C. Cohen, Paul-Emile Gras, Arthur Pentecoste, Renyu Zhang

   Pages 129-149

9. Conclusion and Advanced Topics

   • Maxime C. Cohen, Paul-Emile Gras, Arthur Pentecoste, Renyu Zhang

   Pages 151-155

From data collection to evaluation and visualization of prediction results, this book provides a comprehensive overview of the process of predicting demand for retailers. Each step is illustrated with the relevant code and implementation details to demystify how historical data can be leveraged to predict future demand. The tools and methods presented can be applied to most retail settings, both online and brick-and-mortar, such as fashion, electronics, groceries, and furniture.

This book is intended to help students in business analytics and data scientists better master how to leverage data for predicting demand in retail applications. It can also be used as a guide for supply chain practitioners who are interested in predicting demand. It enables readers to understand how to leverage data to predict future demand, how to clean and pre-process the data to make it suitable for predictive analytics, what the common caveats are in terms of implementation and how to assess prediction accuracy.

• demand prediction
• supply chain analytics
• data-driven forecasting
• predictive analytics
• data science and operations
• data-driven decision tools
• business analytics
• predictive modelling

“To remain competitive in today's economy, it is imperative for retailers to undertake a digital transformation. Having demand prediction capabilities is a crucial building block to optimize omnichannel marketing and operations. This book can serve as an invaluable guide on how to leverage data and AI to predict demand and is a must have on the shelf of practitioners in the retail industry.” (Anindya Ghose – Heinz Riehl Chair Professor at NYU Stern School of Business and author of TAP: Unlocking the Mobile Economy) 

“Predicting retail sales does not need to solely rely on experience and intuition anymore. The recent progress in predictive analytics provides great tools to help retailers predict demand. This book is instrumental for retailers who seek to embrace data-driven decision making.” (Georgia Perakis – William F. Pounds Professor at MIT Sloan School of Management) 

“The key to success for many retailers lies in making sure that the right products areavailable at the right time in the right store. Failing to meet this goal may adversely affect customer loyalty and long-term profits. The only way to systematically succeed in this goal at scale is to rely on data and algorithms. This book is very pragmatic and explains how to leverage past data to predict future demand for retailers.” (Aldo Bensadoun, Founder and Executive Chairman of the Aldo Group) 

“End-to-end retail decisions from procurement, capacity/inventory, distribution channel management to pricing and promotions crucially rely on robust demand prediction models, making this book vital for retailers. The content of this book is comprehensive yet remains accessible and actionable. An excellent reference and a must read for data science enthusiasts as well as data science managers who have been changing the retail business as we know it.” (Özalp Özer, Senior Principal Scientist at Amazon, George and Fonsa Brody Professor at UT Dallas, and author of The Oxford Handbook of Pricing Management) 

“For business analytics students and practitioners interested in understanding how to implement statistical demand forecasting models using Python, this book provides an invaluable hands-on approach, with detailed programming examples to guide the reader.” (Gerry Feigin, Partner and Associate Director at BCG GAMMA and author of Supply Chain Planning and Analytics and The Art of Computer Modeling for Business Analytics) 

“Finally a book that methodically demystifies retail demand prediction has arrived. This is a must read for any aspiring scientists looking to apply statistical and machine learning techniques to real-world demand prediction problems, as well as an excellent refresher for practitioners to stay current.” (Nitin Verma, Vice President, Digital Solutions and Chief Scientist at Staples)

• Desautels Faculty of Management, McGill University, Montreal, Canada

  Maxime C. Cohen

• Virtuo Technologies, Paris, France

  Paul-Emile Gras

• Boston Consulting Group GAMMA, New York, USA

  Arthur Pentecoste

• New York University Shanghai, Shanghai, China

  Renyu Zhang

Maxime C. Cohen is a Professor of Retail and Operations Management, Co-Director of the Retail Innovation Lab, and a Bensadoun Faculty Scholar at McGill University, Canada. He is also a Scientific Advisor on AI and Data Science at IVADO Labs and a Scientific Director at the non-profit MyOpenCourt.org. His core expertise lies at the intersection of data science and operations research. He holds a Ph.D. in Operations Research from MIT, USA.

 Paul-Emile Gras is a data scientist at Virtuo Technologies in Paris, France. His expertise is at the interface of demand forecasting and revenue management. Prior to joining Virtuo, he was a research assistant in operations at McGill University, Canada.

 Arthur Pentecoste is a data scientist at the Boston Consulting Group’s New York office, USA. His main scope of expertise is in predictive modelling and analytics applied to demand forecasting and predictive maintenance.

 Renyu Zhang is an Assistant Professor of Operations Management at New York University Shanghai, China. He is also an economist and tech lead at Kuaishou, one of the world’s largest online video-sharing and live-streaming platforms. He is an expert on data science and operations research. He holds a Ph.D. in Operations Management from Washington University in St. Louis, USA.

Policies and ethics