Business forecasting : the emerging role of artificial intelligence and machine learning / edited by Michael Gilliland, Len Tashman, and Udo Sglavo.

Includes index.

Michael Gilliland (Cary, NC) is Marketing Manager for SAS forecasting software, prior to which he held forecasting positions in the food, consumer electronics, and apparel industries. He is the author of several books and writes The Business Forecasting Deal blog (blogs.sas.com/content/forecasting), is Associate Editor of Foresight: The International Journal of Applied Forecasting, and in 2017 received the Lifetime Achievement Award from the Institute of Business Forecasting. He holds a BA in Philosophy from Michigan State University, and master’s degrees in Philosophy and Mathematical Sciences from Johns Hopkins University.

Udo Sglavo (Raleigh, NC) is Director of Forecasting R&D at SAS, where he heads up a team of statisticians and midtier developers working on SAS’s award-winning software for large-scale automatic forecasting. Prior to SAS, he spent more than five years providing and consuming advanced analytical content and solutions to enterprises ranging from Fortune 500 companies to Internet startups. He is a member of the practitioner advisory board of Foresight magazine (International Institute of Forecasters).
Len Tashman (Golden, CO) is Director at the Center for Business Forecasting (CBF), which offers advice and assistance on forecast model building and customized workshops for companies and organizations worldwide. Tashman is Professor Emeritus, University of Vermont, teaching MBA courses in forecasting and decision making; is a member of the Board of Directors of the International Institute of Forecasters (IIF), the world's leading clearinghouse for the publication and dissemination of research on forecasting methods and practices; is a founding and continuing editor of Foresight: The International Journal of Applied Forecasting; and is an editor at Forecast Accuracy Measurement: Pitfalls to Avoid and Practices to Adopt.

Table of contents

Foreword (Spyros Makridakis and Fotios Petropoulos) xi

Preface (Michael Gilliland, Len Tashman, and Udo Sglavo) xv

State of the Art 1

Forecasting in Social Settings: The State of the Art (Spyros Makridakis, Rob J. Hyndman, and Fotios Petropoulos) 1

Chapter 1 Artificial Intelligence and Machine Learning in Forecasting 31

1.1 Deep Learning for Forecasting (Tim Januschowski and colleagues) 32

1.2 Deep Learning for Forecasting: Current Trends and Challenges (Tim Januschowski and Colleagues) 41

1.3 Neural Network--Based Forecasting Strategies (Steven Mills and Susan Kahler) 48

1.4 Will Deep and Machine Learning Solve Our Forecasting Problems? (Stephan Kolassa) 65

1.5 Forecasting the Impact of Artificial Intelligence: The Emerging and Long-Term Future (Spyros Makridakis) 72

Commentary: Spyros Makridakis's Article "Forecasting The Impact Of Artificial Intelligence" (Owen Davies) 80

1.6 Forecasting the Impact of Artificial Intelligence: Another Voice (Lawrence Vanston) 84

Commentary: Response to Lawrence Vanston (Spyros Makridakis) 92

1.7 Smarter Supply Chains through AI (Duncan Klett) 94

1.8 Continual Learning: The Next Generation of Artificial Intelligence (Daniel Philps) 103

1.9 Assisted Demand Planning Using Machine Learning (Charles Chase) 110

1.10 Maximizing Forecast Value Add through Machine Learning and Behavioral Economics (Jeff Baker) 115

1.11 The M4 Forecasting Competition -- Takeaways for the Practitioner (Michael Gilliland) 124

Commentary --The M4 Competition and a Look to the Future (Fotios Petropoulos) 132

Chapter 2 Big Data in Forecasting 135

2.1 Is Big Data the Silver Bullet for Supply-Chain Forecasting? (Shaun Snapp) 136

Commentary: Becoming Responsible Consumers of Big Data (Chris Gray) 142

Commentary: Customer versus Item Forecasting (Michael Gilliland) 146

Commentary: Big Data or Big Hype? (Stephan Kolassa) 148

Commentary: Big Data, a Big Decision (Niels van Hove) 150

Commentary: Big Data and the Internet of Things (Peter Catt) 152

2.2 How Big Data Could Challenge Planning Processes across the Supply Chain (Tonya Boone, Ram Ganeshan, and Nada Sanders) 155

Chapter 3 Forecasting Methods: Modeling, Selection, and Monitoring 163

3.1 Know Your Time Series (Stephan Kolassa and Enno Siemsen) 164

3.2 A Classification of Business Forecasting Problems (Tim Januschowski and Stephan Kolassa) 171

3.3 Judgmental Model Selection (Fotios Petropoulos) 181

Commentary: A Surprisingly Useful Role for Judgment (Paul Goodwin) 192

Commentary: Algorithmic Aversion and Judgmental Wisdom (Nigel Harvey) 194

Commentary: Model Selection in Forecasting Software (Eric Stellwagen) 195

Commentary: Exploit Information from the M4 Competition (Spyros Makridakis) 197

3.4 A Judgment on Judgment (Paul Goodwin) 198

3.5 Could These Recent Findings Improve Your Judgmental Forecasts? (Paul Goodwin) 207

3.6 A Primer on Probabilistic Demand Planning (Stefan de Kok) 211

3.7 Benefits and Challenges of Corporate Prediction Markets (Thomas Wolfram) 215

3.8 Get Your CoV On . . . (Lora Cecere) 225

3.9 Standard Deviation Is Not the Way to Measure Volatility (Steve Morlidge) 230

3.10 Monitoring Forecast Models Using Control Charts (Joe Katz) 232

3.11 Forecasting the Future of Retail Forecasting (Stephan Kolassa) 243 Commentary (Brian Seaman) 255

Chapter 4 Forecasting Performance 259

4.1 Using Error Analysis to Improve Forecast Performance (Steve Morlidge) 260

4.2 Guidelines for Selecting a Forecast Metric (Patrick Bower) 271

4.3 The Quest for a Better Forecast Error Metric: Measuring More Than the Average Error (Stefan de Kok) 277

4.4 Beware of Standard Prediction Intervals from Causal Models (Len Tashman) 290

Chapter 5 Forecasting Process: Communication, Accountability, and S&OP 297

5.1 Not Storytellers But Reporters (Steve Morlidge) 298

5.2 Why Is It So Hard to Hold Anyone Accountable for the Sales Forecast? (Chris Gray) 303

5.3 Communicating the Forecast: Providing Decision Makers with Insights (Alec Finney) 310

5.4 An S&OP Communication Plan: The Final Step in Support of Company Strategy (Niels van Hove) 317

5.5 Communicating Forecasts to the C-Suite: A Six-Step Survival Guide (Todd Tomalak) 325

5.6 How to Identify and Communicate Downturns in Your Business (Larry Lapide) 331

5.7 Common S&OP Change Management Pitfalls to Avoid (Patrick Bower) 338

5.8 Five Steps to Lean Demand Planning (John Hellriegel) 342

5.9 The Move to Defensive Business Forecasting (Michael Gilliland) 346

Afterwords: Essays on Topics in Business Forecasting 351

Observations from a Career Practitioner: Keys to Forecasting Success (Carolyn Allmon) 351

Demand Planning as a Career (Jason Breault) 354

How Did We Get Demand Planning So Wrong? (Lora Cecere) 357

Business Forecasting: Issues, Current State, and Future Direction (Simon Clarke) 358

Statistical Algorithms, Judgment and Forecasting Software Systems (Robert Fildes) 361

The <> for Forecasting (Igor Gusakov) 364

The Future of Forecasting Is Artificial Intelligence Combined with Human Forecasters (Jim Hoover) 367

Quantile Forecasting with Ensembles and Combinations (Rob J. Hyndman) 371

Managing Demand for New Products (Chaman L. Jain) 376

Solving for the Irrational: Why Behavioral Economics Is the Next Big Idea in Demand Planning (Jonathon Karelse) 380

Business Forecasting in Developing Countries (Bahman Rostami-Tabar) 382

Do the Principles of Analytics Apply to Forecasting? (Udo Sglavo) 387

Groupthink on the Topic of AI/ML for Forecasting (Shaun Snapp) 390

Taking Demand Planning Skills to the Next Level (Nicolas Vandeput) 392

Unlock the Potential of Business Forecasting (Eric Wilson) 394

Building a Demand Plan Story for S&OP: The Business Value of Analytics (Dr. Davis Wu) 396

About the Editors 401

Index 403

"Forecasting is the process of making predictions of the future based on past and present data and most commonly by analysis of trends. A commonplace example might be estimation of some variable of interest at some specified future date. Prediction is a similar, but more general term This book provides ideas from the most important and influential authors in the field of forecasting on an array of topics that are highly relevant. It provides multiple perspectives on relevant issues like monitoring forecast performance, forecasting process, communication and accountability for the forecast, the use of big data in forecasting, and the role of AI/ML in enhancing traditional time series forecasting methods. Note: Content is mostly material previously published in "practitioner" journals (Foresight and Journal of Business Forecasting), with a few articles from the academic International Journal of Forecasting. Some articles report on academic research, or include case studies, but most are thoughtful discussion of important business forecasting topics, such as the role of the sales force in forecasting, or the value of judgmental overrides to a statistical forecast, or how to determine what forecast error is "avoidable." Articles were chosen for their importance, influence, informativeness, and for being provocative -- leading the reader to new considerations and ideas"-- Provided by publisher.

Description based on print version record and CIP data provided by publisher; resource not viewed.