Demand Forecasting Best Practices

Demand Forecasting Best Practices

by Nicolas Vandeput
Released July 2023
Publisher(s): Manning Publications
ISBN: 9781633438095

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Lead your demand planning process to excellence and deliver real value to your supply chain.

In Demand Forecasting Best Practices you’ll learn how to:

  • Lead your team to improve quality while reducing workload
  • Properly define the objectives and granularity of your demand planning
  • Use intelligent KPIs to track accuracy and bias
  • Identify areas for process improvement
  • Help planners and stakeholders add value
  • Determine relevant data to collect and how best to collect it
  • Utilize different statistical and machine learning models

An expert demand forecaster can help an organization avoid overproduction, reduce waste, and optimize inventory levels for a real competitive advantage. Demand Forecasting Best Practices teaches you how to become that virtuoso demand forecaster.

This one-of-a-kind guide reveals forecasting tools, metrics, models, and stakeholder management techniques for delivering more effective supply chains. Everything you learn has been proven and tested in a live business environment. Discover author Nicolas Vandeput’s original five step framework for demand planning excellence and learn how to tailor it to your own company’s needs. Illustrations and real-world examples make each concept easy to understand and easy to follow. You’ll soon be delivering accurate predictions that are driving major business value.

About the Technology
An expert demand forecaster can help an organization avoid overproduction, reduce waste, and optimize inventory levels for a real competitive advantage. This book teaches you how to become that virtuoso demand forecaster.

About the Book
Demand Forecasting Best Practices reveals forecasting tools, metrics, models, and stakeholder management techniques for managing your demand planning process efficiently and effectively. Everything you learn has been proven and tested in a live business environment. Discover author Nicolas Vandeput’s original five step framework for demand planning excellence and learn how to tailor it to your own company’s needs. Illustrations and real-world examples make each concept easy to understand and easy to follow. You’ll soon be delivering accurate predictions that are driving major business value.

What's Inside
  • Enhance forecasting quality while reducing team workload
  • Utilize intelligent KPIs to track accuracy and bias
  • Identify process areas for improvement
  • Assist stakeholders in sales, marketing, and finance
  • Optimize statistical and machine learning models


About the Reader
For demand planners, sales and operations managers, supply chain leaders, and data scientists.

About the Author
Nicolas Vandeput is a supply chain data scientist, the founder of consultancy company SupChains in 2016, and a teacher at CentraleSupélec, France.

Quotes
This new book continues to push the FVA mindset, illustrating practices that drive the efficiency and effectiveness of the business forecasting process.
- Michael Gilliland, Editor-in-Chief, Foresight: Journal of Applied Forecasting

A must-read for any SCM professional, data scientist, or business owner. It's practical, accessible, and packed with valuable insights.
- Edouard Thieuleux, Founder of AbcSupplyChain

An exceptional resource that covers everything from basic forecasting principles to advanced forecasting techniques using artificial intelligence and machine learning. The writing style is engaging, making complex concepts accessible to both beginners and experts.
- Daniel Stanton, Mr. Supply Chain®

Nicolas did it again! Demand Forecasting Best Practices provides practical and actionable advice for improving the demand planning process.
- Professor Spyros Makridakis, The Makridakis Open Forecasting Center, Institute For the Future (IFF), University of Nicosia

This book is now my companion on all of our planning and forecasting projects. A perfect foundation for implementation and also to recommend process improvements.
- Werner Nindl, Chief Architect – CPM Practice Director, Pivotal Drive

This author understands the nuances of forecasting, and is able to explain them well.
- Burhan Ul Haq, Director of Products, Enablers

Both broader and deeper than I expected.
- Maxim Volgin, Quantitative Marketing Manager, KLM

Great book with actionable insights.
- Simon Tschöke, Head of Research, German Edge Cloud

Table of contents

  1. inside front cover
  2. Full quotes from reviewers of Demand Forecasting Best Practices:
  3. Demand Forecasting Best Practices
  4. Copyright
  5. contents
  6. front matter
    1. preface
    2. acknowledgments
    3. about this book
      1. How this book is organized: a roadmap
      2. liveBook discussion forum
    4. about the author
    5. about the cover illustration
  7. Part 1. Forecasting demand
  8. 1 Demand forecasting excellence
    1. 1.1 Why do we forecast demand?
    2. 1.2 Five steps to demand planning excellence
      1. 1.2.1 Objective. What do you need to forecast?
      2. 1.2.2 Data. What data do you need to support your forecasting model and process?
      3. 1.2.3 Metrics. How do you evaluate forecasting quality?
      4. 1.2.4 Baseline model. How do you create an accurate, automated forecast baseline?
      5. 1.2.5 Review Process. How to review the baseline forecast, and who should do it?
    3. Summary
  9. 2 Introduction to demand forecasting
    1. 2.1 Why do we forecast demand?
    2. 2.2 Definitions
      1. 2.2.1 Demand, sales, and supply
      2. 2.2.2 Supply plan, financial budget, and sales targets
    3. Summary
  10. 3 Capturing unconstrained demand (and not sales)
    1. 3.1 Order collection and management
    2. 3.2 Shortage-Censoring and Uncollected Orders
      1. 3.2.1 Using demand drivers to forecast historical demand
    3. 3.3 Substitution and cannibalization
    4. Summary
  11. 4 Collaboration: data sharing and planning alignment
    1. 4.1 How supply chains distort demand information
    2. 4.2 Bullwhip effect
      1. 4.2.1 Order forecasting
      2. 4.2.2 Order batching
      3. 4.2.3 Price fluctuation and promotions
      4. 4.2.4 Shortage gaming
      5. 4.2.5 Lead time variations
    3. 4.3 Collaborative planning
      1. 4.3.1 Internal collaboration
      2. 4.3.2 External collaboration
      3. 4.3.3 Collaborating with your suppliers
    4. Summary
  12. 5 Forecasting hierarchies
    1. 5.1 The three forecasting dimensions
    2. 5.2 Zooming in or out of forecasts
    3. 5.3 How do you select the most appropriate aggregation level?
      1. 5.3.1 Which aggregation level should you focus on?
      2. 5.3.2 What granularity level should you use to create your forecast?
    4. Summary
  13. 6 How long should the forecasting horizon be?
    1. 6.1 Theory: Inventory optimization, lead times, and review periods
    2. 6.2 Reconciling demand forecasting and supply planning
    3. 6.3 Looking further ahead
      1. 6.3.1 Optimal service level and risks
      2. 6.3.2 Collaboration with suppliers
    4. 6.4 Going further: Lost sales vs. backorders
      1. 6.4.1 Lost sales
      2. 6.4.2 Backorders
      3. 6.4.3 Hybrid
    5. Summary
  14. 7 Should we reconcile forecasts to align supply chains?
    1. 7.1 Forecasting granularities requirements
    2. 7.2 One number forecast
    3. 7.3 Different hierarchies . . . different optimal forecasts
      1. 7.3.1 Spot sales and stock clearances
      2. 7.3.2 Product life-cycles
      3. 7.3.3 Example: top-down vs. bottom up
    4. 7.4 One number mindset
    5. Summary
  15. Part 2. Measuring forecasting quality
  16. 8 Forecasting metrics
    1. 8.1 Accuracy and bias
    2. 8.2 Forecast error and bias
      1. 8.2.1 Interpreting and scaling the bias
      2. 8.2.2 Do it yourself
      3. 8.2.3 Insights
    3. 8.3 Mean Absolute Error (MAE)
      1. 8.3.1 Scaling the Mean Absolute Error
      2. 8.3.2 Do it yourself
      3. 8.3.3 Insights
    4. 8.4 Mean Absolute Percentage Error (MAPE)
      1. 8.4.1 Do it yourself
      2. 8.4.2 Insights
    5. 8.5 Root Mean Square Error (RMSE)
      1. 8.5.1 Scaling RMSE
      2. 8.5.2 Do it yourself
      3. 8.5.3 Insights
    6. 8.6 Case study – Part 1
    7. Summary
  17. 9 Choosing the best forecasting KPI
    1. 9.1 Extreme demand patterns
    2. 9.2 Intermittent demand
    3. 9.3 The best forecasting KPI
    4. 9.4 Case study – Part 2
    5. Summary
  18. 10 What is a good forecast error?
    1. 10.1 Benchmarking
      1. 10.1.1 Naïve forecasts
      2. 10.1.2 Moving average
      3. 10.1.3 Seasonal benchmarks
    2. 10.2 Why tracking demand coefficient of variation is not recommended
      1. 10.2.1 COV and simple demand patterns
      2. 10.2.2 COV and realistic demand patterns
    3. Summary
  19. 11 Measuring forecasting accuracy on a product portfolio
    1. 11.1 Forecasting metrics and product portfolios
    2. 11.2 Value-weighted KPIs
    3. Summary
  20. Part 3. Data-driven forecasting process
  21. 12 Forecast value added
    1. 12.1 Comparing your process to a benchmark
      1. 12.1.1 Internal benchmarks
      2. 12.1.2 Industry (external) benchmarks
    2. 12.2 Tracking Forecast Value Added
      1. 12.2.1 Process efficacy
      2. 12.2.2 Process efficiency
      3. 12.2.3 Best practices
      4. 12.2.4 How do you get started?
    3. Summary
  22. 13 What do you review? ABC XYZ segmentations and other methods
    1. 13.1 ABC XYZ segmentations
      1. 13.1.1 ABC analysis
      2. 13.1.2 ABC XYZ analysis
    2. 13.2 Using ABC XYZ for demand forecasting
      1. 13.2.1 Products’ importance
      2. 13.2.2 Products’ forecastability
      3. 13.2.3 ABC XYZ limitations
    3. 13.3 Beyond ABC XYZ: Smart multi-criteria classification
    4. Summary
  23. Part 4. Forecasting methods
  24. 14 Statistical forecasting
    1. 14.1 Time series forecasting
      1. 14.1.1 Demand components: Level, trend, and seasonality
      2. 14.1.2 Setting up time series models
    2. 14.2 Predictive analytics and demand drivers
      1. 14.2.1 Demand drivers
      2. 14.2.2 Challenges
    3. 14.3 Times series forecasting vs. predictive analytics
    4. 14.4 How to select a model
      1. 14.4.1 The 5-step framework
      2. 14.4.2 4-step model creation framework
    5. Summary
  25. 15 Machine learning
    1. 15.1 What is machine learning?
      1. 15.1.1 How does the machine learn?
      2. 15.1.2 Black boxes versus white boxes
    2. 15.2 Main types of learning algorithms
      1. 15.2.1 Short history of machine-learning models
      2. 15.2.2 Tree-based models
      3. 15.2.3 Neural networks
    3. 15.3 What should you expect from ML-driven demand forecasting?
      1. 15.3.1 Forecasting competitions
      2. 15.3.2 Improving the baseline
    4. 15.4 How to launch a machine-learning initiative
    5. Summary
  26. 16 Judgmental forecasting
    1. 16.1 When to use judgmental forecasts?
    2. 16.2 Judgmental biases
      1. 16.2.1 Cognitive biases
      2. 16.2.2 Misalignment of incentives (intentional biases)
      3. 16.2.3 Biased forecasting process
    3. 16.3 Group forecasts
      1. 16.3.1 Wisdom of the crowds
      2. 16.3.2 Assumption-based discussions
    4. Summary
  27. 17 Now it’s your turn!
    1. Closing words
  28. references
  29. index
  30. inside back cover

Product information

  • Title: Demand Forecasting Best Practices
  • Author(s): Nicolas Vandeput
  • Release date: July 2023
  • Publisher(s): Manning Publications
  • ISBN: 9781633438095