Data Science for Supply Chain Forecasting

by Nicolas Vandeput

Using data science in order to solve a problem requires a scientific mindset more than coding skills. Data Science for Supply Chain Forecasting, Second Edition contends that a true scientific method which includes experimentation, observation, and constant questioning must be applied to supply chains to achieve excellence in demand forecasting.

This second edition adds more than 45 percent extra content with four new chapters including an introduction to neural networks and the forecast value added framework. Part I focuses on statistical "traditional" models, Part II, on machine learning, and the all-new Part III discusses demand forecasting process management. The various chapters focus on both forecast models and new concepts such as metrics, underfitting, overfitting, outliers, feature optimization, and external demand drivers. The book is replete with do-it-yourself sections with implementations provided in Python (and Excel for the statistical models) to show the readers how to apply these models themselves.

This hands-on book, covering the entire range of forecasting—from the basics all the way to leading-edge models—will benefit supply chain practitioners, forecasters, and analysts looking to go the extra mile with demand forecasting.

Events around the book

Link to a De Gruyter Online Event in which the author Nicolas Vandeput together with Stefan de Kok, supply chain innovator and CEO of Wahupa; Spyros Makridakis, professor at the University of Nicosia and director of the Institute For the Future (IFF); and Edouard Thieuleux, founder of AbcSupplyChain, discuss the general issues and challenges of demand forecasting and provide insights into best practices (process, models) and discussing how data science and machine learning impact those forecasts.The event will be moderated by Michael Gilliland, marketing manager for SAS forecasting

310 pages, Kindle Edition

Published March 22, 2021

Reviews

[Walter Ullon · Rating 3 out of 5]

Other than the last couple of pages where the author talks strictly about supply chain issues, how to deal with stakeholders, and specific KPIs he found useful in his vast experience with the subject, I'm really struggling to find anything in the remainder of the book to justify a higher rating.

There's really nothing here that cannot be found in better introductory texts on foresting in general. The application to Supply Chains is basic at best, and the models (while proven and effective) are nothing a data scientist worth his/her salt would not already be familiar with. So while the author makes the case that this is a text aimed at DSs, it's really aimed at junior, excel based analysts/planners looking to get baseline forecasts - there are actual excel recipes for every statistical model.

There's some ML in the second half of the book but very basic and done better elsewhere for those interested in that side of things.

If you are really looking for great resources on your forecasting journey, I can recommend the following (for practitioners, not theorists):
Forecasting:
Advanced Forecasting with Python by Korstanje

Tree Methods:
Hands on Gradient Boosting with XGBOOST and ScikitLearn by Wade

Neural Networks:
1. Hands on Machine Learning with ScikitLearn and Tensorflow by Geron
2. Deep Learning with Python by Chollet

Feature Engineering:
Feature Engineering for Machine Learning by Soledad Galli
(please make sure to check out the UDEMY course as well!)

Feature Selection:
Feature Selection for Machine Learning by Soledad Galli
(please make sure to check out the UDEMY course as well!)

Regression Analysis:
Regression Analysis by Jim Frost

[Ryan · Rating 2 out of 5]

This book provides an introduction to the concept of forecasting as applied to supply chain challenges.

Though the book does occasionally address topics specific to supply chain, more often than not the text can be considered as a general overview on forecasting or time series regression.

I generally cannot recommend the book as I cannot understand the audience the book is trying to address. The coverage of technical topics is uneven, at times being extremely elementary and while other times assuming the reader has a significant amount of prior experience.

As an experienced generalist analytics practitioner hoping to learn some new techniques specific to supply chain, I came away disappointed. That being said, the author’s excitement for the subject area does come through and I am hopeful for improvement in future publications.