Data Science for Supply Chain Forecasting, 2nd Edition

Length: 280 pages
Edition: 2
Language: English
Publisher: de Gruyter
Publication Date: 2021-03-22
ISBN-10: 3110671107
ISBN-13: 9783110671100
Sales Rank: #173956 (See Top 100 Books)

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.

Title Page
Copyright
Contents
Acknowledgments
    Second Edition
    First Edition
About the Author
Foreword – Second Edition
Foreword – First Edition
Introduction
    Supply Chain Forecasting
    What Is Tomorrow Going to Be Like?
    How to Read This Book
        Old-school Statistics and Machine Learning
        Concepts and Models
        Do It Yourself
        Can I Do This? Is This Book for Me?
    The Data Scientist’s Mindset
    The Data Scientist’s Toolkit
        Excel
        Python
        Python Code Extracts
        Other Resources
Part I Statistical Forecasting
    1 Moving Average
        1.1 Moving Average Model
        1.2 Insights
        1.3 Do It Yourself
    2 Forecast KPI
        2.1 Forecast Error
        2.2 Bias
        2.3 MAPE
        2.4 MAE
        2.5 RMSE
        2.6 Which Forecast KPI to Choose?
    3 Exponential Smoothing
        3.1 The Idea Behind Exponential Smoothing
        3.2 Model
        3.3 Insights
        3.4 Do It Yourself
    4 Underfitting
        4.1 Causes of Underfitting
        4.2 Solutions
    5 Double Exponential Smoothing
        5.1 The Idea Behind Double Exponential Smoothing
        5.2 Double Exponential Smoothing Model
        5.3 Insights
        5.4 Do It Yourself
    6 Model Optimization
        6.1 Excel
        6.2 Python
    7 Double Smoothing with Damped Trend
        7.1 The Idea Behind Double Smoothing with Damped Trend
        7.2 Model
        7.3 Insights
        7.4 Do It Yourself
    8 Overfitting
        8.1 Examples
        8.2 Causes and Solutions
    9 Triple Exponential Smoothing
        9.1 The Idea Behind Triple Exponential Smoothing
        9.2 Model
        9.3 Insights
        9.4 Do It Yourself
    10 Outliers
        10.1 Idea #1 – Winsorization
        10.2 Idea #2 – Standard Deviation
        10.3 Idea #3 – Error Standard Deviation
        10.4 Go the Extra Mile!
    11 Triple Additive Exponential Smoothing
        11.1 The Idea Behind Triple Additive Exponential Smoothing
        11.2 Model
        11.3 Insights
        11.4 Do It Yourself
Part II Machine Learning
    12 Machine Learning
        What Is Machine Learning?
        12.1 Machine Learning for Demand Forecasting
        12.2 Data Preparation
        12.3 Do It Yourself – Datasets Creation
        12.4 Do It Yourself – Linear Regression
        12.5 Do It Yourself – Future Forecast
    13 Tree
        13.1 How Does It Work?
        13.2 Do It Yourself
    14 Parameter Optimization
        14.1 Simple Experiments
        14.2 Smarter Experiments
        14.3 Do It Yourself
        14.4 Recap
    15 Forest
        15.1 The Wisdom of the Crowd and Ensemble Models
        15.2 Bagging Trees in a Forest
        15.3 Do It Yourself
        15.4 Insights
    16 Feature Importance
        16.1 Do It Yourself
    17 Extremely Randomized Trees
        17.1 Do It Yourself
        17.2 Speed
    18 Feature Optimization #1
        18.1 Idea #1 – Training Set
        18.2 Idea #2 – Validation Set
        18.3 Idea #3 – Holdout Dataset
    19 Adaptive Boosting
        19.1 A Second Ensemble: Boosting
        19.2 AdaBoost
        19.3 Insights
        19.4 Do It Yourself
    20 Demand Drivers and Leading Indicators
        20.1 Linear Regressions?
        20.2 Demand Drivers and Machine Learning
        20.3 Adding New Features to the Training Set
        20.4 Do It Yourself
    21 Extreme Gradient Boosting
        21.1 From Gradient Boosting to Extreme Gradient Boosting
        21.2 Do It Yourself
        21.3 Early Stopping
        21.4 Parameter Optimization
    22 Categorical Features
        22.1 Integer Encoding
        22.2 One-Hot Label Encoding
        22.3 Dataset Creation
    23 Clustering
        23.1 K-means Clustering
        23.2 Looking for Meaningful Centers
        23.3 Do It Yourself
    24 Feature Optimization #2
        24.1 Dataset Creation
        24.2 Feature Selection
    25 Neural Networks
        25.1 How Neural Networks Work
        25.2 Training a Neural Network
        25.3 Do It Yourself
Part III Data-Driven Forecasting Process Management
    26 Judgmental Forecasts
        26.1 Judgmental Forecasts and Their Blind Spots
        26.2 Solutions
    27 Forecast Value Added
        27.1 Portfolio KPI
        27.2 What Is a Good Forecast Error?
Now It’s Your Turn!
A Python
    How to Install Python
    Lists
    NumPy Arrays
    Slicing Arrays
    Pandas DataFrames
        Creating a DataFrame from a Dictionary
        Slicing DataFrames
        Exporting DataFrames
    Other Libraries
Bibliography
Glossary
Subject Index
    Notes