Hands-On Prescriptive Analytics

Part II. Essential Background Material

This part of the book contains material needed for the rest of this book: Python essentials and probability essentials.

I include these because the material in both is used throughout this book and because they form the backbone of much done in Prescriptive Analytics. In fact, they are heavily used in all three analytics: Descriptive, Predictive, and Prescriptive. So you should have a good background in both. You can skip this part if you already know and understand how to use Python and are comfortable with basic probability theory.

Since the subtitle for this book is “Optimizing Your Decisions with Python,"” I will review the key features of Python in a Python primer. This book emphasizes practicality, not theory, so hands-on Python applications will be provided. I will only skim the surface of Python; anything in more detail and depth would require its own book, which would probably be encyclopedic. Consequently, you should not feel lost if you are not conversant in the basics of the Python programming language and infrastructure. Everything will be developed in a JupyterLab notebook.

As I mentioned, I review basic probability concepts in this part. A major probability theorem, Bayes’ Theorem, is developed and illustrated. The concept of a prior probability is introduced to reflect or capture a subjective view of the chance of something happening. This is important because the probabilities used in Prescriptive Analytics are subjective. ...