Machine Learning Times
Machine Learning Times

7 years ago
Book Review of “Applied Predictive Analytics” by Dean Abbott


Industry leader and author Dean Abbott will be presenting at Predictive Analytics World Boston (Oct 5 – 9) on “Data Preparation from the Trenches: 4 Approaches to Deriving Attributes.” Abbott will also run two post-conference full-day training workshops, “Advanced Methods Hands-on: Predictive Modeling Techniques” (where his book Applied Predictive Analytics will be given to attendees), and “Supercharging Prediction: Hands-On with Ensemble Models

Dean Abbott’s new book, “Applied Predictive Analytics: Principles and Techniques for the Professional Data Analyst,” published by Wiley in April, smoothly delivers the established teachings of a preeminent hands-on instructor.

This groundbreaking contribution to the field of predictive analytics provides a unique gift: A how-to that is accessible, yet quite comprehensive, taking the reader through much of the established teachings of one of the industry’s preeminent hands-on instructors. The author, Dean Abbott, is renowned as both a leading “rock star” hands-on consultant in predictive analytics, as well as a fantastic, 5-star-rated conference speaker and an acclaimed training workshop instructor. You get the best of all worlds with this particular expert: deep analytical insights, stellar execution, clear communication, and contagious enthusiasm. And he has translated these assets nicely into a book.

Abbott’s stated mission with this book (as mentioned in its “Introduction” at the end of the book) is to provide very practical guidance for executing on predictive analytics, as if chatting to someone peering over his shoulder as he works through a project. This mission is accomplished, and in doing so it accomplishes something even more significant: The book takes much of Abbott’s well-honed training agenda (do attend his in-person sessions if you can!), along with the accessibility of his casual speaking style, and translates them onto the page. As a result, this book reads in a much more conducive and engaging manner than, say, a more formally structured textbook.

The book is extremely practical. It is mostly organized around project execution steps, rather than around analytical methods, application areas, or industry verticals.

“Applied Predictive Analytics” focuses on the issues and tasks that consume the vast majority of any hands-on predictive analytics project. Some reviewers of this book – as well as others in the industry in general – appear to believe you must understand the theory behind the analytical modeling methods in order to be an effective hands-on practitioner of the art. There’s a religious debate to be had over this. But, either way, this book covers necessary knowledge; no one book covers all this as well as all the in-depth math behind analytical modeling methods. In the end, executing on predictive analytics in a commercial context is an empirical exercise more than an exercise in applying theory. For example, pragmatic choices in the data preparation often makes a much bigger difference than the choice of predictive modeling method. Also, regardless of the modeling method employed and its theoretically sound capabilities, the proof is always in the pudding: The results of modeling must be empirically validated over unseen test data. It’s a kind of experimental science.

I do feel this book can serve as a great follow-on for “digging in” after reading my book, Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die which, unlike Abbott’s book, is not a how-to, but rather introduces the concepts and provides an industry overview.

By: Eric Siegel, Founder, Predictive Analytics World