Machine Learning Times
Machine Learning Times
Elon Musk Predicts Artificial General Intelligence In 2 Years. Here’s Why That’s Hype
 Originally published in Forbes, April 10, 2024 When OpenAI’s...
Survey: Machine Learning Projects Still Routinely Fail to Deploy
 Originally published in KDnuggets. Eric Siegel highlights the chronic...
Three Best Practices for Unilever’s Global Analytics Initiatives
    This article from Morgan Vawter, Global Vice...
Getting Machine Learning Projects from Idea to Execution
 Originally published in Harvard Business Review Machine learning might...

8 years ago
Jim Sterne’s Book Review of “Predictive Analytics” by Eric Siegel


Book review originally published in the journal Applied Marketing Analytics

Eric Siegel’s book, ‘Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie or Die’ gets its subtitle from the many ways statistical prognostication has been used. The life insurance industry was founded on and continues to grow by predicting when you are likely to shuffle off this mortal coil. Actuaries analyse the financial consequences of risk and advise their clients accordingly. This is quite an old profession.

Since the arrival of more computer power and more data to study, many industries are using predictive capabilities in different ways. Eric Siegel addresses a wide variety of applications as a means to explain what predictive analytics is, how it is applied and some of the results. His goal is not to teach the fine art of mathematical investigation or how to write a query in R, but to describe the practical application of prediction from a business perspective so that non-maths majors can grasp the possibilities. Examples include: Target predicting, embarrassingly, which of their customers might be pregnant; Hewlett-Packard forecasting which of their employees are most likely to quit; IBM calculating whether an event will attract a critical mass of prospects; Chase Bank foretelling which mortgage customers are about to refinance and switch to another firm; Brigham Young University Hospital predicting premature births, and many more.

From IBM’s Watson on the television show Jeopardy! to how police departments are using mathematical models to allocate resources around a city, Siegel uses such wide-ranging examples that a wider grasp of the subject is delivered without being pedantic. The book is written with a wry sense of humour that does not overwhelm but allows Siegel’s voice to come through. It is as though he were in the room, chatting animatedly about his favourite subject. This is a gentle read for those who want to understand predictive analytics in general but also a valuable resource for those just starting to implement a predictive analytics programme for their organisation. It has an extensive (68-page) set of appendices and notes directing the reader to more in-depth materials that are likely to be more cogent for a specific industry.

This is not a book for the active practitioner. It clearly covers concepts but does not provide enough detail to allow one to dive in and build models to make predictions. It does not move the practice forward by offering new methods, techniques or approaches. It does not go down any one rabbit hole to fully explain the deep details of how to actually bend maths to your will. But these were not Siegel’s intentions.

It feels instead that he has written a book to explain what he does for a living to everybody not in the industry. ‘I’m
a mathematician’ (or a statistician or an analytics professional) is a conversation stopper. But finally, Siegel has declared, ‘I am a predictor of the future and explain it
all in this fun book!’

‘Predictive Analytics’ is perfect for the curious and for the senior manager who needs to decide about investing in yet another technology. With artificial intelligence right around the corner, it is crucial to understand the basics and this book provides the fundamentals in clear language to ensure that the rest of us do not get left behind.

Author Bio:

Jim Sterne is an international consultant focused on measuring the value of the online marketing for creating and strengthening customer relationships since 1993. Sterne has written eight books on using the Internet for marketing, produces the eMetrics Summit – and is co-founder and current Chairman of the Digital Analytics Association –

Click here for more information about the book ‘Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie or Die.

Leave a Reply