Have you ever heard that those who buy diapers are more likely to buy beer too? How about that when stapler is sold at a retailer, it is a good indicator that a company has hired a new employee? Would you be surprised to learn that those using their credit card to buy a drink in a “drinking establishment” are more likely to miss their credit card payment?
A few other surprising facts readers will find in a new book, Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie or Die by Eric Siegel include:
• Clinical researchers predict divorce with 90 percent accuracy.
• Researchers employ machine learning to predict Hollywood blockbusters and hit songs.
• Life insurance companies predict age of death to decide whether to approve and then price a policy application.
• The state of Maryland uses predictive models to detect inmates more at risk to be perpetrators or victims of murder.
• University of Phoenix predicts which students are at risk of failing a course and then target them with intervention measures.
To fully describe what predictive analytics (PA) are and how such data is used, Siegel uses these facts and case studies such as big box retailer, Target, predicting which female customers will have a baby in coming months so that they can market relevant items to the expectant parents. And, how Hewlett-Packard uses analytics to predict who will remain in their employ or who is at a high risk of quitting.
When you go to the grocery store or drug store and you get coupons printed that seem to offer just the products you may be interested in, that is another every day use of PA that the average consumer may encounter.
Siegel writes, “I was at Walgreens a few years ago, and upon checkout, an attractive, colorful coupon spit out of the machine. The product it hawked, pictured for all of my fellow shoppers to see, had the potential to mortify. It was a coupon for Beano, a medication for flatulence.”
The author had developed a lactose intolerance, and the drug store was recommending products that might be compatible with his medical condition. He describes PA as benefiting both the consumer and the organization by empowering it “with an entirely new form of competitive armament.”
Siegel spends a lot of the book going through the different predictive models and how the data is extracted and used. This type of data mining is being used in numerous ways, not just for consumerism. He provides examples from family and life, healthcare, crime fighting and fraud detection, staff and employees and human language understanding.
Of course, those in government have found ways to use PA to their own personal advantage. President Obama’s 2012 campaign used over 50 analytics experts. His team used persuasion modeling to determine which voter could be “positively persuaded by a political campaign contact such as a call, door knock, flyer or TV ad.”
The Obama team used PA to also select those voters where contact would backfire or the “do-not-disturbs” where any contact would hurt the campaign more than help by switching the voter over to his opponent. For those wondering how a candidate with as sloppy a record as Obama had coming out of his first term could win re-election, this book may have an answer for you.
While the book answers so many questions about how marketers know so much about consumers, it’s not just a book for marketers. It is one of those business books that cross many departments including sales, research and development, human resources, customer service among others.
Siegel’s writing style is highly readable and enjoyable. This book has many technical chapters but the author uses easily recognizable examples and case studies that make the book easy to read and to understand.Powered by Sidelines