Building one-to-one relationships with your customers means "letting your customers teach you about themselves through their interactions with your firm and using what you learn to increase your profitability by making their lives easier." So say Michael J. A. Berry and Gordon S. Linoff in their new book, Mastering Data Mining: The Art and Science of Customer Relationship Management (John Wiley & Sons, 2000). In this book, the authors deftly explain that the ability to learn is critical for a company to become a true one-to-one marketer and that data mining is central to the learning process.
An organization's ability to give customers what they want depends on its ability to learn from customers' experiences. We know far more about our customers than any third-party organization could ever hope to know, but we need data mining to unleash the potential of that information. Berry and Linoff have written yet another of the most readable books in our industry on the subject of data mining. If you missed their first book, Data Mining Techniques for Marketing, Sales and Customer Support (John Wiley & Sons, 1997), check it out. It is a very comprehensive and comprehensible review of what is involved in data mining. In their new book, they use an analogy to photography, which explains the picture of a camera on the cover, to describe four different approaches to data mining that a company can take. One of these, developing in-house expertise in data mining, corresponds to building your own darkroom and becoming a skilled photographer.
Online transaction processing systems notice customer activity. Decision support systems provide organizations with a memory. Data mining allows organizations to learn from what is remembered, to use what has happened in the past to help predict the future. Berry and Linoff use Part One of Mastering Data Mining to introduce data mining in the context of customer relationship management. Part Two covers more technical aspects of data mining, especially data mining techniques, data and the modeling of data. Part Three provides the real meat of the book, with case studies of data mining applied to real-world problems.
Berry and Linoff show that they have extensive personal experience helping companies get value from data mining. In addition, their expert writing skills make technical material not just interesting, but fascinating. You've just got to love the title of Chapter 9, "Who Needs Bag Balm and Pants Stretchers?" It is a wonderful case study of The Vermont Country Store (VCS), which specializes in hard-to-find items, such as Olivetti typewriters, push mowers and Postum (not to mention bag balm and pants stretchers). Read the case study to find out how VCS achieved a return on their data mining investment of 1,182 percent!
Berry and Linoff have an incredible ability to make you want to read case studies, even for industries unrelated to your own. Other case studies deal with customer acquisition and cross-selling (Who Gets What?) and customer retention (Please Don't Go!). The authors make an interesting point about why catalogers should be studied by e- commerce "wannabes." Where brick-and-mortar retailers primarily deal with anonymous transactions, catalogers know their customers and their purchasing patterns over time. Their strengths in predicting who will buy what products, when and how often are the exact same strengths that will be critical to selling on the Web. In many cases, catalogers have been among the first to exploit the Web. Companies wanting to excel at e-commerce can learn much from the data mining practices of catalogers, some of which are chronicled in this book.
I particularly liked how the authors describe building a data mining environment as a "subversive activity, the beginning of a quiet revolution that will shift corporate focus from products to customers, from guesswork and opinions to analysis and fact." The way that emphasis on fact becomes reality starts with listening to data. "Data miners have two ears, one for listening to the business users and the other for listening to data." Churn management or modeling is an example of how miners can listen to data. It looks at the past as a predictor of future behavior in the area of customer churn. The authors use very effective charts, graphs and screen prints from data mining and data visualization tools to illustrate their points and some of the insights gained within the case studies.
Anyone whose organization wishes to either enter the world of data mining or excel at it, should consider Mastering Data Mining a must-read. It's tough work for us to learn from our experiences with our customers; but for us to be successful in the extremely competitive future, it just simply has to happen. Those who learn, both from their customers' experiences and from Berry and Linoff will grow and prosper. Those who don't learn, won't.
Register or login for access to this item and much more
All Information Management content is archived after seven days.
Community members receive:
- All recent and archived articles
- Conference offers and updates
- A full menu of enewsletter options
- Web seminars, white papers, ebooks
Already have an account? Log In
Don't have an account? Register for Free Unlimited Access