The newest edition of the leading introductory book on datamining, fully updated and revised
Who will remain a loyal customer and who won't? Which messagesare most effective with which segments? How can customer value bemaximized? This book supplies powerful tools for extracting theanswers to these and other crucial business questions from thecorporate databases where they lie buried. In the years since thefirst edition of this book, data mining has grown to become anindispensable tool of modern business. In this latest edition,Linoff and Berry have made extensive updates and revisions to everychapter and added several new ones. The book retains the focus ofearlier editionsshowing marketing analysts, businessmanagers, and data mining specialists how to harness data miningmethods and techniques to solve important business problems. Whilenever sacrificing accuracy for the sake of simplicity, Linoff andBerry present even complex topics in clear, concise English withminimal use of technical jargon or mathematical formulas. Technicaltopics are illustrated with case studies and practical real-worldexamples drawn from the authors' experiences, and every chaptercontains valuable tips for practitioners. Among the techniquesnewly covered, or covered in greater depth, are linear and logisticregression models, incremental response (uplift) modeling,naïve Bayesian models, table lookup models, similarity models,radial basis function networks, expectation maximization (EM)clustering, and swarm intelligence. New chapters are devoted todata preparation, derived variables, principal components and othervariable reduction techniques, and text mining.
After establishing the business context with an overview of datamining applications, and introducing aspects of data miningmethodology common to all data mining projects, the book coverseach important data mining technique in detail.
This third edition of Data Mining Techniques covers such topicsas:
How to create stable, long-lasting predictive models
Data preparation and variable selection
Modeling specific targets with directed techniques such asregression, decision trees, neural networks, and memory basedreasoning
Finding patterns with undirected techniques such as clustering,association rules, and link analysis
Modeling business time-to-event problems such as time to nextpurchase and expected remaining lifetime
Mining unstructured text
The companion website provides data that can be used to test outthe various data mining techniques in the book.