This book is in a way the “sequel” of the first book that I wrote together with Konstantinos Tsiptsis. It follows the same principles, aiming to be an applied guide rather than a generic reference book on predictive analytics and data mining. There are many excellent, well-written books that succeed in presenting the theoretical background of the data mining algorithms. But the scope of this book is to enlighten the usage of these algorithms in marketing applications and to transfer domain expertise and knowledge. That’s why it is packed with real-world case studies which are presented with the use of three powerful and popular software tools: IBM SPSS Modeler, RapidMiner, and Data Mining for Excel.

Here are a few words on the book’s structure and some tips on “how to read the book.” The book is organized in three main parts:

• Part I, the Methodology. Chapters 2 and 3: I strongly believe that these sections are among the strong points of the book. Part I provides a methodological roadmap, covering both the technical and the business aspects for designing and carrying out optimized marketing actions using predictive analytics. The data mining process is presented in detail along with specific guidelines for the development of targeted acquisition, cross-/deep-/up-selling and retention campaigns, as well as effective customer segmentation schemes.
• Part II, the Algorithms. Chapters 4 and 5: This part is dedicated in introducing the main concepts of some of the most popular and powerful data mining algorithms for classification and clustering. The data mining algorithms are explained in a simple and comprehensive language for business users with no technical expertise. The intention is to demystify the main concepts of the algorithms rather than “diving” deep in mathematical explanations and formulas so that data mining and marketing practitioners can confidently deploy them in their everyday business problems.
• Part III, the Case Studies. Chapters 6, 7, and 8: And then it’s “action time”! The third part of the book is the “hands-on” part. Three case studies from banking, retail, and telephony are presented in detail following the specific methodological steps explained in the previous chapters. The concept is to apply the methodological “blueprints” of Chapters 2 and 3 in real-world applications and to bridge the gap between analytics and their use in CRM. Given the level of detail and the accompanying material, the case studies can be considered as “application templates” for developing similar applications. The software tools are presented in that context.

In the book’s companion website, you can access the material from each case study, including the datasets and the relevant code. This material is an inseparable part of the book, and I’d strongly suggest exploring and experimenting with it to gain full advantage of the book.

Those interested in segmentation and its marketing usage are strongly encouraged to look for the previous title: Konstantinos Tsiptsis and Antonios Chorianopoulos. Data Mining Techniques in CRM: Inside Customer Segmentation. Wiley, New York, 2009.

Finally, I would really like to thank all the readers of the first book for their warm acceptance, all those who read or reviewed the book, and all those who contacted us to share kind and encouraging words about how much they liked it. They truly inspired the creation of this new book. I really hope that this title meets their expectations.