The French also have their data miners and more particularly their data mining authors. Stéphane Tufféry is one of them. In 2008 he authored the book “Data Mining et Statistique Décisionnelle” which has been translated in English in 2011 (a huge work according to the size of the book – more than 680 pages – done by Rod Riesco). The English version is entitled “Data Mining and Statistics for Decision Making” with forewords from David J. Hand. Although the author comes from academic world, the book is focused toward data mining for the industry.
Most important data mining techniques are covered in this book. From linear regression to SVM, through decision tree and neural networks. Each technique is introduced through theory and clear examples. Often, R and SAS code examples are given. These three steps – theory, examples, codes – make this book an excellent toolbox for the data miner or statistician. Examples in the book have a focus on CRM applications. The book doesn’t contain many equations, and is thus oriented toward practitioners, rather than researchers. Also to be noted, the two very well written and comprehensive chapters on linear regression and clustering.
The book contains an impressive comparison of SAS, SPSS and R: most important functions of these three major tools are compared in 55 pages (!). It’s an amazing work, really. Another relevant section is a discussion of data mining and information technology. Appendix B contains an impressive list of readings in data mining (with description from the author). To conclude, this is a very comprehensive book for any data miner, but too detailed to be read from the beginning until the end. Anyway, this book is a must-have toolbox for any serious data miner.