Customer Reviews

Statistical Modeling and Analysis for Database Marketing: Effective Techniques for Mining Big Data

5 star:		(3)
4 star:		(0)
3 star:		(1)
2 star:		(0)
1 star:		(0)

 

 

I predict that Dr. Ratner's Statistical Modeling and Analysis for Database Marketers: Effective Techniques for Mining Big Data will be on every database marketer's bookshelf. Dr Ratner has put together an assembly of chapters that provide an indispensable resource for the daily problems facing data analysts and model builders in the database/direct marketing community. In each of the seveenteen chatpers Dr. Ratner addresses a typical problem and discusses the common solution. He points out unknown working assumptions or weaknesses of the latter, and then offers better solutions, which require basic knowledge of EDA/data mining. Dr. Ratner's writing style is unique as he makes familar concepts new, and new concepts familar. Thus, the book is easy and enjoyable reading. I specially like chapter that blends statistics with the machine learning, such as the introduction of the GenIQ Model.

This is a must have introductory book for the practitioner using data mining to build predictive models in industry. While it does have a few snippets of SAS code, it is a conceptual book that explains the "why" and the "how" of practical model building. (If you want SAS code buy "The Data Mining Cookbook" by Olivia Parr Rud.) It dispenses of with the antiquated notion of the "true" model of classical statistics and econometrics, and shows how to arrive at an acceptable model that yeilds good predictions. As practitioner's, this is what we care about most. Among other things, it gives good explanations of: (1) the EDA paradigm versus classical statistics (2) Tukey's bulging rule for transforming variables (3) variable selection, though there is no mention of clustering to eliminate redundant variables. It discusses some of the weaknesses of automatic variable selection methods (4) smoothed scatterplots and logit plots (5) decile analysis and using bootstrapping to derive confidence intervals for cum lift.

The book shows you how to use logistic regression, OLS, and CHAID to build predictive models. For those interested in Genetic modeling, it has a clearly written chapter on the subject that explains how genetic modeling can be used to create new variables that can have more information than either of the original variables.

While this book does not cover everything, and is definitely not the last word on the subject, it is a solid first word. In particular, the book does not cover splines, shrinkage techniques such as model averaging, ridge regression, ..etc. For treatments of these and similar advanced topics see Frank Harrell's "Regression Modeling Strategies" and Hastie, Tibsharani and Friedman's "Elements of Statistical Learning".

I consider myself fortunate to be the first to review this book. The title aptly indicates what the book is about: Statistical Modeling and Analysis for Database Marketers: Effective Techniques for Mining Big Data. The author provides in a Tukey-esque manner a collection of solutions to common problems facing database analysts, model builders, and marketers. The book can uniquely serve as a textbook, a how-to guide, and a reference source depending on the reader's statistical training and database marketing experience. Moreover, the author actually goes where other authors provide lip service: he creates the marriage of the "old" statistical methodologies with the new machine learning influence by introducing machine learning methods specifically tailored to database assessment of optimal model performance. The book's illustrations involve real problems, real data, and better solutions. This book is a keeper!

I see a common thing between the three Chapman and Hall books that I (briefly) owned: an enthusiastic practitioner eager to broaden and share their technical knowledge, and a book that will impress beginners, but leave more seasoned folk - in this case, readers with statistics/econometrics degrees - appreciative but disappointed with technical level and scope.

PS. If you *are* impressed by this stuff, join 'SAS BI and Analytics' LinkedIn group to receive a steady stream of daily marketing e-mails from Mr. Ratner. Typically, these lead to his Web page, where he presents short stats-themed articles seguing into promotion of his wonderful software. The story takes an uglier turn when you confirm, with Google's help, how much of the text is borrowed without attribution.

PPS. Two years later, the author responds - see "Comments".