Customer Reviews

Data Mining Cookbook: Modeling Data for Marketing, Risk and Customer Relationship Management

5 star:		(9)
4 star:		(2)
3 star:		(1)
2 star:		(1)
1 star:		(1)

 

 

Book is OK, but DON'T BUY THE CD-ROM! I dropped [a large amount] for what I thought would be a worth-while "self-learning" course on Data Mining programming in SAS. To my great disappointment, I found that while Olivia had included the code (which you can type in yourself), there was NO DATA PROVIDED, making the code all but useless (can't run the models with no data!). I e-mailed her asking for some kind of a sample data set. She agreed, but after months of begging she provided nothing whatsoever. Don't make the same mistake I did - STAY AWAY FROM THE CD-ROM!!!

By reading this book you should learn how to cook data mining applications...but if you have very little or no appreciation of data mining and customer relationship management (CRM), and you have never used SAS software, you'll probably end up burning your first few cakes or even worst your fingers !!
As the author gives a very brief introduction to data mining, make sure before you even start reading this book that you have a grasp of statistical modelling and data mining in a CRM context, otherwise you will find the material presented in this book too much to take in at once, and worst, you may probably end up being put off building your own data mining applications.
The author clearly has a solid statistical (read SAS) background, making this book a strong contender as one of the best books on data mining around, providing the reader with a number of useful recipes, practical examples and pragmatic data mining approaches which should be studied and understood in detail. Being a cookbook, the author's (or should I say the chef's) particular style may not suite your palate. In other words, you may not like the author's bias towards using logistic regression as the main data mining technique. As a result, you will not learn how to cook exotic dishes using ingredients such as neural networks. However, the choice to use logistic regression as the main statistical techniques pays off, as this allows the reader to start learning to cook robust/reliable meals (models), before cooking with the more exotic ingredients (techniques).
The topics and interventions provided by the well-experienced contributors are in context with the author's material, strengthening the practical context in which data mining applications are presented. On a few occasions, I found that the author does not discuss figures and tabulated outputs in a straightforward way, inevitably affecting the readability of the book. Notwithstanding, the methodology and material presented has a considerable amount of depth and rigour, and the general themes are well structured and maintained throughout.
Many figures and tabulated results are presented in the graphical output provided by the SAS system, which may be less appealing to you if you are not going to be using SAS. Also, many data mining software tools now available have significantly better graphical data presentation capabilities than those presented in this book, inevitably giving it a slightly dated look. Unsurprisingly, being the first version of the cookbook, there are a few typos (and one incorrect figure at the beginning of the first chapter).
In summary, this book is not for the novice, but will be a book that you will want read more than once.

Yes, its not for beginners or executives. That's great, because so many other books are aimed at glossing over the details for novices. This book gets down and dirty with exactly how one goes about analyzing and modeling data in applied marketing. It assumes some knowledge of data and basic analysis, but it also reviews assumptions along the way and points out "gotchas" for the less experienced. Yes, there is an overemphasis on Logistic Regression and a paucity of info on other techniques, but the Logistic Regression work is well done. Yes, it is very SAS based, but the code is not hard to translate to other systems. She doesn't spend as much time as I would prefer on explaining all the output that she presents, though its an excellent start. But she does provide specific details on ALL the steps, from getting and transforming data to how to present your results and use your model, things that are ignored in many other books. Sure, there are easy quibbles and minor errors throughout, but what tech book today is error free? So, if you are looking for the basic guidebook on just how one goes about "modeling", then this is the one. Its got a permanent place on my bookshelf, and is one of the standards I recommend along with Kimball, Pyle, and other "ya gotta have" books.

I was disappointed after reading 3 chapters of this book. Leafing forward, the book is saturated with SAS examples that I not only cannot understand but do not care about. It seems the whole book was written just to promote the (sold separately)...CD ROM with source SAS code. If you are going to write a SAS book, label it as such.

Generally speaking, it is a good book. Contains a lot of real world examples. and it gets into a lot of details on modeling which you don't normally see in a data mining book.
however, some parts of the book were pretty crude. It contains some mistakes. for example, in one chapter the author tries to compare a few repricing scenerios. she compared the account after rate increase with the account before rate increase. and before rate increase, the attrition rate is zero. and it is just not the right way to evaluate a strategy. normally, you would have to compare an account which got a rate raise with the same account as if it didn't receive the increase. and even without the rate increase, the attrition rate down the road can't be zero. normally, you have to use test and control group on this kind of situation. besides, the author made some calculation mistakes in the comparison table. the numbers simply don't add up.
Anyway, overall the book is still a nice one if you can absorb all the nice information in it.

Logistic Regression From A - Z! This book has it all.

The author lays out clear, concise methodologies to build robust predictive models using SAS. The nice thing is this book lays out the process step by step with SAS code examples. You do not have to be a statistics major to understand how to use the built in SAS functionality.

The modeling methods are unbelievably detailed including topics like defining the objective function, testing variables for predictability using chi squared, fitting continuous variables using the most linear variable transformation format (squared, cubed, cubed root, log, exponent, tangent, sine, cosine, etc... 19 total formats), changing categorical variables to continuous indicator variables for logistic regression use, using stepwise, backward, and score regression methods to further eliminate less predictive variables, defining deciles, and model testing methods like bootstrapping, jackknifing and gains tables to validate the model.

I do not fully understand the mathematical concepts involved throughout the entire process nor do I want to. The book provides a consistent repeatable programming methodology to follow that is broken down into very quantifiable steps.

I would recommend this book for anyone with limited statistical knowledge and a need to understand predictive modeling programming methodologies. Knowledge of the SAS programming language is essential to make full use of this material. The book uses real life examples from the banking, insurance, and marketing industries and contains additional valuable information related to these fields.

I found this book every bit as comprehensive as suggested by the glowing forward by Michael Berry. I was pleased to see thorough and comprehensive treatment of the full modeling process and commensurate attention to the documentation of it. Modeling of the total customer value proposition is masterful. I also profitted from the initial digestion of the rich complexities of internet activity data. This book brings a wealth of business knowledge to the statistical modeling and data mining professional. The author is to be congratulated on a fine book.

Good book for learning about the data mining techniques of logistic and linear regression. It helped highlight some good uses, and fortunately, I've recently had the opportunity to use it in my work.
However, I was a bit disappointed that the data preparation seemed very coding intensive. The author could have shown readers how to merge lookup tables of risk values onto customer datasets, rather than hard-coding each of the rules and values; or to use the SAS procedure for creating indicator variables, instead of writing the rules for each category.
Overall, I'm glad that I purchased the book - it lives up to its claims - but it misses some of the better practices, and time saving devices, in data preparation

I have been doing SAS for 11 years. So the SAS code does not bother me.

The best value of this book is that it is very practical; as the title suggests, it is a cookbook. I finished reading about 200 pages in 4 hours and I reviewed it many times when writing SAS coding. If you have deep engineering background, you probably will look for more to dig into after finishing the book. If you are statistical, this is not a book that teachs you how to be rigorous. It is not a book for academidians in any way.

I would rename the title as Data Mining cookbook using SAS software if I can; I concur that the book's value is decisively discounted if the reader does not know SAS software. I, on the other hand, do recommend SAS as a good DM tool.

Finally, a book that thoroughly explains predictive and descriptive modeling in simple language. It discusses the importance of defining the objective as well as using quality data. Parr-Rud uses real world examples to detail methods for building response, risk, churn, and lifetime value models. She even includes several validation techniques that are not available in most packaged solutions. A very accessible book.