Rating: 
Summary: Excellent data mining textbook
Review: Broad coverage, including hot new topics: SVM, boosting and bagging, modern evaluation methods (ROC and lift curves). Well grounded in practical data mining applications, talks about DM issues outside model building, which are rarely discussed: feature engineering, data cleaning, etc. Clear and well written: illustrative examples help the presentation a lot. Describes in detail decision trees and rule learners, instance-based learning, and numerical prediction. Accompanied by the WEKA system, implementing in Java many of the methods discussed in the book, and available for download for free. An excellent hands-on textbook for an applied Machine Learening/DM class, or recommended reading for ayone who wants to understand DM. Good next step for those that have whetted their appetite with Berry and Linof's book.
Rating:
Summary: If you read machine learning then you should read it also
Review: I have read machine learning writed by Tom M. Mitchell and also I have read Data Mining Concepts and Techniques writed by J. Han and M. Kamber. Both text books is very useful for someone who want to get concept of a modern data analysis approaches. But, however, to understant about that clearly, you should read this book also because the example and author's form writing is so good and nice, very easy to understant.
Rating:
Summary: Stop searching for datamining: You've found it.
Review: I've been working with "big name software" for some years, but when I joined the institution I work now and no tools where available I begun my quest for an open source tool that could help me build statistical models applied to real business problems.As a result of this quest I found the WEKA data mining software on the Internet (you can find it on www.cs.waikato.ac.nz/~ml/weka/) and that nice piece of software leaded me to this book. This book is EXCELLENT and I am giving 5 *five* stars to it as it helped me understanding the whole process of datamining: from loading the data to building the model. I've read some reviews and I think some of them are not fair (particularly one that says that this book have "just words with no relation or sense at all").. THIS BOOK IS REALLY WELL WRITTEN but you have to read it slowly: As when you study something. Buy this book (*don't forget to download the software*) and I am totally sure that you will be producing and using models in a week. Can't imagine that some weeks ago Cheers,
Rating:
Summary: Stop searching for datamining: You've found it.
Review: I've been working with "big name software" for some years, but when I joined the institution I work now and no tools where available I begun my quest for an open source tool that could help me build statistical models applied to real business problems. As a result of this quest I found the WEKA data mining software on the Internet (you can find it on www.cs.waikato.ac.nz/~ml/weka/) and that nice piece of software leaded me to this book. This book is EXCELLENT and I am giving 5 *five* stars to it as it helped me understanding the whole process of datamining: from loading the data to building the model. I've read some reviews and I think some of them are not fair (particularly one that says that this book have "just words with no relation or sense at all").. THIS BOOK IS REALLY WELL WRITTEN but you have to read it slowly: As when you study something. Buy this book (*don't forget to download the software*) and I am totally sure that you will be producing and using models in a week. Can't imagine that some weeks ago Cheers,
Rating:
Summary: An excellent textbook for machine learning
Review: In fall 2000, I taught a master's level course in ML to about 25students at New York University. Fortunately both for me and mystudents, I was able to use and assign excellent recent textbooks inthe area: "Machine Learning" by Tom Mitchell and "DataMining: Practical Machine Learning Tools and Techniques with JavaImplementations" by Ian H. Witten and Eibe Frank. I recommendboth books enthusiastically. A student who has mastered Mitchellhas a solid grasp of the basic element of nearly every method ofmachine learning currently in use, and of almost every aspect of MLresearch. A student who has mastered Witten/Frank has a deepknowledge of the major ML techniques, and a strong sense of theopportunities and pitfalls to be encounted when these techniques areput into practice. A complete review of both books, to appear inArtificial Intelligence Journal, can be found at...
Rating:
Summary: An excellent textbook for machine learning
Review: In fall 2000, I taught a master's level course in ML to about 25students at New York University. Fortunately both for me and mystudents, I was able to use and assign excellent recent textbooks inthe area: "Machine Learning" by Tom Mitchell and "DataMining: Practical Machine Learning Tools and Techniques with JavaImplementations" by Ian H. Witten and Eibe Frank. I recommendboth books enthusiastically. A student who has mastered Mitchellhas a solid grasp of the basic element of nearly every method ofmachine learning currently in use, and of almost every aspect of MLresearch. A student who has mastered Witten/Frank has a deepknowledge of the major ML techniques, and a strong sense of theopportunities and pitfalls to be encounted when these techniques areput into practice. A complete review of both books, to appear inArtificial Intelligence Journal, can be found at...
Rating:
Summary: Data mining technology power on 400 pages.
Review: It's difficult to get interesting
literature related to this theme. On the one hand there are some books written for managers, on the other hand there are some pretty mathematical books for academics. But this book is the best mix. You get an introduction to data mining and learn step by step from the basics up to the hard algorithm stuff with nice examples.
There is a clear theme structure, and the deep technical sections are marked, so you can read what you are most interested in. The book describes not only one algorithm, but a lot of them and discusses plusses and minuses. Where it's necessary it uses simple diagrams to illustrate something, not so much that it looks like they want to fill the pages, like in other books. Best of all, the algorithms are implemented as an
open source java software named "weka". This is my state of the art data mining tool.
You can see the algorithms working and use the implementations for your ideas (like me). If you are hungry to learn more
about one or the other thing, the book provides a literature list. For me this book was one of the best books in the last years, because it provides the best mix and gives you a fast but deep view in this theme.
Rating: 
Summary: Useless
Review: My goal when I purchased this book was to learn the fundametal techniques and algorithms of data mining, such as C4.5/C5.0 and other popular algorithms, after reading the book my goal is far from being reached, on the one hand the book is not will structured, it covers many topics but with a very weak logical connection among them, on the other hand there's no complete and simple example that take the reader from A to Z illustrating step by step the basic concepts of reducing entropy, rules productions and pruning etc..., finally there's no design explanation of the downloadable code that can give a global view of the "software" architecture and it's building blocks, leaving the reader confused and wishing he saved he's money!.
Rating:
Summary: Our most popular book
Review: Over the last 3 years our company has bought 15+ copies of this book and have given it to our new employees to help them gain a practical perspective when writing machine learning applications. The book is filled with practical insights and gems learnt from real data analysis experience. We have read almost all other data mining and machine learning books and have standardized on this book. Although the book is great, the software is amazing! Weka (the name of the software that is described in the book and is available for free) contains the largest collection of machine learning algorithms available in a coherent package. The software is written in Java and we have used it under a variety of platforms. Weka is incredible, and when combined with the well written explanations I have to give this book top marks. I'm looking forward to the next edition.
Rating: 
Summary: Disappointing
Review: Poor writing, often delves on irritating jokes and unimportant topics (for instance I didn't buy this book to tell me about how cool javadoc is), fails to deliver complete mathematical background for the models, fails to give a good explanation on how to use Weka software.
Overall it's a big black hole that'll eat away a chunk of your time while providing a super low return in useful knowledge. Can't they write a few separate chapters that provide all the information you need and teach you a few algorithms instead of trying to be an encyclopedia and be so shallow as they are? Academic, hard to follow, often references other books for critical info, poorly organized. Skip it while it's not too late.
| 
