Customer Reviews

The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition (Springer Series in Statistics)

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

 

 

The book provides a long-sought link between Statistics and Data Mining. Problems of classification are adequately addressed with regard to both model accuracy and reliability. The discussion of boosting and its evolution demonstrates just how fast "greediness" for accurate classifiers is growing.

In the years to come will apparently witness an increasing wave of multi-disciplinary approaches in devising and modifying classification techniques. Whenever that comes, this book will already have made its contribution to that development.

This is a review of the 1st edition, though I have looked at a copy of the 2nd edition and as far as I can tell, it all still applies.

This is a genuinely excellent book. The authors thoroughly understand the topic and explain it with remarkable clarity. There are a good number of well thought out exercises and the book's website contains a lot of additional information and data.

If you really want to understand statistical learning methods, rather than just applying them blindly, then this book is definitely one to read.

This review is not meant to be a review for the paper edition of an otherwise excellent book, but it is only specific to the Kindle edition.
Obviously one can't expect the same quality of a printed book, but the quality of the Kindle edition is absolutely awful. All the mathematical formulas have been converted into some kind of bitmap images all of extremely poor quality, such that they are barely readable and sometimes completely wrong (i.e. different from what you read in the printed edition).
I don't know if this is a common problem for Kindle editions of books containing mathematical formulas/tables/images, but it is surprising that Amazon is selling this edition at more than £30: given the quality of the mathematical formulas, images and tables therein this book shouldn't be sold at all in the Kindle edition, not even given away for free!