I'm excited to take this class this fall at the U of M. I've heard that the fall course is more algorithmically rigorous than the spring course because the computer science department tries to open it up to non-CS majors at that time (biology majors interested in bioinformatics, for example). The professor, George Karypis, has a reputation on campus. I'm doing a dual degree in statistical science and CS so I'm looking forward to seeing how this compares to some similar class offered by the stats department.
Well I’m pretty sure it is a textbook (by Pearson a textbook publisher) put together by research PHDs in Data Mining, so textbook pricing seems appropriate to me. I’m more worried whether all that profit just goes to the publishers.
1st Edition of this book was excellent. Gives a solid explanation of both data mining/ml techniques and the trade-offs of choosing them.
The update to the chapter of classification was needed. Previously, the section on SVM and ANN was a subpart of a chapter, spanning no more than 10 pages, glad they added more detail there.
They also spend time in early chapters talking about preprocessing and cleaning data, something that often is glossed over.
I followed the first edition of this book during my master's degree Data Mining course. This is a good book (not too math heavy like [0]). It is a good book for somebody getting into data mining but it is more theoretical. For another excellent book that concentrates on building models using R I highly recommend [1] which has a great balance of theory and practical. Fun fact regarding [1] - one of the authors is the daughter of the renowned physicist Ed Witten.
16 comments
[ 3.2 ms ] story [ 49.8 ms ] threadthis is against policy
Also see Mining of Massive Datasets: http://infolab.stanford.edu/~ullman/mmds/book.pdf
The update to the chapter of classification was needed. Previously, the section on SVM and ANN was a subpart of a chapter, spanning no more than 10 pages, glad they added more detail there.
They also spend time in early chapters talking about preprocessing and cleaning data, something that often is glossed over.
[0] https://web.stanford.edu/~hastie/ElemStatLearn/
[1] http://www-bcf.usc.edu/~gareth/ISL/