Comments on: Small book review: Super Crunchers

By: Data Mining Book Review: Freakonomics | Data Mining Research - www.dataminingblog.com

Sat, 10 Sep 2011 23:14:43 +0000

[...] Seven Levitt and Stephen Dubner, a very interesting reading. It’s the same kind of books as Super Crunchers (Ian Ayres) and The Numerati (Stehen Baker). The concept is to explain given case studies using [...]

By: Christophe Giraud-Carrier

Christophe Giraud-Carrier — Wed, 20 Feb 2008 16:34:00 +0000

Thanks for pointing out “Competing on Analytics”. I just ordered the book. I did, however, very much enjoy Ayres’ book. He seems to focus exclusively on regression as a his tool of choice and provides little details indeed about the various applications he mentions. However, he does a very nice job, I think, at making things accessible to a broad audience and several of the examples are rather compelling as they clearly show how data mining (super crunching, or whatever you wish to call our science) often challenges conventional “wisdom”. I am rather certain that Ayres did not write the book for experts but rather for lay people. As such, I think the book is a success, and should certainly help people better appreciate our science and what it can offer. We can always argue about the choice of names, and some of the assertions that Ian does indeed make (and that we could easily take up issue on), but again, overall, I think the book is a welcome boost to data mining in general. I am eager to see what additional light “Competing on Analytics” sheds on our fascinating science. By the way, James, thanks for your review of it, that you pointed to in your comment.
Christophe (http://datamininglab.blopspot.com)

By: Sandro Saitta

Sandro Saitta — Tue, 12 Feb 2008 09:52:00 +0000

Thanks for mentioning “Competing on Analytics”, I didn’t know the book. I agree with you on the issue of using “super crunchers” instead of “data miners”. However, since this book is more about vulgarizing the field, I find it alright.

Ayres states that super crunching is not as easy as data mining, since it concerns decision support on real-life data. This is were I disagree with him (about the definition of what data mining really is).

By: James Taylor

James Taylor — Tue, 12 Feb 2008 00:30:00 +0000

While I liked Super Crunchers somewhat (review here), I did not find it as useful as Competing on Analytics (review here). Ian writes well but his refusal to call data mining and data miners by their correct name was irritating and he waved his hands a little too often for me - making assertions and not drilling down.
Anyway, worth reading both books I think
JT

James Taylor
Author, with Neil Raden, of Smart (enough) Systems