Advice & Resources
In this section, I give you advice on where to start and list resources. Resources are often free online, but sometimes I recommend books and other paid resources. You can always search the blog for past posts—I offer links with the appropriate keywords in each list of resources. I have book reviews in almost all of these areas, and my own books are always an option. Also, consider following me on twitter, @KMcCormickBlog. I tweet several times a week, and often this might point you in the right direction for professional reading or other resources. My reading and elimination of mediocre resources out there might save you some time. Finally, you are always free to contact me.
A great place to start is Meta Brown’s Data Mining for Dummies for which I’ve written full review.
The advantage of this book is that it starts from the very beginning and it is tool-neutral. I know Meta well. She and I both have histories with SPSS Inc., and we collaborated on the SPSS Modeler Cookbook. I have yet to write anything as effective as a first book in this area.
I’ve written blog post, The Essential Elements of Data Mining, that emphasizes some of the differences between Stats and Data Mining that got a fair amount of attention when I wrote it.
My book, SPSS Statistics for Data Analysis and Visualization, has a fairly extensive chapter introducing data mining as an approach. Several chapters in the book address data mining topics. The IBM SPSS Cookbook, with me as lead author, seems a more direct choice, but it is primarily a software book. Readers have suggested that it has also helped explain the theory. I list it under SPSS Modeler Resources.
KD Nuggets. Almost encyclopedic in scope, this website can be overwhelming at first, but it’s got much that will you need: info on conferences, training, workshops, university degrees and more.
The Cross Industry Standard Process for Data Mining (CRISP-DM) is the de facto standard in Data Mining. A KD nuggets poll years ago established that about 1/2 of data miners use this approach—no other approach has as large a following.
Tom Khabaza’s Nine Laws of Data Mining. Tom was one of the key employees at ISL when that company made Clementine. He was also one of the lead author’s of CRISP-DM. All of my colleagues admire the Nine Laws - very insightful. Tom was also one of the coauthors on the SPSS Modeler Cookbook.