Thursday, December 27, 2007
A good resource on statistical data mining
Lately I got myself interested in statistical data mining. I think there's a huge potential in this area which combines mathematics and algorithms. We have exabytes of information in various digital forms and the amount of information doubles roughly every 3 years. This demands us to find new models and algorithms to efficiently and accurately extract useful/relevant information from this vast repository. This is where data mining techniques come into play. I found the set of lecture notes by Andrew Moore to be very useful to get the basic concepts right. I like the simplicity in which he unfolds each lesson.