Tuesday, December 18, 2012

Some Interesting Videos / Talks

Interesting talk by Jeff Hammerbacher on some of the things he's doing with Data Science in Healthcare / Genomics

I have recently become a huge fan of Nate Silver and Statistical Bayesian Inference. He recently gave a talk at Google


Saturday, November 10, 2012

Nate Silver and the new Numerati

By now, we probably all know who Nate Silver is. He correctly forecast the result in 49 out of 50 states and all 35 US Senate Races in the 2008 election cycle and all 50 states in the 2012 election cycle. How did he do this? Bayesian Analysis. Ignore all the political pundits.. Nate simply removed the noise from the true signals. You can check out his 538 blog at the New York Times for more details.


We have also learned that the Obama campaign engaged in a massive data mining operation with micro - targeting and voter segmentation that many could say helped them win. They hired Data Scientists to build predictive models for everything from potential voter turn out, potential voters, fund raising through email campaigns to finding out which email campaigns raised the most money and why. This was recently featured in Time Magazine. If 2008 was the Facebook election, you could say 2012 was the data election.

Nate recently published a book 'The Signal and the Noise' . It should make for an interesting read.

Wednesday, October 31, 2012

Slides from “Survey of Text Mining / NLP in R” talk #rstats

Here are my slides from Survey of Text Mining / NLP in R talk delivered at the October Meetup of the Austin R User Group