The instruction of the bootcamp was really top notch — both Phuc and Dave were great. This bootcamp serves as a really solid and surprisingly thorough introduction to data science. The take-home course materials seem to be a really valuable reference. Specifically, I found the random forest, bagging, boosting, and cross-validation sections to be very useful.
Prior to the course, I had some basic understanding of machine learning. Looking at class participants, I think absolute beginners can get started and start predictive modeling in just two days. Very well planned and very focused.
I loved the course. Using R to do predictive modeling and analyzing data is a great resource to have in a developer’s list of tools.
I think participating in Kaggle was a good addition. By doing that, I was able to go online and look at what others were doing with the titanic data. It also gave me a sense of achievement when I posted my results for the first time, and scored somewhat better than average.