I have wrapped up the Coursera Mining Massive Datasets class put on by Stanford University. This course was really challenging to me because I had too much on my plate at the time I started the course. It introduced me to MapReduce concepts, some new tools like Support Vector Machines, and some interesting treatment of ideas I currently know. It was nice to both deepen and expand my knowledge. This course was unusual as they broke it out into basic and advanced tracks. I found the advanced track questions easier than I found the basic questions. The only think I disliked about this course is that I had a week between the end of the lectures and the final. This was a handicap for me as I picked up some other projects (more on this to come) and wasn’t as focused as I could be.
One of the distractions I picked up was a Kaggle competition. I personally find classification problems to be really interesting so I thought I would play around and try my budding skills out on a Kaggle competition. I am not in the running for prize money (yet) and am having fun trying out what I know and picking up some new things. I hope to have a full writeup of this experience once the competition is complete in a few days.