Blake Shaw, a data scientist at Foursquare, gave a great talk at Datagotham. The visualization of New York City check-ins, at the beginning of the video, is simply amazing. It is worth watching the video just for that. However, after seeing that great visualization, you will be persuaded to watch the rest of the video. This talk is an excellent example of what good data science and visualization can do.
Once again, California Institute of Technology will be broadcasting Learning From Data online. This is an introductory course on machine learning. All of the videos are broadcast live, and online homework and discussion forums are available. I have not participated in the course, so I would love some comments about how this class compares with the Coursera machine learning course.
Matthias Vallentin, a computer science PhD student at UC Berkeley, has published a Probability and Statistics Cookbook. The book can be freely downloaded in PDF format via the website. Also, the latex source is available on Github. Matthias states that others are free to fork the source and make changes.
The book is not a textbook. It is more of a cheatsheet. It contains many of the common probability and statistics techniques and the associated formula. I would consider this book to be an excellent resource to have around.
Have you ever seen the movie Moneyball? It is about winning baseball games with a low budget and great data science (that is a gross oversimplification). Well, Numberfire tries to do that on way more sports than just baseball. Numberfire considers themselves a Sports Analytics company. I had never heard of Numberfire before, and just the other day I was wondering if there are companies trying to provide better data for people playing fantasy football. So, the timing of this video was excellent for me. Nik Bonaddio, the CEO of Numberfire, gives a quick overview of what Numberfire does and how it works. Hint, it involves lots of Markov Chains.
By the way, if you have not seen the movie Moneyball, I highly recommend it.
“The Human Face of Big Data” is an intriquing project. Check it out.
Jake Porway of DataKind gives another entertaining talk. This one is more of a Superhero story. Just watch the video, and it will make sense.
This video was different than I expected. I expected to hear how the National Football League (NFL) is using player statistics for better player acquisition and fantasy football. However, the talk was about the NFL business model. The business model of the NFL focuses on filling stadiums. Thus the NFL starting collecting data about why fans prefer to watch games at home and what do fans really want from an NFL game. The NFL now generates numerous reports to help each individual team maximize the in-stadium experience.
Here are some of my thoughts on the talk.
- The NFL maybe needs to invest in a data visualization expert
- The NFL maybe needs to rethink the business model
A few notable courses for data science are: a new machine learning course from the University of Washington, Linear Algebra from Brown, and Natural Language Processing by Michael Collins from Columbia.
See the following pages to seed what other courses are now available.