We host a monthly tech talk series we call Droptalks. In the past, we've hosted Steve Souders, Guido van Rossum, Greg Papadopoulos, and Amit Singh.
A couple weeks ago, we were lucky to have Hilary Mason in town. Hilary is the Chief Scientist of bit.ly, the world-famous URL shortener. Bit.ly may seem like a simple service, however, when done at such a large scale there is much more behind the scenes. There's also a lot of neat data to play with.
Hilary spoke about some of the challenges and lessons from her work trying to derive meaningful uses from the mass of data that flows through bit.ly. She spoke about the history of bit.ly, some of the philosophy of analyzing time-series data, and some cool engineering tricks. She even gave demos of three internal tools at bit.ly that will be released as products in the next few months (really cool stuff!).
And here are the slides.
For those interested in learning more about Analytics and Data Science, Hilary suggested a few introductory books:
- Drew Conway’s and John Myles White’s Machine Learning for Hackers which “uses R on web data and email data”.
- Toby Segaran’s Programming Collective Intelligence – which is “getting a little out-dated, … but it’s a really good introduction to how to think about a machine learning program”.
- “If you just want the math side, … the core canonical math book” is Christopher M. Bishop’s Pattern Recognition and Machine Learning.