I am experienced with development, machine learning, and basic stats. So, the "big" part.
(Most of the books I see involve new scripting languages, and I would really prefer to simply work in Java and R.)
EDIT: I am looking for technologies for distributing data and processing (maybe Hadoop?) ultimately for prediction / recommendation. Not married to any particular technology yet. I am also very curious to see discussions about using large data sources directly versus keeping smaller samples.
[link][4 comments]