As noted in the last round, this is a pretty light introduction to recommendations targeted mostly at only moderately technical folks (the audience of the blog that published it).
If you just want data sets drop me a line, though most of the ones we test with are probably prohibitively large for just playing around with (millions of links / ratings). O'Reilly's Programming Collective Intelligence gives some decent background information, but in my opinion doesn't really cover enough to build a real system. A couple papers I often suggest with a lot of practical content are:
Toward the Next Generation of Recommender
Systems: A Survey of the State-of-the-Art and
Possible Extensions
That one's fairly readable for people outside of the field. The Google News paper, which has some insights on doing large scale recommendations on a fairly dense user to item matrix, is a little more jumping into the deep end, but is worth glancing at even just to follow the references it sites:
Google News Personalization: Scalable Online Collaborative Filtering
http://news.ycombinator.com/item?id=548584
http://www.gruenderszene.de/it/we-think-youd-also-like-and-t...
As noted in the last round, this is a pretty light introduction to recommendations targeted mostly at only moderately technical folks (the audience of the blog that published it).