Get insights from the Netflix, Amazon, etc. on recommendation engines

[sonyahanson]

Fun stuff. Some interesting insights here already, from these two blog posts from Netflix (though they're already >2 years old):

http://techblog.netflix.com/2012/04/netflix-recommendations-beyond-5-stars.html
http://techblog.netflix.com/2012/06/netflix-recommendations-beyond-5-stars.html

-> 'optimizing for diversity as well as accuracy' and having categories, because maybe you're not always in the mood for the same salad? We can pick and choose what from these is relevant to us.

[sonyahanson]

also

If you are looking for a ranking function that optimizes consumption, an obvious baseline is item popularity. The reason is clear: on average, a member is most likely to watch what most others are watching. However, popularity is the opposite of personalization: it will produce the same ordering of items for every member. Thus, the goal becomes to find a personalized ranking function that is better than item popularity, so we can better satisfy members with varying tastes.

[sonyahanson]

Wikipedia link to 'the family of machine learning problems known as learning to rank'.