How does the Stumbleupon algorithm really work.? I have no idea, and I doubt anyone else really does know for sure, other than core programmers at Stumbleupon.
I do know one thing though, Tim is probably the person who has spent the most time studying Stumbleupon, analytically.
Whilst I really appreciate facts, where there are a lack of facts I appreciate discussions that at least try to create models based upon extensive research data
You might find this a little geeky, but for those that like delving into how things might work, Tim’s modelling of the Stumbleupon algorithm is just pure gold.