News for hackers. Stuff that matters.
Re:Categories of deep recommendation systems by inertiatic on Saturday December 28, 2019 @02:54PM (#21901300)
Most recommendation systems are collaborative filtering + some fine tuning.

I don't see how collaborative filtering can not work. Especially in the case of modern media providers where they have data about whether you actually finished watching something, how many videos of a series you watched etc.

Re:Categories of deep recommendation systems by pps43 on Saturday December 28, 2019 @03:20PM (#21901476)
Collaborative filtering cannot recommend new stuff. By the time all your friends have watched and liked the new hotness it's already too late to recommend it to you.
Re:Categories of deep recommendation systems by inertiatic on Saturday December 28, 2019 @03:48PM (#21901620)
By the time a single person with highly similar tastes to me has high engagement to a new item, that can be suggested, by providing a boost to new items.

I'm not familiar with what the best approaches for the cold start problem of getting that first (few) interaction(s) are, but in the case of Netflix it's easily handled by a new on Netflix section.

Re:Categories of deep recommendation systems by zwaps on Sunday December 29, 2019 @06:44AM (#21905415)
The problem of recommending something (especially something genuinely new) is actually quite complex, which you realize by studying inferential/causal statistics.

A statisticians would say that you are making "heroic assumptions" about both the taste of viewers, and the dimensions of the product, especially given that the products you have are actually quite sparse. Heck, there's even interesting literature in empirical economics (called empirical industrial organization) trying to estimate prices/demand/costs (which is, essentially the same issue as Netflix trying to estimate what you like) and dealing with the inherent curse of dimensionality. This becomes really obvious if you are actually write down explicitly what you are doing.

Of course ML engineers are engineers and not really interested in causal inference, so Netflix wants me to watch 12 Hitler documentaries in a row and Amazon recommends that I better buy that second fridge right after the first.

Where _does_ collaborative filtering actually work?