Re:I changed my mind about advertising
by quietbritishjim on Thursday February 10, 2022 @09:30AM
(#30286437)
I'm not trying to defend ads in general, but one problem that a recommender engine certainly suffers from is how to deal with a new entity. How do you make a new entrant gets into that list even though, while they may provide value, there's currently no evidence of that are far as the recommender is concerned?
[ Parent
| on HN ]
While often ignored, item-to-item similarity recommenders work really well for new items and have been the basis for Amazon's and YouTube's early recommendation algorithms
https://glinden.blogspot.com/2011/02/youtube-uses-amazons-re...
Re:I changed my mind about advertising
by lostcolony on Thursday February 10, 2022 @10:05AM
(#30287085)
I think you may be misunderstanding the parent (I may also be misunderstanding though) - they're saying that with a new user (not a new product), you have no information for providing recommendations to them; you have no idea what they're interested in.
Re:I changed my mind about advertising
by quietbritishjim on Thursday February 10, 2022 @12:38PM
(#30289721)
I was talking about new products/movies/whatever, not users. Sorry, "new entity" was too vague in retrospect.
My point was around the utility of marketing, at least in theory. If I release a new brand of baked beans, how would a recommender based on past sales (and combinations of sales) know to recommend it to anyone. Marketing allows it to go up the list (unfairly, according to the post I was replying to).
Re:I changed my mind about advertising
by lostcolony on Thursday February 10, 2022 @06:03PM
(#30294042)
Ah, okay. Then yeah, the original reply is valid. I assumed you meant a new user to a site, since you can't recommend anything then no matter what you've built (without user tracking that can maybe have built up some kind of profile from elsewhere).
Re:I changed my mind about advertising
by williamtrask on Thursday February 10, 2022 @10:35AM
(#30287603)
This is also a problem ad engines face. Non-unique to recommenders.