I thought you were talking about search results and not algorithmic recommendations.
I think most recommendations for video services is done through collaborative filtering and similar ML techniques, meaning you get recommended what other profiles similar to you have watched. It may be possible to infer a profile of "people who like the Office (UK) but will not like the Office (US)" but I imagine it may present challenges, especially if the intersection of people who like both is large.
> I thought you were talking about search results and not algorithmic recommendations.
I don't personally see a distinction in irritation or creepiness here. They can't know I don't want experimental art streetcar or a modern remake. So I have to be a bit forgiving.
Amazon do something more loathesome: they proffer "in the style of" before hits for the actual author.
I think most recommendations for video services is done through collaborative filtering and similar ML techniques, meaning you get recommended what other profiles similar to you have watched. It may be possible to infer a profile of "people who like the Office (UK) but will not like the Office (US)" but I imagine it may present challenges, especially if the intersection of people who like both is large.