How useful was the Netflix Prize challenge for Netflix? • Hacker News Board

Re: How useful was the Netflix Prize challenge for Netflix?

#201

Post by stepbeek » Thu, Jul 08, 2021, 7:01 AM UTC

dooferlad wrote: post #110

stepbeek wrote: post #100

Earlier quoted context omitted.

> In the end they will promote what they WANT to be popular This is a hugely important point. I'm completely uninterested in most netflix originals, but I understand why they're going to continue to recommend them to me.

What Netflix wants to be popular also tramples over what I am already watching. I find that the UI gets in the way of enjoying several programs that I am part way through by pushing something new. If they want to continue to make series and only get me to watch half of the episodes then the algorithm is spot on. That said, Amazon Prime video is so much worse. It suggests that I would like to watch series 1 of a show…

iirc amazon video owns their own recommendations distinct from the rest of the company, where previously recommendations were generated from the standard retail systems. I'm convinced that they got worse when this change was made but this is purely anecdotal.

Re: How useful was the Netflix Prize challenge for Netflix?

#202

Post by ctvo » Thu, Jul 08, 2021, 1:39 PM UTC

klausjensen wrote: post #97

koonsolo wrote: post #92

I don't get why they wanted to go all out on AI for this. I use Netflix, and a simple algorithm would already be an improvement: - If I watched a movie and gave it a thumbs down, don't recommend it - If I watched a movie - If I browsed over a movie 50 times, read the info, and still didn't play it, stop recommending it. - If I watched the last episode, remove the "new episodes" banner. WTF

Completely agree. I am constantly baffled at the bullshit Netflix suggests me. I just went to the frontpage of my Netflix and...: - "My list" recommends 3 series where I have alread watched the last episode - "Only on Netflix" recommends another two series, I have already wathed. - A section displayed is "Watch together for older kids" - I dont have kids, never watched any kids stuff on my account. - "Documentaries"…

> Maybe they are just too busy making sure all new series are woke-i-fied to care about how this simple stuff works?

Or maybe it's not as simple as you think? "Baffled" is a strong word. It's the same "baffled" that Amazon can't find all the fake reviews. The same "baffled" that Facebook can't delete all your photos, everywhere, when you close an account.

Maybe things at scale are more challenging? These are some of the most valuable companies in the world. I'm sure they're happy to throw buckets of money at you if you can solve these "simple" problems for them.

Re: How useful was the Netflix Prize challenge for Netflix?

#203

Post by Supermancho » Thu, Jul 08, 2021, 3:44 PM UTC

hobofan wrote: post #65

Supermancho wrote: post #25

Earlier quoted context omitted.

> At the time, Netflix wasn't super high-tech I will admit that it was interesting to see what algorithms were poised to be cutting edge in media recommendation. The result was rather disappointing to me. Netflix STILL isn't that exciting from anything but a compensation standpoint. The problems at netflix are about programming, while the technical challenges are droll at best.

Yeah, I'm sure being responsible for 10% of the internet's traffic is trivial on a technical level, together with all the codec and video encoding engineering they are doing.

> I'm sure being responsible for 10% of the internet's traffic is trivial on a technical level

> the codec and video encoding engineering they are doing

I am confident that is not what the vast majority are working on. Those aren't constrained problems that a single developer would be responsible for. Making unrealistic statements, is more than a little disingenuous.

Re: How useful was the Netflix Prize challenge for Netflix?

#204

Post by anonu » Thu, Jul 08, 2021, 8:11 PM UTC

koonsolo wrote: post #92

I don't get why they wanted to go all out on AI for this. I use Netflix, and a simple algorithm would already be an improvement: - If I watched a movie and gave it a thumbs down, don't recommend it - If I watched a movie - If I browsed over a movie 50 times, read the info, and still didn't play it, stop recommending it. - If I watched the last episode, remove the "new episodes" banner. WTF

There's movies you watched and there's movies you never watched and/or never heard of. Its that latter group that the netflix prize was designed for.

The former group is just simple filters as you point out - which informs the ranking of the second group.

Re: How useful was the Netflix Prize challenge for Netflix?

#205

Post by dmitryminkovsky » Sat, Jul 10, 2021, 2:05 AM UTC

Avalaxy wrote: post #148

dmitryminkovsky wrote: post #3

I've always wondered about this. I first read about this challenge in "Programming Collective Intelligence,"[0] the O'Reilly book from 2007 that drove me to become a professional programmer. It starts like this: > Netflix is an online DVD rental company that lets people choose movies to be sent to their homes, and makes recommendations based on the movies that customers have previously rented. It was a different and…

It's a good book! I read it before we started calling it "artificial intelligence" or "machine learning". It was just data mining back then. I think the book and the algorithms in it are still very relevant today.

I’ve wondered whether that’s the case :)