Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Real World Recommendation System

blog.fennel.ai

Post reply on HN
Print view View original

91–100 of 156 posts

Re: Real World Recommendation System

#91

Post by jenny91 »

lysecret wrote: post #64
greatpostman wrote: post #36

I’ve built one of these at FAANG. Generally the different parts of the system are completely separate teams that interact through apis and ingest systems. Usually there’s a mix of online and offline calculations, where features are stored in a nosqldb and some simple model runs in a tomcat server at inference time, or the offline result is just retrieved. Almost everything is precomputed. We had an api layer where an…

Yea same here. What Nosql DB did you use for these lookups? Im currently using postgres for it but seems a bit like a waste. Even though the array field is nice for feature vectors.

Presumably they mean internal stuff like google bigtable or equivalent. (Though some version of that is now on gcp).

Re: Real World Recommendation System

#92

Post by chudi »

notriddle wrote: post #77
chudi wrote: post #47

Earlier quoted context omitted.

all feeds are recommendations systems, instagram, facebook, twitter, tiktok, youtube, every single one is a recommendation system.

Technically, yes, but when they're talking about this sort of thing, they mean "personal recommendation system" or "content-based recommendation system." For example, the HN front page is a recommendation system if you literally mean system-that-recommends-web-pages-to-look-at. But it's not personalized; every visitor sees the same front page. This fundamentally makes it a different sort of thing.

If You have 10000 posts that You have to sort it in some way and the user just going to see 20 of those, the sorting is the recommendation system, people are just used to think of products, movies and songs, but in those platforms the users are the products

Re: Real World Recommendation System

#93

Post by samhw »

jedberg wrote: post #56
oofbey wrote: post #51

Off-topic, but how did Netflix manage to get itself inserted into the FAANG acronym anyway? Their impact on the tech industry is trivial compared to all the others. Sure, if you just take out the N it's offensive, but we could have said "GAFA" or "FAAMG" would be more accurate to include Microsoft in their place.

FAANG was created by the TV personality Jim Cramer to talk about high growth tech stocks. At the time Netflix was doubling every year. It was based purely on finance. It's now been taken over by the tech industry to be shorthand for places that are highly selective in their hiring and tend to work on cutting edge tech at scale. That being said, the impact of Netflix on tech is pretty big. They pioneered using the clo…

> FAANG was created by the TV personality Jim Cramer to talk about high growth tech stocks. At the time Netflix was doubling every year. It was based purely on finance.

That, and FAAG had less of a ring to it.

Edit: Dammit, the GP made the same observation. Oh well, I'm keeping it.

Re: Real World Recommendation System

#94

Post by lmc »

whimsicalism wrote: post #78
lmc wrote: post #40

Earlier quoted context omitted.

Much of the field seems to be fixated on throwing massive compute resources at models with results that can neither be evaluated nor reproduced. "the Recommender Systems research community is facing a crisis where a significant number of papers present results that contribute little to collective knowledge […] often because the research lacks the […] evaluation to be properly judged and, hence, to provide meaningful…

By "the field", you surely mean the academic field. In the industry, we run controlled experiments to validate all the time. Recommender systems is one of the few areas in ML where almost all of the knowledge is contained in industry, not academia.

That was my thinking - anything of value is product-specific and behind closed doors. It's not my field, but something I see come up from time to time that seems weirdly over-represented in ML articles.

Re: Real World Recommendation System

#95

Post by samhw »

troiskaer wrote: post #82
oofbey wrote: post #65

Earlier quoted context omitted.

No question they've done some things that have had some impact on others in the industry. But none of them are particularly important. It's all relative. Companies like Twitter, Uber, AirBnb have all released open source projects or figured things out how to solve hard problems in ways that others have emulated. But for every other one of the FAA(N)G companies, I can barely work a day as a developer without touching…

> But none of them are particularly important Nowhere was the argument made that somehow Netflix was more influential than Twitter/Uber/AirBnB, but your counter-argument that somehow it's less influential because you haven't heard of/used some projects directly holds no ground.

> your counter-argument that somehow it's less influential because you haven't heard of/used some projects directly holds no ground

Oh come on, they are indisputably right that Microsoft, Twitter, Uber, Airbnb, hell, even Cloudflare are more technically influential than Netflix is.

Apple and Google would make anyone's top 5, that's his point. No argument about it. Their products collectively dominate anyone's life, along with MSFT. Netflix is maybe in your top 10, top 20 for sure, but it's not up there as one of the few 'platform that everyone's lives are built on' techcos.

(Like, Netflix vs Microsoft? Seriously? For that matter, Amazon probably wouldn't be in my top 5 either, and not only because it's not mainly a tech company. I s'pose it depends how you define 'Amazon', and if you include AWS. But for Netflix there's just no argument that they win a spot there.)

Re: Real World Recommendation System

#96

Post by keewee7 »

colesantiago wrote: post #45
mrfox321 wrote: post #29

Earlier quoted context omitted.

TikTok

Why TikTok in particular? What is the engineering story behind TikTok's recommendation system? How did they get it right?

TikTok seem to be learning from what the user is actually watching and for how long and not just the user's "Like"/"Not Interested In" actions. However it still seem to learn from the "Not Interested In" action more than any other platform.

Re: Real World Recommendation System

#97

Post by notriddle »

chudi wrote: post #92
notriddle wrote: post #77

Earlier quoted context omitted.

Technically, yes, but when they're talking about this sort of thing, they mean "personal recommendation system" or "content-based recommendation system." For example, the HN front page is a recommendation system if you literally mean system-that-recommends-web-pages-to-look-at. But it's not personalized; every visitor sees the same front page. This fundamentally makes it a different sort of thing.

If You have 10000 posts that You have to sort it in some way and the user just going to see 20 of those, the sorting is the recommendation system, people are just used to think of products, movies and songs, but in those platforms the users are the products

This hardly seems like a reasonable way to characterize Netflix, which has a personal recommendation system, especially compared to HN, which is ad supported yet gives the same recommendations to everyone.

Re: Real World Recommendation System

#98

Post by samhw »

efsavage wrote: post #90
KaiserPro wrote: post #17

> As a result, primary databases (e.g. MySQL, Mongo etc.) almost never work I mean it does. As far as I'm aware Facebook's ad platform is mostly backed by hundreds of thousands of Mysql instances. But more importantly this post really doesn't describe issues of scale. Sure it has the stages of recommendation, that might or might not be correct, but it doesn't describe how all of those processes are scheduled, coordin…

> mostly backed by hundreds of thousands of Mysql instances Kind of. It's part of the recipe but one you find at these large tech companies (I've worked at FB and GOOG) is they have the resources to bend even large/standard projects like MySQL to their will, while ideally preserving the good ideas that made them popular in the first place. There are wrappers/layers/modifications/etc that eventually evolve to subsume…

I mean, this post from a year ago makes it sound not that non-standard: https://engineering.fb.com/2021/07/22/data-infrastructure/my...

What you're describing sounds like you mean something on the level of Cockroach, talking the Postgres wire protocol but implemented entirely independently underneath (which came indirectly out of Google). Facebook's MySQL deployment sounds more like a heavily-patched-but-basically-MySQL installation. I think Facebook is overanalogised to Google sometimes, as an engineering org.

(Admittedly I haven't worked at either whereas you have - though I have at another FAANG fwliw - but am basing this impression partly on what I hear from friends & partly on plain old stuff I read on the internet.)

Re: Real World Recommendation System

#99

Post by samhw »

samstave wrote: post #33
vikingcaffiene wrote: post #3

Gentle reminder to anyone reading this that your problems are probably not FAANG problems. If you architect your system trying to solve problems you don't have, you are gonna have a bad time.

Wow, this is something that has been a floater-in-mind for decades ; I'll top it off with an interview at Twitter with the Eng MGR ~2009-ish? -- Him: So tell me how you would do things differnetly here at twitter based n your experience? ME: " Well, I have no idea what your internal processes are, or architecture, or problems, so my previous experience wouldn't be relevant. " I'd go for the best option that suits goa…

> Wow, this is something that has been a floater-in-mind for decades

Have you literally never come across the "you're not Google!!!" trope before now, during the whole ~decade leading up to this very day? Gosh I envy you.

(Also, I am reaaally struggling to understand that story. Who is speaking? It sounds like a story within a story within a story. I can just about piece together the gist, but I'm very confused by all the formatting and nested quotes.)

Post reply on HN