[HN Gopher] Sibyl - Prediction Service at DoorDash
___________________________________________________________________
Sibyl - Prediction Service at DoorDash
Author : bothra90
Score : 20 points
Date : 2022-01-23 12:44 UTC (1 days ago)
(HTM) web link (doordash.engineering)
(TXT) w3m dump (doordash.engineering)
| bradknowles wrote:
| Wait, so they are actively encouraging Sybil attacks?
|
| See https://en.wikipedia.org/wiki/Sybil_attack
| iratewizard wrote:
| I think it's a coincidence. Sybil is reference to the book /
| movie about multiple personality disorder. Both deal with
| multiple personality systems.
| woodruffw wrote:
| I assume it's a reference to the ancient Greek prophetesses[1].
|
| [1]: https://en.wikipedia.org/wiki/Sibyl
| monkeydust wrote:
| I'm yet to have the 'wow' moment from any recommendation
| service.... Netflix, Amazon, Deliveroo... At best I get the 'meh
| why not'. It's obviously a hard problem to solve.
| o_____________o wrote:
| Try TikTok for a few weeks, genuinely
| ec109685 wrote:
| TikTok is optimized to get as much signal as possible from
| users, as well as they were smart about getting some signal
| from the videos themselves:
| https://www.eugenewei.com/blog/2020/9/18/seeing-like-an-
| algo...
|
| Something like Amazon gets very little signal after you
| bought something whether you really liked it or not.
| Zababa wrote:
| My view on this is that recommendation services are made to try
| to funnel people to the same thing. While they sell some kind
| of "hyper personalization", they're just another kind of
| classic marketing. Especially for Netflix. Talking about series
| you watched seems to be a big part of watching series, so
| pushing people to watch the same stuff works better.
| loceng wrote:
| If they had the full catalogue of all movies and series ever
| made then it'd easily be much easier to actually make more
| relevant recommendations, but their catalogue is actually
| shrinking as they have less old content they've been able to
| renew since those content owners have been starting their own
| streaming services.
| postexitus wrote:
| Amazon, the book store has everything published under the sun
| and still cannot recommend something better than "oh, here
| you go, this is sci-fi as well!".
| loceng wrote:
| They arguably don't have your view history though, though
| their relatively new streaming service will be likely
| changing that slowly.
| chrisjarvis wrote:
| What about Youtube? Im surprised to not see them mentioned in
| any of the comments under yours. For all their faults, I
| regularly am recommended amazing(ly interesting to me) videos.
| vernie wrote:
| I read that something like 60 hours of video are uploaded to
| YouTube every second, so I find it hard to believe that the
| best stuff they can recommend is the same handful of 9 year
| old videos I've already watched sprinkled with dogshit right
| wing American political content.
| Hokusai wrote:
| > It's obviously a hard problem to solve.
|
| Or maybe that is not the problem they are trying to solve. They
| optimize to sell as much as possible, not to get you the best
| experience.
|
| It's like asking for the most shopped articles that are the
| ones farther away. Is it difficult to design better
| supermarkets? Or are they just optimizing for you to spend more
| time and money inside?
| clevergadget wrote:
| tiktok is the only one i think
| tyingq wrote:
| The "Shadow predictions" bit is interesting. They could set that
| up in a way to score it versus actuals...where the shadow
| implementation automatically becomes the live one once it's
| better than the incumbent.
| sepiasaucer wrote:
| People are commenting on the quality of Door Dash predictions,
| but that isn't what the article is about. The article is just
| about the architecture for high speed/throughput of prediction
| requests.
|
| I would be interested in knowing how much improvement they saw by
| using C++ or Kotlin. Also, I don't really understand what compute
| service is actually used to run the model predictions in this
| framework.
| wdb wrote:
| Sibyl, was also the name of the Delphi clone for OS/2 :)
| Forge36 wrote:
| I just cancelled my membership (was free with a credit card i
| already had).
|
| They offered a "free membership" for 10 months "at a $120 value"
| (which used to be $60 a year), however I couldn't figure out how
| to activate it.
|
| I can't figure out what the value is over other services/direct
| from restaurant. Like another poster, most of the suggestions
| were bad. "Do you want dairy queen?" Or "quick you can order free
| from Kwik Trip in the next 10 minutes".
|
| The post makes the suggestions look good. My top recommendation
| is the cheesecake factory. Followed by McDonalds. Who are they
| targeting? Who is getting McDonalds delivered?
| decremental wrote:
| I get McDonald's delivered all the time. Can't beat 13 minute
| delivery for coffee in the morning.
| woodruffw wrote:
| Do you order anything besides coffee? Maybe I'm
| misunderstanding, but why would you wait 13 minutes for
| someone to drop off $1 of distinctly average coffee?
|
| (I say this as someone who has ordered McDonald's through
| DoorDash before.)
| dfsegoat wrote:
| It's a $12 minimum order where I am anyway. So you pay $12
| whether you have $12 of items or not.
|
| So, I am guessing GP has a couple egg-mcmuffins in there
| somewhere.
| vorpalhex wrote:
| My coffee routine only takes 8 mins from whole beans to v60
| pour over, most of that the kettle warming.
| samcheng wrote:
| ... with MUCH better-tasting coffee than e.g. McDonald's as
| a bonus!
| withinboredom wrote:
| We get McDonalds delivered all the time. We don't have a car.
| dangrossman wrote:
| I get McDonalds delivered. Why not?
| iratewizard wrote:
| One of my wife's assistants likes McDonald's. A weekly reward
| for no products breaking in shopping when she does packaging is
| lunch. The cost of having McDonald's delivered is far less than
| the opportunity cost for her to pick it up (and obviously for
| us too).
| jorblumesea wrote:
| McDonalds is one of the most popular restaurants in all of
| America. Forget DD, probably 10% of America orders McDonald's
| every day. It's not that surprising. It probably keeps pretty
| well during delivery because it's designed to be under a warmer
| for long periods of time.
| hobs wrote:
| I see posts like this and just think that as far as I can tell
| DD's recommendations are: Ads Ads Ads
| Shitty place nobody would want to eat Shitty place nobody
| would want to eat Shitty place nobody would want to eat
| Shitty place nobody would want to eat Oh look something
| interesting
| netizen-936824 wrote:
| Doordash: Hey try this new place! _lists taco bell_
| woodruffw wrote:
| I have the same experience as you, and it's one of the main
| reasons why I try to call places for takeout instead (or use a
| local app).
|
| I (idly) wonder whether they're optimizing for the wrong(?)
| things: throwing a bunch of garbage up front maximizes the
| amount of time that I spend in-app, which is probably one of
| their key metrics. What they don't(?) realize is that I'm
| spending all that time filtering through the dreck, and so the
| metric is really measuring my frustration and not my
| engagement.
| bastardoperator wrote:
| I predict they'll get my order wrong or leave something off
| despite charging me and deliver my food cold.
___________________________________________________________________
(page generated 2022-01-24 23:05 UTC)