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

Spotify’s Discover Weekly: How machine learning finds new music

hackernoon.com

Post reply on HN
Print view View original

261–270 of 275 posts

Re: Spotify’s Discover Weekly: How machine learning finds new music

#261

Post by com2kid »

whiskeySix wrote: post #128
chrissnell wrote: post #71

Earlier quoted context omitted.

I think this might be a huge problem for them and I’m pretty sure that they’re aware of it. The lack of variety seems to span all genres and radio stations. I’m really into Texas Country, Americana, and Red Dirt music. These are distinct sub-genres under “alt-Country” music but from the Spotify perspective, they’re all basically the same 40-50 songs. I can’t tell the difference between the Reckless Kelly, Robert Earl…

Pandora? Really? I've found Spotify to be orders of magnitude better than Pandora for both variety and discovery. Pandora was the first to have competent discovery functionality, and it was impressive for its time, but I'm wondering if this is "good old days" syndrome speaking.

With Pandora I can give it one song, and get a playlist out that won't repeat for a couple of hours (I really wish it was longer!)

With Spotify, I enter in a song, and get lots of stuff from that same artist (something Pandora can't do!) and then after that's done, a bunch of repeats.

Then again my problem may be that I'm trying to use Spotify the same way I use Pandora.

Re: Spotify’s Discover Weekly: How machine learning finds new music

#262

Post by bayonetz »

pdeuchler wrote: post #231

My Foolproof Guide To Managing Your Discover Weekly Playlist: - Only listen to the DW playlist once through. Find the songs you even remotely like, put them in a new playlist. Listen to that playlist instead (I call these playlists "DW-{datestamp}"). - Find your favorite songs in the playlist, explore that artist/album. Even if you don't think you'd like the other stuff listening to more of an artist seems to help su…

Feels like an SEO hacker trying to understand and influence a black box search result ranker like Google's. Which is kind of nuts and you'll always be a step behind. Would be pretty cool and interesting if a recommender like Spotify would publish a guide on how to get the most out of their system. Like what you did, but from the builders themselves.

Re: Spotify’s Discover Weekly: How machine learning finds new music

#263

Post by anjc »

nkozyra wrote: post #218
anjc wrote: post #168

Earlier quoted context omitted.

Relying on collaborative filtering (using play counts, as Spotify do) can lead to non-diverse and non-serendipitous recommendation. If I like Abbey Road then a typical collaborative filtering scheme might tell me I like Sgt Pepper's and Let it Be. Excellent recommendation, but useless if I'm already familiar with the band and the genre. There might be an unknown Japanese band that'd suit my tastes perfectly and I'd n…

That just seems like a narrow net problem than an issue with the approach. Assuming I have some distance function that tells me who's "similar" to me and it's malleable, I should be able to reach those outliers.

Yeah, makes sense, and for sure works for many cases. But there's no meaningful distance between two sets of preferences that have a null intersection.

I've come across this just as a user with regard to film. I reckon that I've watched all of the 10/10 mainstream comedies that have been made in English. I want more 10/10 comedies, so I'll have to look at foreign languages films. But there isn't enough overlap of user preference, due to demographic separation I suppose, to get decent recommendation from other countries. If you start adding metainformation preferences (e.g. must not be in English, must be >9/10 stars etc) then you're back to Content-based recommendation territory (i.e. audio analysis as Spotify are doing)

Re: Spotify’s Discover Weekly: How machine learning finds new music

#264

Post by erikbern »

lobster_johnson wrote: post #258
erikbern wrote: post #242

Earlier quoted context omitted.

We had to build some explicit filters for this at Spotify. For instance we blacklisted Christmas music from being part of the listening data – until them people would get a ton of Christmas music recommendations every January. But to your point, there's a long tail of other contextual things.

Weirdly, some genres seem to be entirely absent. I listen to a lot of jazz and classical, and with the exception of the occasional jazzy pop song, I never get recommendations for those genres. Granted, Spotify doesn't have a huge amount of contemporary jazz (much of what I listen to are imported ECM tracks that Spotify doesn't have, though not all), but it does have a lot of classical. I don't think it's ever recomme…

classical music has notoriously bad metadata on spotify – it just doesn't fit into the data model of artist/album/track. i think that causes the system to filter out a lot of the listening data or fail to find patterns.

not sure what's up with jazz but i'm guessing it could be a similar problem

Re: Spotify’s Discover Weekly: How machine learning finds new music

#265

Post by eziruby »

ricardobeat wrote: post #23

Discover Weekly works well enough for me - I do wish I could exclude devices from influencing that playlist as what I listen while gaming on PS4 is completely different from the rest of the day. It also seems to have a bias towards “big” commercial releases. Spotify’s “intelligence” in general is a huge let down though. Radio stations are extremely limited - more like 15-song static playlists indefinitely on repeat!…

The rdio Radio was actually very good. You can find a similar approach in Mentor.FM (and you can import your last.fm history to feed it).

Re: Spotify’s Discover Weekly: How machine learning finds new music

#266

Post by driverdan »

confounded wrote: post #41
Asdfbla wrote: post #29

Sometimes I wish Spotify added a bit more 'noise' to their recommendations, so to speak. If I don't listen to much music except Discover Weekly for a few weeks, I (subjectively) find that what's recommended to me more or less sounds the same after a while. Either they are afraid to insert new things that stray too far from an optimal recommendation or they forget too much of my listening history.

I’ve noticed that there are certain seemingly-esoteric songs that many people are assigned, and subsequently feel let down upon realizing that they’re (currently) common assignations. It wasn’t because the algorithms recognized their excellent personal taste. “ Didn’t I ” by Darondo seems to be a good example of this. A fantastic, forgotten soul song (and from the Bay Area!) that was assumed to be a recognition of my…

> subsequently feel let down upon realizing that they’re (currently) common assignations

This is a really foreign concept to me. Why would you be let down because other people listen to the same song?

Re: Spotify’s Discover Weekly: How machine learning finds new music

#267

Post by KozmoNau7 »

emodendroket wrote: post #139
KozmoNau7 wrote: post #124

Earlier quoted context omitted.

He can use the "private session" option for that instead.

I wish that option were more easily accessible instead of being hidden away behind multiple menus.

It's right there in the dropdown beside your name in the desktop app.

Re: Spotify’s Discover Weekly: How machine learning finds new music

#268

Post by robteix »

myrmi wrote: post #22
robteix wrote: post #18

Earlier quoted context omitted.

Wrt fear of sending signals, I feel the same. Also, I have a young daughter who often asks me to play music in the car or Google Home and those affect my recommendations. I wish Spotify had some switch I could turn on to temporarily ignore anything I did until I switched it back off.

What you're after is what they call 'private listening' or 'private session': https://support.spotify.com/cz/using_spotify/the_basics/how-...

Oh I didn’t know that! Awesome! Thank you.
Post reply on HN