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

61–70 of 275 posts

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

#61

Post by KozmoNau7 »

chewz wrote: post #24

With all that AI excitement Spotify, Google Play Music and Apple Music misserably fail at generating good musical recomendations. At least for me. Spotify Discover Weekly was no different for me when I still used Spotify (six months ago). Not only it is not personalized at all it is also quite lame. I am doing enough to seed - following enough artists, genres, liking album, subscribing to playlists but the quality of…

I have the complete opposite experience compared to you. All of my Discover Weekly and Daily Mixes are at least 75% music I like, even if I didn't know it beforehand, or only knew the artist by name.

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

#62

Post by KozmoNau7 »

erokar wrote: post #26

A curious side effect of Discover Weekly is that it sometimes influences what I listen to, i.e. I'm afraid to listen to a song in a particular genre because I don't want Disover Weekly to get the wrong idea. But then again, maybe Discover Weekly knows me better than I do.

Just listen to music. Don't worry, listen to what you like, create your own playlists. Use Discover Weekly for inspiration, not your sole source of music.

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

#63

Post by tomaskafka »

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.

You (and Spotify's team) would like to read this paper; I wish eveyone making recommender systems would.

Recommender Systems for Self-Actualization https://dl.acm.org/citation.cfm?id=2959189

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

#64

Post by KozmoNau7 »

flohofwoe wrote: post #50
dotdi wrote: post #49

I discovered how good Spotify's Discover Weekly was just a few days ago. Basically, I liked all but 2 songs on that list. My taste in music is also rather specific, which made it even more impressive. I shall see how the following weeks fare.

It's nice the first few times, but after a while I get the impression that I'm trapped in a "Groundhog Day" loop and hear the same music over and over again. Spotify should add a slider that lets me widen or narrow the 'search area', sometimes I want to hear more similar music, sometimes I want to find more stuff at the edges where all the interesting stuff lurks.

Spotify seems to mostly stick with the ~5 or so most popular song by a particular artist, so I am seeing some repetition. I don't mind, since I like most of those songs, but you should really take them as artist recommendations, and explore their other songs.

I've found, that if you put in more effort into discovering music yourself, Spotify's recommendations improve.

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

#65

Post by treerock »

Fabled wrote: post #57

In case you didn't know, Spotify categorizes music into genres behind the scenes. You can use this site to find out what genres your favorite artists are categorized as: http://everynoise.com/engenremap.html You can use this information to then check out Spotify's auto-generated playlists for each genre. They have at least three types for each one: "The Sound of ", containing definitive representation of the genre, "…

I've been using Discover Weekly for a few years now and haven't had that problem. The only annoyance that it sometimes adds a song I already have saved (and therefore have no need to 'discover').

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

#66

Post by KozmoNau7 »

HearMeRoar wrote: post #28
tjoff wrote: post #25

Discover Weekly is weird. For the longest time it kept recommending Finish music (roughly 30% of all recommendations), I'm from Sweden and barely ever listen from anything from Finland (or Sweden for that matter). They have a ridiculous bias towards covers. I bet I've been recommended 50 (I wish that was an exaggeration) version of the Gladiator theme ('now we are free'). And they are all terribly bad (as in blood co…

I’m from Sweden too and I always get at least 2 german/danish songs in my discover weekly and I hate it.

Entschuldigung/undskyld

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

#67

Post by KozmoNau7 »

tjoff wrote: post #25

Discover Weekly is weird. For the longest time it kept recommending Finish music (roughly 30% of all recommendations), I'm from Sweden and barely ever listen from anything from Finland (or Sweden for that matter). They have a ridiculous bias towards covers. I bet I've been recommended 50 (I wish that was an exaggeration) version of the Gladiator theme ('now we are free'). And they are all terribly bad (as in blood co…

In my experience (listening to ~95% metal/hard rock), all of the automated playlists work amazingly well.

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

#68

Post by chrissnell »

cr1895 wrote: post #54
confounded wrote: post #41

Earlier quoted context omitted.

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…

>“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 friend’s unique taste in his car... until the other four people inside revealed they’d all had it in the last two weeks, too. It could be popularized by DJs who are playing it, e.g. Four Tet, whose personal playlist on Spotify now has close to 39 thousand foll…

It was also used in “Breaking Bad”, in the scene where Walter sets “Ken Wins” BMW on fire. Thomas Golubić was the music supervisor for BB and Better Call Saul and these shows’ playlists make superb additions for Spotify listening, in my opinion. They’re chock-full of great discoveries like Darondo.

It doesn’t surprise me that “Didn't I” comes up in many playlists, but it does surprise me that the other great songs on that album don’t get worked into Spotify stations. This is a great example of their algorithmic problems.

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

#69

Post by hkon »

iddqd wrote: post #58
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 used to listen exclusively to Discover Weekly for a while. One week a finish rap song made it to the list, and I skipped past it every time it came on. Next week there was 2 finish rap songs. Then 5. Eventually half of my discovery list was finish rap, something I have no interest of. Canceled my subscription shortly after. Their algorithms are feeding themselves. I wish they had a dislike button so I could at leas…

EXACT SAME THING, happened to me I considered to create new account just because of this....

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

#70

Post by Cthulhu_ »

iddqd wrote: post #58
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 used to listen exclusively to Discover Weekly for a while. One week a finish rap song made it to the list, and I skipped past it every time it came on. Next week there was 2 finish rap songs. Then 5. Eventually half of my discovery list was finish rap, something I have no interest of. Canceled my subscription shortly after. Their algorithms are feeding themselves. I wish they had a dislike button so I could at leas…

They do have a dislike button though, the thumbs down icon next to the play controls (on the desktop version of Spotify).
Post reply on HN