I adore Discover Weekly. No lesser adjective will do.
Now turn the data into a dating/social app so users can discover the cools that share their exceedingly good taste in music.
Spotify’s Discover Weekly: How machine learning finds new music
91–100 of 275 posts
Re: Spotify’s Discover Weekly: How machine learning finds new music
#92Sometimes 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.
FWIW I find probably 1/3 of my music through DW, 1/3 through manually browsing related stuff on Spotify (if I discover a new artist and see they were featured on a compilation, I might listen to that compilation) and 1/3 from real life (friends' recommendations, unknown bands from festivals etc). For my pattern of use, DW is varied and absolutely amazing. I only listen to my DW probably 1 week in 4 though.
Re: Spotify’s Discover Weekly: How machine learning finds new music
#93If there is at least one song that I like in Discover Weekly, then I consider it to be a good mix. However, this happens once a month at best. After reading the article and all three methods for recommendations, I cannot understand how on Earth it comes up with its suggestions. Do I feed it bad data? Does it not take into account the relative "weight" of a particular track, i.e. my preference to listen to it multiple…
Same experience on my end. I mean, the recommendation system is better than nothing, but I very rarely find something I really like based on it.
Re: Spotify’s Discover Weekly: How machine learning finds new music
#94If there is at least one song that I like in Discover Weekly, then I consider it to be a good mix. However, this happens once a month at best. After reading the article and all three methods for recommendations, I cannot understand how on Earth it comes up with its suggestions. Do I feed it bad data? Does it not take into account the relative "weight" of a particular track, i.e. my preference to listen to it multiple…
I don't always keep forever tracks found on discover weekly, but I usually enjoy most songs that are on it when I am in the mood for new things.
Re: Spotify’s Discover Weekly: How machine learning finds new music
#95Other Spotify features include: your daily mix (like discover weekly, but daily, and providing an individual playlist per each genre), release radar, charts, suggesting songs given a playlist, and creating a radio from a song.
Re: Spotify’s Discover Weekly: How machine learning finds new music
#96Earlier quoted context omitted.
They do have a dislike button though, the thumbs down icon next to the play controls (on the desktop version of Spotify).
It's there only if you listen to a radio, not to a playlist.
Sometime within last month it appeared for discover weekly too, at least on mac client - https://imgur.com/a/QJluP
Re: Spotify’s Discover Weekly: How machine learning finds new music
#97Earlier quoted context omitted.
Time to introduce her to Moana for a change of pace.
Interestingly (and now very off topic), she hasn't even seen Frozen. She does not yet know it is a film AFAIK, and I'm in no hurry to tell her. I believe that the concept of Frozen has been explained to her by her peer group, through the medium of hair plaits. Three year old kids are a weird and amazing bunch.
Thinking about it a little more, we've listened to a lot of Moana / Frozen / Disney on my Spotify account and none of that has come up in the Discover Weekly, so I guess they filter for it somehow already. Though I guess when they compare to other people with the same tracks you'll probably get a bunch of listeners that fall into a similar category anyway. Also, it doesn't sound like the number of times you play a track adds a huge amount of weight anyway.
Re: Spotify’s Discover Weekly: How machine learning finds new music
#98If there is at least one song that I like in Discover Weekly, then I consider it to be a good mix. However, this happens once a month at best. After reading the article and all three methods for recommendations, I cannot understand how on Earth it comes up with its suggestions. Do I feed it bad data? Does it not take into account the relative "weight" of a particular track, i.e. my preference to listen to it multiple…
The algorithm doesn't seem to work at all for me as well. There's usually just a single song that I actually like in the discover weekly list every other week.
Re: Spotify’s Discover Weekly: How machine learning finds new music
#99Sometimes 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.
For some reason every week I get like 2-5 songs with the same beat, but a bit remixed or covered by someone else. It's trying way too hard to recommend similar songs sometimes.
Or even just featured in a single / best-of album from the same artist. I'm fairly sure my "library" now contains a bunch of duplicates due to this.
Re: Spotify’s Discover Weekly: How machine learning finds new music
#100Discover weekly is usually just generic garbage. The daily mixes aren't much better, usually playing the same songs over and over in a different order.
I have a ton of songs that I've found over time that I like that spotify has managed to kill for me.
I really enjoyed soundcloud's music and tended to find way more interesting stuff on there. Too bad it's apparently run by morons.