Live data from Hacker News

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

hackernoon.com

41–50 of 275 posts

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

#41
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 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 makes me wonder about the motivations. Did the IP for this song recently change hands?

(I still get the shivers recalling the month when people kept gleefully playing me “Temporary Secretary” by Paul McCartney; a new discovery from their Discover Playlists. I could have marched to Stockholm to strangle a data scientist.)

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

#42
post #14
post #12

Discover Weekly works really well for me. It surfaces a lot of music I've forgotten about and for the most part provides an interesting collection to listen to. Having said that, I have a very eclectic taste in music, so it's probably harder to hit on things I won't like. My process is to try to listen to it several times through and then pick out the stand out tracks once everything has had a chance to grow on me. O…

Same. Also, anytime I get a bad recommendation I blame my daughter for wanting to listen to the Frozen soundtrack.

Time to introduce her to Moana for a change of pace.

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

#43
post #16

Spotify's discovery engine playlists (Discover Weekly and Release Radar) just don't work for me. I now ignore both playlists and I suspect that the lists are influenced by payola. I've tried training the algo by following artists and saving albums in the style that I would like, but these playlists keep peddling stuff that is way off the mark. Interestingly, the daily mix playlists have responded to this training, bu…

They don't work for me either. Most of the songs I like in these playlists are the songs I already listened to hundreds of times.

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

#44
post #9

I am still missing Rdio in that regard, they were just playing the right songs all the time. With Spotify this is absolutely not the case and it's even far worse than YouTube.

While I haven't found a recommendation engine that works well enough for me, rdio's was very close to it.

It's big feature, among others, was their heavy rotation section - I only followed people that shared a similar taste to mine and we had a really cozy circle of listeners whose current favorites were surfaced by said heavy rotation section. We discussed albums in comment sections, shared playlists and I regularly stumbled upon familiar usernames and friends when discovering new gems. This social component to discovery is completely missing from Spotify, yet it's more powerful than any recommendation engine I have used, including Spotify's attempts, which I'd rate as mediocre.

I miss rdio.

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

#47
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.

Rdio had an option to address that: Its radio / "play similar stuff"-feature would let you select how far you wanted to stray from the original source of the generated playlist. If I remember correctly it went from "same artist" to "adventurous" in 5 steps.

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

#48
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.

Rdio had an option to address that: Its radio / "play similar stuff"-feature would let you select how far you wanted to stray from the original source of the generated playlist. If I remember correctly it went from "same artist" to "adventurous" in 5 steps.

Would you please stop reminding me how much better Rdio was :(

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

#50
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.

Post reply on HN