←back to thread

226 points cloudfudge | 3 comments | | HN request time: 0.001s | source
Show context
freedomben ◴[] No.41882074[source]
I think this is great, but I do hope thought is being put into solving the hardest problem of all IMHO: Music Discovery

I have bought a lot on Bandcamp, but would have bought 10x more if I could just find stuff I liked. The existing system makes discovery nearly impossible unless you happen to like the stuff being mainly bought and curated or are in a lucky genre.

Discoverability is especially hard because 99% of the music people create sucks. This may not seem true if you mainly listen to "radio" and playlists, but if you ever get access to a large catalog of independent music, try picking stuff at pseudo-random and take notes. As much as I love good art (and I do), most art is not good art. You can't go on popularity because some of the great artists (especially on Bandcamp) are relatively unknown and therefore are not popular. For example, Thousand Needles in Red is a phenomenal band with great albums, and almost completely unknown. These Four Walls is similar (but at least they are on Youtube Music/Spotify/etc). I'd buy the crap out of similar albums, but discovering them is very challenging. I mainly found those two out of random luck.

Anyway I'm rambling, but I do hope you can figure out a good means for discovery. I think finding and grouping people with similar tastes is among the best ways, and also having artists that a person likes recommend other artists can be super valuable.

replies(13): >>41882220 #>>41882254 #>>41882413 #>>41882664 #>>41882844 #>>41882884 #>>41883148 #>>41884081 #>>41884158 #>>41884351 #>>41884652 #>>41885908 #>>41886016 #
mg ◴[] No.41882413[source]
I run a self-learning music discovery engine called Gnoosic:

https://www.gnoosic.com

I can confirm that when you suggest a random band to a random user, they will dislike it with over 90% probability.

I'd be interested to hear how well Gnoosic works for your musical taste.

replies(8): >>41882554 #>>41882743 #>>41884146 #>>41884795 #>>41885067 #>>41886319 #>>41888340 #>>41896849 #
1. chx ◴[] No.41884146[source]
Band level doesn't quite work. Alas, it needs to be track level. There are a lot of bands where I like a track and that's it.

My favorite example is Seven Sirens And a Silver Tear from Sirenia, a Norwegian gothic metal band. There's no metal in that. It took me a long long time before I learned this but the track is a direct descendant of the Midlight Sonata. And I was hunting for similar songs and I now keep a playlist of them -- but if you started from Sirenia you would never find any of them.

replies(2): >>41886193 #>>41886328 #
2. alisonatwork ◴[] No.41886193[source]
This. There are many, many artists who I only own one or two tracks of - including some of the most-played tracks in my collection - because the vast majority of their other output is not my taste at all. If finding good music was as simple as just buying everything that a single artist put out, it would be much easier to build a collection.

The good news is that in the digital era you no longer need to fork over cash for an entire album or even an EP when you only care about one of the songs - which leaves more money available to buy music from other artists. I often wonder if in the long run it still balances out for artists, since the songs one person likes probably aren't the same as the songs another person likes, especially in niche genres.

3. nxpnsv ◴[] No.41886328[source]
If the track is known, then from the context of this and other things you like, you would still reach useful recommendations in not too many clicks. Track level would be interesting, but is also harder as data is a lot sparser making it harder to build reliable recommendations.