[Triphibian]

One of the things I find frustrating about music suggestions is that the app/algorithm doesn't care why you like a certain band. A long time ago I asked Pandora to make David Bowie station and it rolled me a generic classic rock station -- Zeppelin and the Stones. I was hoping for old school glam, maybe T-Rex and Eno. There's no way to communicate that desire to our music players. To say, "please don't think me a basic AF music listener."

I have noticed an interesting phenomenon around TOOL. If you start a playlist on Apple Music from TOOL it will start playing everything from Metallica to Nirvana. A lot of people like TOOL for a million different reasons and Apple doesn't know any different except for the overlaps in taste. If you play a Mike Patton band, such as Mr. Bungle though -- you will get some TOOL in your playlist -- because both bands are esoteric and often challenging.

I'm looking forward to the day (or wishing maybe) when my app considers these factors. For me the issue isn't discovery, but rather I want my robot DJ to vibe more closely with me.

[Terr_]

It seems some of these services (e.g. Spotify) don't really do musical similarity, but instead emphasize indirect "other fans also like" similarity.

That tends to disregard many reasons you like a particular track, and does especially badly when the liked-track isn't part of a uniform style for an album or artist.

I recognize it's a heck of a lot easier to implement, but it's still a disappointment.

[dropofwill]

They definitely do both, in the public recommendations API you can see vestiges of the old EchoNest acoustic properties along with some new ones they’ve come up with. It’s fun to play around with.

https://developer.spotify.com/documentation/web-api/referenc...

The guy behind Every Noise at Once (engineer at EchoNest/Spotify until the recent layoffs), has some interesting thoughts about this topic:

https://www.furia.com/page.cgi?type=log&id=478

He’s quite biased towards not using ML or acoustic characteristics for recommendations. But even if you disagree it is interesting to hear about how things were working under the curtain (for daylist in this case).

[MrDrMcCoy]

At its peak, Last.fm was pretty good at this. It had enough data on "people that like these songs also tend to like these songs" that it would generally know what to recommend. I miss those days...