[MrDrMcCoy]

Way back when Last.FM has its own radio service, I could throw a few random genres and/or artists at it, and it would recommend me pretty much exactly want I wanted every time. I gladly enabled scrobbling in my music players, and it tended to recommend me good stuff every time. Ever since its radio feature got killed, its database has been getting worse and worse. Just now, I tried to search for some things it used to be good at finding, and the artists section was not filled with artists at all, but rather a bunch of what appear to be random playlists with incomplete metadata.

Pandora had decent algorithms for recommending things, but it had such a small library that it would frequently repeat the same handful of albums for anything I searched for. This irks me, as I hate wearing out good music.

Spotify is currently where I keep my weeks-long playlists that I've built over the past couple decades. Even with such large playlists as input for their radio recommendations, Spotify doesn't do a very good job recommending new music either.

Whatever happened to the good databases and their algorithms? They definitely used to exist.

[vidanay]

> Pandora had decent algorithms for recommending things, but it had such a small library that it would frequently repeat the same handful of albums for anything I searched for. This irks me, as I hate wearing out good music.

I've been a daily user of Pandora for something like 10 years. It's been getting steadily worse the whole time, and especially in the last two years.

I like to create my own station that is "seeded" by a few artists, and then allow the algorithm to do what it wants to play related music. This used to be great, until one day I noticed that it had become stuck playing the same 50 or so songs. This was after about three years of listening to that station on a weekly basis. As an experiment, I created a new station and seeded it again with similar artist. Again, it was fine for 2-3 years until it got stuck on a handful of songs. I did this again recently and it has become stuck within four months. There are even a few of my seed songs that it simply ignores and never plays.

[musictubes]

Last.fm had the best categorizing features I ever saw. Songs would. It only be listed under “female artist” but would also have things like “extensive vamping,” that really got to the heart of what the song was about. They got closer to understanding why I liked songs than any other service. All of the other services feel rather dumb when it comes to preferences. It feels like they still rely on associating other people that liked artist x also liked artist y. As a music aficionado it’s infuriating.

Apple has tried to help by using human curated playlists but I frequently find myself thinking I have better taste than their “experts.”

[galkk]

> Apple has tried to help by using human curated playlists but I frequently find myself thinking I have better taste than their “experts.”

It feels like all the time, when there is human curation factor, it ends up being sold off, gamed, exchanged for favors etc.

[terribleperson]

I used Pandora a lot when I was a teenager, and experimented a bit. If you were listening the same time I was, the size of the library probably wasn't the primary issue.

Presumably their recommendation algorithm and the Music Genome Project tagging allowed them to, given a set of tags, find similarly tagged songs. This worked really well. It's how they used it and how they picked what track to play next that caused issues.

First, thumbs up. As far as I could tell, at the time Pandora would strongly prefer to play a track you'd thumbsed up on a station over anything else, as long as it was available to play, which mainly just required it to not have played to you in the last two hours. So if you used thumbs up the normal way, a well-used station would eventually turn into a loop of things you'd already heard.

Second, the way they used the algorithm - it seemed to me like they only or mostly used the station seeds as the input, there was no blending going on, and if thumbs ups impacted it, well, they had their own problems. That is, if you had a station with two seeds, it played some songs close to one seed, then it switched to the other seed and played some songs close to the other seed. Skipping would usually bump you to a different seed.

To get around all this and get a variety of new material, I created a station with a lot of seeds - 25 to 50 or more - and never thumbsed up anything on it.

[bsder]

> Whatever happened to the good databases and their algorithms? They definitely used to exist.

It was called a record store employee, and they no longer exist.

There's an AI search engine I'd like to see ...

Even the "market segmentation" of pop music still doesn't work for crap. Even something as basic as "Gee, I like 80s New Wave, how about recommending some artists born roughly in the 21st century who would fit?" seems to be totally beyond the pale of anything currently existing.

[MrDrMcCoy]

My tastes have always been niche enough that most record store employees would give me the "deer in the headlights" look or condescend to me when I asked for a particular artist or similar that I found on Last.fm.

If the database quality of current Last.fm were similar to its state back when it had radio, I would think that an AI trained on their data would be pretty good. With the current state of it... It would have to be crap. Heck, even if an AI model could be trained on the play counts of every song of every user on every streaming service, I'm not sure it could approach the curated relational algorithm that Last.fm had at its peak. Would definitely love to see an attempt, though.

[gosub100]

> It was called a record store employee

I'm happy to not relive the days where CDs were and inflation adjusted $35 for about 10 songs. And there is no economic incentive or guarantee that any given retail employee would know anything about the inventory. Go to home Depot and canvas some of them about home repairs if you don't believe me.

[bsder]

> I'm happy to not relive the days where CDs were and inflation adjusted $35 for about 10 songs.

Limited edition vinyl stuff, for example, generally goes for right around that in order to support the artists. Most of that money is going directly to the artist, nowadays (as opposed to live in which it all goes to Ticketmaster).

If you're not willing to spend at least some money, well, then you're part of the problem why artists can't get paid for doing music and why so much of it kinda sucks.

> And there is no economic incentive or guarantee that any given retail employee would know anything about the inventory. Go to home Depot and canvas some of them about home repairs if you don't believe me.

Sure, if you went to Tower Records, you almost always had someone clueless. However, the point of going to those stores was to NOT go to the big retailer, it was to go to the local record stores that had people who worked there specifically because they were super passionate about music.

This was how you found out about that super obscure artist. It was also how you found out about the local bands that might be of interest to someone who liked that super obscure artist. etc.

[galdosdi]

There was an article in the Times recently about how Spotify is no longer solely using "how much do we predict the user will like this song" as a metric, but now is also considering "how much do we pay this artist per play" to optimize for cheaper higher-profit-for-spotify music.

[NikkiA]

Amazon music does an 'ok' job at recommendations for me, slightly better than spotify, but that's not a high bar. Jango does a better job, or did last time I used it, but it has so little available music that it somewhat self limits itself.