Thanks for reporting, we are looking into it 
1 Like
I have yet to find a recommendation system that is of value to me (I’ve occasionally used RYM and Last.fm), but I’ll bite. (Context: I have a “playlist” of 2400+ tracks in foobar2000 that I shuffle, resulting in ~400 artists (each unique collaboration counted as its own artist) per week)
“Top Artist” would only be useful to me if there were some option of it only showing tracks I haven’t heard yet or haven’t heard in X amount of time. If I look at the results right now it’s 99% tracks I already know and regularly listen to, but I might be one of few people who listen to the artists resulting in me curating this list myself.
“Similar Artist” seems way more useful to me but it kind of has the same problem as “Top Artist” and other recommendation systems (RYM specifically). Like “Top Artist” I would love to see an option to only show new tracks or tracks I haven’t heard in a while. Also like RYM’s (album) recommendation system this recommends a lot of artists/tracks from a specific label that I don’t really like, and I’m not really sure why. Currently on the first page there are 3 tracks I already regularly listen to, ~12 tracks from that label I don’t like or artists from that label, and 5 tracks from artists I don’t have any interest in (though I guess the system wouldn’t know I don’t like them)
I guess I’m mostly just looking for a recommendation system that recommends artists/tracks/labels that I haven’t heard yet and will probably like. Would it be an idea to have track/release ratings from MB or CB have some influence too? At the very least that could filter things that are already known one doesn’t like.
2 Likes
I got some interesting datasets I guess. An acquaintance of mine has been creating boxsets/playlists on tons of genres and styles for over a decade http://rymboxset.blogspot.com/. I don’t know if these are on MB but I’d assume most of them are, since they are generally based on influential music within a scene.
I would also be available to gather some “if you like (recording) you will probably like these too” lists (within my area of music) if needed
2 Likes
This could be something more aligned/tied into Critique Brainz?
I think Last.fm does this in quite a nice way, with a mix of what it shows you in its recommendation wall:
2 Likes
Bandcamp does something like this, and it’s one of its best features. It generates you several playlists called “Your mixtape” which contain music grouped by similarity which you like or might like. For this it uses music you have frequently listened to, especially if you liked it, and throws in some additional music that fit into this category. So you get a nice mix of familiar and new music. It also shows a small list of artists which are part of the playlist, so you can easily see what musical style this is.
For someone frequently listening to different genres or moods this grouping is very useful.
3 Likes
Right now, the playlist only show tracks that the user haven’t heard in the last week. X = 7 days is a small window though. We can surely increase this X. Thank you for the feedback 
2 Likes
I don’t know if this is working properly for me then. Is there some way to see when I’ve listened to a track from within LB itself? Currently the #1 track it shows me Last.fm says I have listened to 114 times and twice this month. Maybe it’s just outside the 7 day window
First thanks very much for this, thanks for the charts as well !
I would love to have an extra API endpoint to query recommendations based on an artist (rather than based on a specific user recent listening history).
Some players rest on this kind of feature to automagically queue tracks similar to currently playing (artist | track).
Cheers & happy listening
k
2 Likes
Who knew machines could be so full of hate? I got recommended Radiohead and it’s left me more traumatised than anything any human has said or done to me in years. 
Hello,
Thx for this amazing work. I was waking for this kind of open technologies for so long time and I looking forward to see them integrated in other project as funkwhale o/
-
I have a question about “Tracks of artists that are popular in ListenBrainz will show up more in the playlist”. Is this a choice or a technical issue ?
This is a amazing idea. But using I think using user based tags is very limited. When I look a the incredibles results of the spotify algorithm I see a source of very precise recommendation : http://everynoise.com/
Don’t know how to help but would love to o/
I have a question about “Tracks of artists that are popular in ListenBrainz will show up more in the playlist”. Is this a choice or a technical issue ?
IIRC, it is inherent in the collaborative filtering algorithm – the basic idea of collaborative filtering is that “some users liked these tracks, so you might like them as well”. Popularity of tracks is an inherent part of this premise. But, I don’t see that as a bad thing – I don’t think because of this limitation we’re only going to get popular tracks recommended, but instead popular tracks within your taste range. If that makes sense…
This is a amazing idea. But using I think using user based tags is very limited. When I look a the incredibles results of the spotify algorithm I see a source of very precise recommendation :
You are quite right! We had hoped that when we built tags/genres that some tools (Picard, etc) allows submitting tags to us, but that hasn’t really happened. This is really a typical chicken and the egg problem – which came first?
If there is no compelling use case for tags/genres then people will not submit them. But if we build a compelling use case (e.g. this genre recommender) and people start using it, it gives them a reason to submit tags so that more of the music they love gets picked up by the algorithm. And if the algorithm does a better job, more people will come and use our recommendations… and the cycle continues.
It is this kind of cycle that I hope we can stimulate with the recommendations. There are plenty of ways in which the MusicBrainz data can be improved and if we can provide cool tools that expose data hole and then couple them with tools to submit the data that is missing, we’ll improve the database overall as we go.
We’ll see how it this plays out.
Don’t know how to help but would love to o/
Do you happen to know how to program in python?
3 Likes
I’m beginning, so I don’t know a lot :s
1 Like
It would be cool to get recommendations based on whole listen history, not just last week or month listens. Or with small timebased weight discount.
Also did you think about use AcousticBrainz data?
Yes they did : this use acoustibrainz data : https://github.com/metabrainz/troi-recommendation-playground in the ab-similarity patch
It as the advantage to allow the discovery of very unknowns artists o/
3 Likes
As far as the link of the recommendation engine with AcousticBrainz mentioned at
is there any description about how it works?
2 Likes
On similar subject
3 Likes
installation instruction are in the repo.
sudo python3 -m troi.cli --help
Usage: cli.py [OPTIONS] COMMAND [ARGS]...
Options:
--help Show this message and exit.
Commands:
info Get info for a given patch
list List all available patches
playlist Generate a playlist using a patch PRINT: This option causes...
test Run unit tests
You can also explore the recommendation algorithms though Similar recordings to - "Return to Nowhere" by Charlotte De Witte - AcousticBrainz
1 Like
Thanks for the feedback: do you know how to provide data in case they are missing? Via Picard or are there any other ways?
AcousticBrainz offers GUI and command line submission tools, see Downloads - AcousticBrainz
The upcoming Picard 2.7 will also have the ability to submit the audio analysis to AcousticBrainz.
3 Likes