Music Recommendation Systems

Users discuss the strengths and weaknesses of algorithmic music discovery features like Spotify's Discover Weekly, sharing personal experiences with recommendations, comparisons to services like Pandora and 8tracks, and desires for better personalization.

📉 Falling 0.4x AI & Machine Learning
5,348
Comments
20
Years Active
5
Top Authors
#2985
Topic ID

Activity Over Time

2007
19
2008
60
2009
77
2010
101
2011
151
2012
152
2013
137
2014
158
2015
213
2016
226
2017
383
2018
268
2019
279
2020
566
2021
429
2022
565
2023
518
2024
654
2025
337
2026
55

Keywords

theverge.com e.g AI www.aud i.e last.fm CD echonest.com SoundCloud RDIO spotify music songs discovery playlists discover weekly listen artists listeners

Sample Comments

guidovranken Dec 23, 2020 View on HN

It looks like the API is overloaded.With regards to taste, you usually need to find a suitable gateway into an unpopular genre to begin appreciating it. I always hated jazz until I turned 30, when I heard the melodic jazz of Avishai Cohen [1] and Phronesis [2], which led me to Eric Dolphy [3] and ultimately to free jazz outfits like Alexander von Schlippenbach and Peter Brotzmann. Having grown bored of everything else also helps.I recently cancelled my paid subscription to Spotify after 10

kingosticks Sep 13, 2019 View on HN

Wouldn't it be better to try and select artists (or at least genres) the Spotify user "likes"?

merijnv May 18, 2016 View on HN

The Spotify "Discover Weekly" seems to do pretty well at finding stuff I like. Although it does seem to be a bit biased toward some of my tastes more than others.

lukevp Feb 11, 2023 View on HN

Spotify does this too (paid recommendations).

llagerlof Feb 3, 2023 View on HN

Beautiful. Definetely could replace spotify "recommended" for me.Please, add some filters:- By language- By year (between, above, below)- By fame (so the user can filter out famous musics or unknown ones)Thank you!

kylel95 Sep 12, 2023 View on HN

thanks for the feedback. i agree and valid points but i have friends who have nearly identical music taste and sometimes i hate songs they play. so there is still a hit or miss factor.then the question would be how to decrease the ratio between hits and misses? do you have any ideas of what you would like to see tackle this?i have a few: - upvoting songs - organize songs by the plays / views it has from the source (youtube, spotify, soundcloud). - suggest songs that genre is the sam

hunt Aug 17, 2019 View on HN

I find Spotify's discover weekly to be great for this.

mattnewton Nov 19, 2020 View on HN

Scrolled through the comments exactly for this. In addition to the discover weekly, I'll often make a new playlist of 5-10 similar songs I like to get another in the same vein, and it works very well for my decidedly not-chart-topping music preferences. Maybe there are some genres I don't listen to enough that it struggles with?

gehwartzen Mar 1, 2018 View on HN

That's why I prefer 8tracks for music discovery. User generated play lists still give me a much better results than algorithms. I don't always want something that matches what I already like but instead new stuff that compliments it.

ThrowawayTestr Feb 19, 2023 View on HN

I think you should give recommendation engines a chance. I've discovered so many new artists and genres through Spotify.