Spotify Reveals How The ‘Fans Also Like’ Feature Works: ‘the second-most important piece of data’
"Fans Also Like" appears on Spotify artist page filled with a list of related artists. Those same artists also surface on their peers' FAL lists. Spotify has now shared how this 'second-most important piece of data' works and its importance in the streamer's data driven ecosystem.
"Artist similarity is probably the second-most important piece of data we extract from listening patterns—after popularity," said Glenn McDonald, Spotify's data alchemist in a blog post. "It's also the data behind radio, genres, and several of the features on Home and the Discover pages."
Fans Also Like is populated algorithmically. "Which is a fancy way of saying it's done with math,” says McDonald. "But the goal of the math is to collect and make sense of aggregate human input. The computers don't have opinions—they're just organizing the collective opinions of people."
How "Fans Also Like" Works
To determine an act's FAL, the first piece of data is shared fans – particularly among artists who might exist on the fringes. "The more fans two artists have in common, and the larger the share of each artist's total fans those shared fans represent, the more similar we consider them," says McDonald. "If an aspiring band has 10,000 fans, and 6,000 of them are also fans of another band that also has 10,000 fans, that's a pretty good sign that the two bands are probably similar. Whereas either of those bands might easily have 1,000 fans who also like Ariana Grande, but Ariana has tens of millions of fans, so those 1,000 shared fans aren't a significant share of hers."
The second piece of FAL data involves shared descriptions – using not just the content on Spotify but also from blogs, magazines, and other sites where music is being discussed. "We scrape millions of web pages about music every day, and combine [that information] with various other sources of artist descriptions, and then look for patterns in shared descriptive vocabulary," says McDonald.
New Artist FALs Sometimes Miss The Mark
Spotify admits that descriptive pattern matching can also produce mistakes, For example, newer artists who don't have a lot of press or who do have common words in their names should take time to look at their Fans Also Like list and make sure it checks out.
“If your band's name is a very common word or phrase, and you don't have very much material yet, the programs may sometimes get this wrong, and thus mistakenly think an unrelated article is talking about you,” says McDonald. “If you're a new or not-yet-famous band and your Fans Also Like list seems very weird to you, especially if it's full of bands with similar names but totally different music, then this might be why. Let us know if it seems like we need to check your list."
And what is the most important piece of Spotify data? Popularity.
Spotify has 100 million paid subscribers. Probably. Our problem is that we make very, very, minority genre music. Our current listeners are very few. However, we are actually good and from 100 million, there must be several thousand people at least who would love our music but the algorithm does not allow us to get heard by them. The idea that you already need to be popular in order to be helped to be popular seems to me to be illogical. If Spotify made it possible to contact other users who curate playlists, it would improve matters a lot.
TRUE!!!!!