Spotify will add the input of artists and labels to its personalized recommendation process, the company announced in a blog post Monday. The process will enable artists and labels to promote a new single, for example, over songs that Spotify’s algorithm might have suggested otherwise.
“In this new experiment, artists and labels can identify music that’s a priority for them, and our system will add that signal to the algorithm that determines personalized listening sessions,” the blog post reads. “This allows our algorithms to account for what’s important to the artist — perhaps a song they’re particularly excited about, an album anniversary they’re celebrating, a viral cultural moment they’re experiencing, or other factors they care about.”
The artists and labels will receive a lower royalty rate for this service — “a promotional recording royalty rate for streams in personalized listening sessions where we provided this service,” according to the announcement — but it is up to them whether or not that participate.
While the “secret sauce” of Spotify’s recommendation algorithm is not publicly available, the announcement describes them as “complex, dynamic systems that consider a wide variety of inputs about what [customers] like — which we refer to as signals — and balance those signals in many possible different pathways to produce an output: the perfect song for the moment, just for you.
“Our personalized recommendations take into account thousands of types of signals: what you’re listening to and when, which songs you’re adding to your playlists, the listening habits of people who have similar tastes, and much more,” it continues. “In order to create algorithms that truly deliver the right song for the right time, we’re also taking into account less obvious factors: things like time of day, or the order in which you’re listening to songs or podcasts, or the release date of a song.”
As for the reasoning behind adding artists and labels to the mix — which would seem to add a commercial or at least promotional element that may not have existed before — the announcement continues, “Artists tell us they want more opportunities to connect with new listeners, and we believe our recommendations should also be informed by artists — their priorities and what they have to say about their music.”
If the songs or artists don’t resonate with listeners, they will be withdrawn. “If the songs resonate with listeners, we’ll keep trying them in similar sessions. If the songs don’t perform well, they’ll quickly be pulled back. Listener satisfaction is our priority —we won’t guarantee placement to labels or artists, and we only ever recommend music we think listeners will want to hear.”
The service will initially be applied to Spotify’s Radio and Autoplay formats, “where we know listeners are looking to discover new music.” The announcement also claims that 16 billion times a month, listeners are hearing an artist they’ve never heard before on Spotify, which seems likely if the autoplay function is being used, which uses the above-named factors to find music it believes the listener will like after the song or album they have chosen is over.