is a blog about design, technology and culture written by Khoi Vinh, and has been more or less continuously published since December 2000 in New York City. Khoi is currently Principal Designer at Adobe, Design Chair at Wildcard and co-founder of Kidpost. Previously, Khoi was co-founder and CEO of Mixel (acquired by Etsy, Inc.), Design Director of The New York Times Online, and co-founder of the design studio Behavior, LLC. He is the author of “Ordering Disorder: Grid Principles for Web Design,” and was named one of Fast Company’s “fifty most influential designers in America.” Khoi lives in Crown Heights, Brooklyn with his wife and three children. Refer to the advertising and sponsorship page for inquiries.+
This Wired article looks at Spotify’s attempts at generating “perfect playlists” to suit its customers’ various moods and life moments. It includes a look at the music service’s new Discover Weekly feature, an algorithmically generated playlist tailored for each user that’s refreshed every Monday.
Combined with what the company calls your ‘taste profile,’ an internally kept list of traits and types of music you tend to enjoy, Spotify can automatically refine and perfect recommendations just for you. When you open the app, you’ll see different playlist choices than I do; those playlists themselves could even be customized just for you. That’s where Discover Weekly comes from: It’s your taste profile, brought to life in two dozen or so songs each week.
I have never found these types of playlists to be remotely satisfactory, whether they were created by man or machine. But I was shocked by my experience with the first playlist that Discover Weekly generated for me this week.
It’s twenty-nine songs long, about two hours worth of music, and I would estimate that I found about eighty percent of that to be really enjoyable, tracks that made me curious about the albums they came from and the artists that recorded them. And that’s the other thing; I consider myself to be a moderately advanced consumer of independent music; I actively seek out new acts all the time and try to stay on top of up-and-coming bands. But Discover Weekly included a healthy percentage of acts that I hadn’t even heard of before, most of which I’m now very curious about.
I can’t say enough about how pleasantly surprising this playlist is; after listening to it repeatedly since trying it out for the first time yesterday, it’s harder and harder to believe that it wasn’t compiled for me by a real person—someone with a vast knowledge of music and who also happened to know my music preferences intimately. If a friend had made this exact playlist for me, that person would be just about the coolest person I know.
Discover Weekly is probably the most potent example yet of the significant competitive edge that Spotify gained when it acquired The Echo Nest last year. That service describes itself as a “music intelligence company;” The Wired article explains it this way:
The Echo Nest’s job within Spotify is to endlessly categorize and organize tracks. The team applies a huge number of attributes to every single song: Is it happy or sad? Is it guitar-driven? Are the vocals spoken or sung? Is it mellow, aggressive, or dancy? On and on the list goes. Meanwhile, the software is also scanning blogs and social networks—ten million posts a day, Lucchese says—to see the words people use to talk about music.
If this is just the beginning of what Spotify and The Echo Nest can do together, our collective expectations for how music discovery should work could change dramatically in the next few years. It could soon become inconceivable that you would ever be presented with a music library or source that doesn’t feel like it was somehow tailored expressly for you. It’s fine that today’s streaming services can boast catalogs of thirty million-plus songs, but that may soon matter little. Would you prefer a huge warehouse full of music that’s mostly irrelevant to you, or a record shop in which everything on the shelves suits your taste? The former is what we have today; the latter is where we might be heading.
What’s more, this kind of taste acuity could be a silver bullet in resolving the continual tension between streaming services and musicians, especially lesser known artists whose income potential has been dramatically reduced in this new paradigm. The Spotify team seems to weight these Echo Nest-driven playlists in favor of acts that its users aren’t familiar with; if they succeed, they could be sending significant play traffic to new contenders. It’s probably far too soon to say how viable this is, but there does seem to be the glimmer of something potentially market-changing in the intelligence and relative indifference to popularity of these recommendations.
Finally, it’s worth noting that Spotify and The Echo Nest have been compiling my “taste profile” for only a few years, and yet the result is a truly remarkable understanding of what I like. By contrast iTunes has over a decade’s worth of my listening habits, and yet as I wrote in this post when Apple Music launched, Apple seems to have very little understanding of my tastes at all. More and more, Apple Music is looking like a disappointment.+