Reggie Ugwu, in a BuzzFeed feature story on the second act of Apple Music, got some details on the new ‘My Favorites Mix’ and ‘My New Music Mix’ playlists introduced with iOS 10:

Revealing how the mixes operate for the first time to BuzzFeed News, Apple claimed a potential advantage over similar algorithmically personalized playlists, including Spotify’s Discover Weekly and Pandora’s Thumbprint Radio: deep historical knowledge of individual users’ tastes and habits, based on years of data carried over from iTunes.

If you gave high ratings to a song or album in your old iTunes library, or just played it a lot more than others, you’ll find that behavior reflected in your My Favorites Mix. Meanwhile, the My New Music Mix algorithm serves recently released songs — as well as songs that Apple Music knows you haven’t played before — that the service’s music experts have flagged as similar to others in your taste profile. Apple Music executives suggested even more personalized playlists will follow in the series; but only after prototypes have been vetted, with all possible outcomes — intentional and otherwise — given careful consideration.

This explains why the ‘My Favorites Mix’ playlists have (anecdotally) been spot-on for people I talked to. As I previously noted, back-catalogue songs from artists you’re not familiar with (essentially, Discover Weekly) would be a good addition to Apple Music’s mixes.

Yesterday, Mark Sullivan of Fast Company interviewed Apple Music’s Head of Global Consumer Marketing, Bozoma Saint John, about Apple Music. On the upcoming changes to Apple Music in iOS 10, Saint John said that the goal was to make the experience simpler and easier whether you are a casual listener or an expert. She also expressed her thoughts on the importance of human-curated music:

Yeah, it’s important, it really is important. Human curation allows you to have the emotion and feel music, because it is a very emotional thing. It makes you feel happy, it helps you when you are feeling sad, gets you pumped up, calms you down. You want me to keep going? Because I could preach. I think it is a very emotional thing and you should treat it as such. We as humans have that and we can express it.

There have been an interesting series of features about Apple Music since WWDC. First, BuzzFeed had a behind-the-scenes look at the people who create playlists for Apple Music and other services. Then, Eddy Cue discussed Apple Music’s integration with Apple’s products, curation, and radio in an interview with the Hollywood Reporter. The message from Apple is clear. Apple Music is distinguished from other streaming services by human curation. I like the emphasis on the human touch, but remain skeptical about whether Apple’s editorial team can create new playlists regularly enough to keep them feeling fresh, which has not always been the case in the past.

A major complaint about Apple Music when it rolled out was that it used a metadata-based matching system, which sometimes caused it to incorrectly match songs in users’ music libraries with Apple’s database. Jim Dalrymple reports for The Loop, that:

Apple has been quietly rolling out iTunes Match audio fingerprint to all Apple Music subscribers. Previously Apple was using a less accurate metadata version of iTunes Match on Apple Music, which wouldn’t always match the correct version of a particular song. We’ve all seen the stories of a live version of a song being replaced by a studio version, etc.

According to Dalrymple, the audio fingerprint matching system that Apple is slowly rolling out to Apple Music is the same system that has been available to customers who subscribe separately to iTunes Match. The new matching functionality is being added by Apple at no additional cost to Apple Music subscribers, which means that if you previously subscribed to Apple Music and iTunes Match, there should be no reason to renew your iTunes Match subscription when it expires. As Jim Dalrymple points out, however, you may want to be sure that the new system is working properly before letting Match expire.

BuzzFeed has a fantastic feature post by Reggie Ugwu that goes inside the teams that create playlists for Apple Music, Spotify, and Google Play.

Ugwu explains that:

In the two years since the Beats acquisition, three of the largest services, including Apple Music, Spotify, and Google Play Music (and smaller ones like Tidal and Rhapsody, too), have increasingly relied on these playlists to accomplish two important goals at once: 1) helping users inundated by a catalog of more than 30 million songs more easily find the ones they actually want, and 2) creating difference in a market where everyone has more or less the same goods.

That’s a tall order. Discovery of digital media, whether it’s music, apps, or something else, is tough when many people are browsing vast media collections on their phones. Early attempts to curate music focused heavily on algorithmic solutions, but increasingly, streaming music services have invested in building editorial teams of music experts to create hand-picked playlists for subscribers.

One of the earliest champions of curated playlists was Jimmy Iovine, co-founder of Beats Music, which was acquired by Apple in 2014. Scott Plagenhoef, head of Apple Music’s editorial team of about a dozen employees, explains Apple’s Iovine-inspired approach to music curation:

“It’s not about us projecting our personal opinions on people, it’s about us kind of being good shepherds and stewards and cutting through this entire vast catalog,” he says. “What’s important isn’t just the most popular artists, or the sort of soft center that’s going to be palatable to a lot of people. It’s finding the artists people are going to either love or have intense reactions to, the ones that are going to mean the most and have the biggest impact.”

Music fans, Plagenhoef argues, echoing Iovine, can smell the difference between a service where much of the product is dictated by algorithms or charts and one that is guided by more knowledgeable but equally passionate versions of themselves. By building its house on a foundation of experts, Apple Music has bet that it can be marginally more trustworthy to users than the competition, and that that margin could make a tie-breaking difference.

As a life-long music fan, I don’t find this as particularly surprising, though maybe I would if I were approaching music curation from a purely technical standpoint. There are lots of clever things you can do algorithmically to group similar songs, but the human element makes a difference.