Pixel Envy

Written by Nick Heer.

Buzzfeed’s Profile of Apple Music’s 2016 Updates

Buzzfeed’s Reggie Ugwu spoke with Zane Lowe, Jimmy Iovine, and Bozoma Saint John about the updates to Apple Music that debuted alongside iOS 10 and MacOS Sierra. The article is pretty light and fluffy, but there’s a noteworthy scoop:

The other big change is the addition of two new personalized playlists: My Favorites Mix and My New Music Mix. The playlists are generated by algorithms, a first for the service, which has largely relied on human curation for its playlists up to this point. 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.

Anecdotally, the recommendations I’ve received from Spotify have generally been more well-rounded in almost all regards, despite using the service less than I do Apple Music or local playback. I also appreciate Spotify’s large variety of community-created playlists.

But I’d rather pay for just one streaming service, and I’d prefer to use the one that’s integrated into the applications I use most: Music on iOS, and iTunes on my Mac. Unfortunately, as I’ve written before, its recommendations have been lacklustre.

Just now, I opened up Music and tapped the “For You” tab to see what it thinks I should be listening to. For some reason, it’s suggesting Linkin Park and Coheed and Cambria, two artists I’m not fond of. So, I went ahead and tapped the “dislike” button on both. Both albums are still in my recommendations and, presumably, will remain there until For You is refreshed. There appears to be no way to do that manually.

Similarly, I think that the items displayed in “Browse” should be somewhat tailored as well. There’s no reason to suggest the new Luke Bryan record — nothing in my playback history suggests that I would be even remotely interested in that record.

There’s a clear solution to a lot of these issues, and Apple has already implemented it. The two new playlists cited by Buzzfeed are among the most accurate I’ve seen, but there are just two of them, and they’re refreshed weekly. It remains a complete mystery to me why the rest of Apple Music’s recommendation features are not using iTunes playback and rating data, nor the previously-collected Genius data.