Google’s music streaming service Play Music will start to suggest music based on the location of the user, the current activity and weather. The service will make use a self learning ‘machine learning’ algorithm to improve suggestions to individual users.
The search giant already uses similar algorithms to make personal recommendations in search results through Assistant, a voice assistant that is part of chat app Allo and also available on the Pixel smartphones from Google.
Users of Google Play Music first have to give permission before the feature is enabled. The app is then able to determine the location of the user and will play e.g. more active music in a gym, a sunset soundtrack appears just as the sky goes pink, and tunes for focusing turn up at the library.
Play Music always saves the playlist offline so users can continue to listen to music, even if their internet connection drops.
The home screen of the app is also revamped, so suggestions play a more important role. Google claims, that besides its algorithms, also expert humans curators are working to provide users with the best possible music