With Google’s approach to software increasingly centering on personalized recommendations and assistance, it is no surprise that the same contextual recommendations come to the search giant’s revamped music service, Google Play.
Using machine learning and clues like location, activity and weather, the app tries to serve up a smorgasbord of playlists that will match your mood and moment. Every time you open the app, it completely refreshes what you see, trying to serve the perfect selection. Tapping the app on Saturday night you could get options for a cocktail party playlist and some serious dancehall jams. When you open it on Sunday afternoon, you could get offered a playlist for relaxing at home and another for cooking dinner. The interface, based on cards, feels a lot like Google Now, and so does the approach to just-in-time doses of pertinent information, in this case the tunes you need.
The more information that the machine learning algorithms have on you the better it will be able to tailor your music choices. For instance, when it locates that you are at the gym you visit every week, it could provide you with a workout playlist, or swap that out to show you a playlist for focusing when your location matches your office. If you travel to a new country for the first time, the algorithm would pick up on this and offer music to accompany your adventure or get you into the swing of local culture. Google Play Music relies on a diverse range of datasets connected to your Google account: from search history, to maps, to YouTube, and beyond.
While there are other music apps that can refresh your playlist every week they are not able to intuitively deliver a match based on a certain mood or activity. The team behind Google Play Music came out of Songza, a New York City startup. That company was all about building playlists that matched a certain mood or activity, but users had to tell the app how they were feeling or what they were doing. Now, working at Google the team has been able to combine Songza with the vast trove of information on users and powerful machine learning algorithms available with Google to create a personal DJ who follows you around and knows exactly what you want to hear, when you want to hear it.