The click and hold Preview action as shown above, makes easy to sample a recommendation and discover more artists and their music, with the slick UI and making it simple and straight forward to move through the recommendations.
Behind the scenes it shows that Spotify are paying attention to the usage profile of their users, and displaying recommendations and suggestions based on tunes played and playlist content. While an individual users’ play history and playlist settings may be quite small digitally. As Spotify has millions of subscribers to the service, cumulatively this must equate to a significant data-set and require Big Data hosting and analytics services behind that to drive recommendations and observe other trends within their user base.
Some quotes from that post:
At the heart of Spotify lives a massive and growing data-set. Most data is user-centric and allows us to provide music recommendations, choose the next song you hear on radio and many other things. We do our best to base every decision, programmatic and managerial, on data and this extends into the culture.
Most of our recurring data is added to our analytics pipeline by a set of daemons that constantly parse the syslog on production machines looking for messages we have defined along with the associated data for each message. Matching data is compressed and periodically synced to HDFS. Typically data is available in our Data Warehouse and Dashboards within 24 hours, but in some cases data is available within a few hours or even instantly through tools like Storm.
Do you use Spotify, what do you like about it?