A server system divides respective groups of a plurality of groups of sessions for multiple users of the media-providing service into respective pluralities of clusters. The server system tracks user interaction with a client device during a user session and identifies the user session as belonging to a first cluster of the pluralities of clusters based at least in part on the user interaction. The server system personalizes content for the user session using one or more content criteria associated with the first cluster, in accordance with identifying that the user session belongs to the first cluster.