In one aspect, a method includes receiving first data for a plurality of accounts, the first data including information related to feature subscriptions and adoption for each of the plurality of accounts, each account utilizing one or more devices and features of an enterprise network, receiving second data for the plurality of accounts, the second data including telemetry information on network device and feature usage by one or more devices associated with each of the plurality of accounts, and generating, using a trained machine-learning model, an analysis of the plurality of accounts, wherein the machine-learning model receives the first data and the second data as input and provides a likelihood of feature adoption by each of the plurality of accounts.