Detecting digital content misuse based on digital content usage clusters

摘要

A method for detecting digital content misuse can include clustering, by a digital content delivery system, a set of data points into a set of digital content usage clusters, each data point from the set of data points representing a unique user account from a set of user accounts maintained by the digital content delivery system, and each data point from the set of data points having been determined based on usage signal data describing digital content usage associated with the unique user account represented by the data point; determining, based on the set of digital content usage clusters, that a first data point from the set of data points is an outlier; and in response to determining that the first data point from the set of data points is an outlier, executing a remedial action with respect to a user account represented by the first data point.