Abstract: Methods and devices for determining whether a mobile device has been compromised. The mobile device has a managed portion of memory and an unmanaged portion of memory, a managed profile and an unmanaged profile, and the managed profile includes files stored in the managed portion of memory and the unmanaged profile includes files stored in the unmanaged portion of memory. The managed profile is governed by a device policy set by a remote administrator. File tree structure information for the unmanaged profile of the mobile device is obtained that details at least a portion of a tree-based structure of folders and files in the unmanaged portion of memory. It is determined from the file tree structure information that the mobile device has been compromised and, based on that determination, an action is taken.

Abstract: Aspects of the disclosure relate to a computing system, computer-implemented method, and computer readable storage media for predicting, for a consumer in a group of consumers assigned to a subset of consumers in a plurality of subsets at the present time, which subset the consumer will be assigned to at a predetermined time in the future. Further aspects of the disclosure relate to a computer-implemented method for determining the likelihood that consumers in a group of consumers will migrate between subsets in a plurality of subsets of consumers. Further aspects of the disclosure related to a computer-implemented method for determining an expected revenue for a group of consumers at a predetermined time in the future.

Abstract: A system, method, and computer readable storage media for training a model to estimate an unknown consumer behavior while preserving consumer privacy by combining a first training data set of a first organization with a second training data set of a second organization on a third-party computer system, wherein the second training data set contains an attribute value the first organization wishes to estimate, and wherein the first organization cannot access the third-party computing system, providing a trainable model definition to the third-party computer, training the model, and returning the trained computer model.