Abstract: A system and a method are disclosed for recommending a set of actions to be performed to improve a target performance metric of a client application. An action recommendation system receives the target performance metric from a user associated with the client application. The action recommendation system determines features of the client application describing characteristics and performance history of the client application. The features of the client application and the target performance metric is provided as input to a machine learning model that outputs sets of target features that are likely to result in improvement for the target performance metric. The action recommendation system ranks the sets of target features and selects one of the sets based on the ranking. The action recommendation system determines a set of recommended actions based on the selected set of target features and presents the set of recommended actions to the user.

Abstract: A keyword reporting system for mobile applications is disclosed that generates keyword reports for a subject mobile application. The reports include a set of most relevant keywords for the subject mobile application with their associated ranking and result value. The ranking of a keyword is the subject mobile application's position in a search result for the keyword. A result value is determined for each keyword as well, where the result value is the number of mobile applications found in a search result for the keyword. Based on the ranking and result value of each keyword, a weight value is determined for each keyword. The weight value indicates the relevance of the keyword for the subject mobile application. A set of keywords are sorted and selected based on the weight value and a keyword report is generated that includes the set of keywords along with their rankings.

Abstract: A keyword reporting system for mobile applications is disclosed that generates keyword reports for a subject mobile application. The reports include a set of most relevant keywords for the subject mobile application with their associated ranking and result value. The ranking of a keyword is the subject mobile application's position in a search result for the keyword. A result value is determined for each keyword as well, where the result value is the number of mobile applications found in a search result for the keyword. Based on the ranking and result value of each keyword, a weight value is determined for each keyword. The weight value indicates the relevance of the keyword for the subject mobile application. A set of keywords are sorted and selected based on the weight value and a keyword report is generated that includes the set of keywords along with their rankings.

Abstract: A utility application for a mobile device inspects data packets from other mobile applications running on the device to gather and record usage data about those applications. Since users of the utility application may not reflect the true population for which the usage data is desired, a system de-biases the data reported from the utility applications using a machine learning model to predict demographics of the users of the utility application. To determine a training data set for the model, the system requests a user to provide a desired user attribute by way of an in-app questionnaire. This enables labeling utility usage data with the demographics, which can be weighted and extrapolated to determine usage across the population as a whole.

Abstract: A system determines attribution of an application install on a mobile device that includes a virtual private network (VPN) application. An application executing on a mobile device may display a third party application advertisement. The VPN application detects a click on the third party application advertisements by monitoring the network requests and records a display time of the advertisement. Further, it detects the download and installation of the third party application by monitoring the network requests and comparing it against a rule from the rules dictionary, and records the installation time of the third party application. If the installation time is within a predetermined threshold time of the display time of the third party application advertisement, an attribution count is updated and is reported to an analytics engine.

Abstract: Disclosed is a method for tracking usage of applications on a mobile device that includes a virtual private network (VPN) application. The VPN application includes a rule dictionary to store a rule for each application that is executable on the mobile device. A rule comprises an identifier for the application and an associated regular expression. To create a rule, a new application is installed on the mobile device and executed to create network traffic. The network traffic from the new application is inspected and a regular expression that matches the new application is created and stored in the rules dictionary. Once the rule is stored, a usage of the application can be identified based on monitoring the network traffic and searching the rule dictionary to identify a matching application. Once a matching application is found, the usage metric of the application is updated.

Abstract: A method for facilitating collection and display of information related to data usage by a plurality of mobile devices is disclosed. The method involves receiving first quantity information and sending a first identifier associated with the plurality of mobile devices and first activity-related information including the first quantity information to a server. The method also involves receiving group activity-related information associated with the plurality of mobile devices, the group activity-related information derived at least in part from second activity-related information including second quantity information, and producing signals for causing a display to display information derived from the group activity-related information. A method of associating a plurality of mobile devices in a group is also disclosed.