Smart recommendation engine for preventing churn and providing prioritized insights
AssigneeAvast Software s.r.o.
InventorRajarshi Gupta
Life of this patent
Estimating the term…
Abstract
A recommendation engine can provide recommendations with respect to an application and can provide insights to a user of a computing device. The recommendation engine can receive a prediction based on user engagement with the application during an initial period of time (e.g., a trial period) as to whether the user will convert use of the application to a paid basis (e.g., a subscription or license to the application). An action can be recommended based on the prediction. The recommendation engine can provide insights to a user based on a score associated with the insight. The score can be determined by measuring previous user interactions with the insight over a period of time.
Claims24
A method for preventing application churn, the method comprising:
- receiving one or more indicators of user activity within an application during a time period;
- determining, based at least in part, on the one or more indicators of user activity, a likelihood that the user will continue to use the application on a paid basis;
- in response to determining that the likelihood that the user will continue to use the application on a paid basis is above a predetermined or configurable threshold, determining a recommended action from a first set of recommended actions;
- and
- in response to determining that the likelihood that the user will continue to use the application on a paid basis is below a predetermined or configurable threshold, determining a recommended action from a second set of recommended actions.
A method for providing insights to a user, the method comprising:
- during an initial period of time, performing operations comprising:
- selecting a plurality of insights from a library of insights, wherein each of the plurality of insights has an associated score;
- providing the plurality of insights to computing devices;
- receiving measurements of user engagement with the plurality of insights;
- and
- updating scores associated with the plurality of insights based, at least in part, on the measurements of user engagement with the insights.
A non-transitory machine-readable storage medium having stored thereon computer-executable instructions for observing device events, the computer-executable instructions to cause one or more processors to perform operations comprising:
- receive one or more indicators of user activity within an application during a time period;
- determine, based at least in part, on the one or more indicators of user activity, a likelihood that the user will continue to use the application on a paid basis;
- in response to a determination that the likelihood that the user will continue to use the application on a paid basis is above a predetermined or configurable threshold, determine a recommended action from a first set of recommended actions;
- and
- in response to a determination that the likelihood that the user will continue to use the application on a paid basis is below the predetermined or configurable threshold, determine a recommended action from a second set of recommended actions.
A non-transitory machine-readable storage medium having stored thereon computer-executable instructions for observing device events, the computer-executable instructions to cause one or more processors to perform operations comprising:
- select a plurality of insights from a library of insights, wherein each of the plurality of insights has an associated score;
- provide, during an initial period of time, the plurality of insights to computing devices;
- receive, during the initial period of time, measurements of user engagement with the plurality of insights;
- and
- update scores associated with the plurality of insights based, at least in part, on the measurements of user engagement with the insights.
A system for preventing application churn, the system comprising:
- one or more processors;
- and
- a non-transitory machine-readable medium having stored thereon computer-executable instructions to cause the one or more processors to:
- receive one or more indicators of user activity within an application during a time period;
- determine, based at least in part, on the one or more indicators of user activity, a likelihood that the user will continue to use the application on a paid basis;
- in response to a determination that the likelihood that the user will continue to use the application on a paid basis is above a predetermined or configurable threshold, determine a recommended action from a first set of recommended actions;
- and
- in response to a determination that the likelihood that the user will continue to use the application on a paid basis is below the predetermined or configurable threshold, determine a recommended action from a second set of recommended actions.
Dependencies are inferred from the claim text.