Post-install application interaction
Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium, including a method for providing content. Data specifying a post-install activity is received from a provider of an application. An opportunity is identified to provide third-party content to a user. A likelihood is determined that the user will perform the specified post-install activity based on one or more attributes of the user and attributes of users that have previously performed the specified post-install activity in the application. A selection value is adjusted for third-party content that identifies the application based on the determined likelihood, wherein the selection value increases as the likelihood increases. The third-party content identifying the application is selected based on the adjusted selection value. The third-party content identifying the application is distributed to a client device of the user.
1. A method, comprising:
receiving, through a user interface presented to a provider of an application and by one or more servers, data corresponding to a particular in-app user action performed by users after the application is installed;
generating, by the one or more servers, a machine learning model that predicts a likelihood that specific users will perform the particular in-app user action after the application is installed based on attributes of users that have already installed the application and performed the particular in-app user action;
determining, by the one or more servers and using the machine learning model, a set of users that have not yet installed the application, but are predicted to perform the particular in-app user action after the application is subsequently installed based on attributes of the users; and
prior to the set of users installing the application, distributing, by the one or more servers, a particular third-party content identifying the application to client devices of the set of users based on the determination that the set of users are predicted to perform the particular in-app user action within the application after installing the application.
2. The method of claim 1 , further comprising:
accessing historical user activity data specifying prior activity of other users within the application;
accessing user attributes of the other users that performed the specified post-install activity;
generating a model that provides a likelihood a user will perform the particular in-app user action after installation of the application; and
applying the model to the one or more attributes of the user to obtain the likelihood.
3. The method of claim 2 , wherein determining the set of users that have not yet installed the application, but are predicted to perform the particular in-app user action after the application is subsequently installed comprises determining the set of users based on the likelihood obtained from the model.
4. The method of claim 1 , further comprising providing, to the provider, the user interface that is populated with a list of in-app actions, wherein receiving data corresponding to a particular in-app user action performed by users after the application is installed comprises detecting provider interaction with one or more of the in-app actions presented in the user interface.
5. The method of claim 1 , further comprising providing, to the provider, a user interface that enables the provider to select a strategy from among multiple different strategies including at least a strategy to achieve the particular in-app user action.
6. The method of claim 1 , further comprising providing, to the provider, a user interface that enables the provider to select a strategy from among multiple different strategies including at least a strategy to drive application installs.
7. A non-transitory computer-readable medium storing instructions, that when executed, cause one or more processors to perform operations including:
receiving, through a user interface presented to a provider of an application, data corresponding to a particular in-app user action performed by users after the application is installed;
generating a machine learning model that predicts a likelihood that specific users will perform the particular in-app user action after the application is installed based on attributes of users that have already installed the application and performed the particular in-app user action;
determining, using the machine learning model, a set of users that have not yet installed the application, but are predicted to perform the particular in-app user action after the application is subsequently installed based on attributes of the users; and
prior to the set of users installing the application, distributing a particular third-party content identifying the application to client devices of the set of users based on the determination that the set of users are predicted to perform the particular in-app user action within the application after installing the application.
8. The non-transitory computer-readable medium of claim 7 , wherein the instructions cause the one or more processors to perform operations further comprising:
accessing historical user activity data specifying prior activity of other users within the application;
accessing user attributes of the other users that performed the specified post-install activity;
generating a model that provides a likelihood a user will perform the particular in-app user action after installation of the application; and
applying the model to the one or more attributes of the user to obtain the likelihood.
9. The non-transitory computer-readable medium of claim 8 , wherein determining the set of users that have not yet installed the application, but are predicted to perform the particular in-app user action after the application is subsequently installed comprises determining the set of users based on the likelihood obtained from the model.
10. The non-transitory computer-readable medium of claim 7 , wherein the instructions cause the one or more processors to perform operations further comprising providing, to the provider, the user interface that is populated with a list of in-app actions, wherein receiving data corresponding to a particular in-app user action performed by users after the application is installed comprises detecting provider interaction with one or more of the in-app actions presented in the user interface.
11. The non-transitory computer-readable medium of claim 7 , wherein the instructions cause the one or more processors to perform operations further comprising providing, to the provider, a user interface that enables the provider to select a strategy from among multiple different strategies including at least a strategy to achieve the particular in-app user action.
12. The non-transitory computer-readable medium of claim 7 , wherein the instructions cause the one or more processors to perform operations further comprising providing, to the provider, a user interface that enables the provider to select a strategy from among multiple different strategies including at least a strategy to drive application installs.
13. A system comprising:
one or more processors; and
one or more memory devices including instructions that, when executed, cause the one or more processors to perform operations including:
receiving, through a user interface presented to a provider of an application, data corresponding to a particular in-app user action performed by users after the application is installed;
generating a machine learning model that predicts a likelihood that specific users will perform the particular in-app user action after the application is installed based on attributes of users that have already installed the application and performed the particular in-app user action;
determining, using the machine learning model, a set of users that have not yet installed the application, but are predicted to perform the particular in-app user action after the application is subsequently installed based on attributes of the users; and
prior to the set of users installing the application, distributing a particular third-party content identifying the application to client devices of the set of users based on the determination that the set of users are predicted to perform the particular in-app user action within the application after installing the application.
14. The system of claim 13 , wherein the instructions cause the one or more processors to perform operations further comprising:
accessing historical user activity data specifying prior activity of other users within the application;
accessing user attributes of the other users that performed the specified post-install activity;
generating a model that provides a likelihood a user will perform the particular in-app user action after installation of the application; and
applying the model to the one or more attributes of the user to obtain the likelihood.
15. The system of claim 14 , wherein determining the set of users that have not yet installed the application, but are predicted to perform the particular in-app user action after the application is subsequently installed comprises determining the set of users based on the likelihood obtained from the model.
16. The system of claim 13 , wherein the instructions cause the one or more processors to perform operations further comprising providing, to the provider, the user interface that is populated with a list of in-app actions, wherein receiving data corresponding to a particular in-app user action performed by users after the application is installed comprises detecting provider interaction with one or more of the in-app actions presented in the user interface.
17. The system of claim 13 , wherein the instructions cause the one or more processors to perform operations further comprising providing, to the provider, a user interface that enables the provider to select a strategy from among multiple different strategies including at least a strategy to achieve the particular in-app user action.
18. The system of claim 13 , wherein the instructions cause the one or more processors to perform operations further comprising providing, to the provider, a user interface that enables the provider to select a strategy from among multiple different strategies including at least a strategy to drive application installs.