SYSTEM AND METHOD FOR USER-LEVEL LIFETIME VALUE PREDICTION

1 . A method, comprising:

obtaining data comprising a history of interactions between a plurality of users and a client application on a plurality of respective client devices;

developing, using the data, a first predictive model to predict a likelihood that a new user of the client application will be a payer;

developing, using the data, a second predictive model to predict an amount of revenue generated by the new user of the client application;

providing the client application to a plurality of new users;

using the first predictive model and the second predictive model to predict the likelihood and the revenue for each new user in the plurality of new users; and

adjusting, based on the predicted likelihood and the predicted revenue, a method of acquiring additional users of the client application.

2 . The method of claim 1 , wherein the history of interactions comprises a record of user activity in the client application.

3 . The method of claim 1 , wherein the data further comprises a record of user activity prior to installation of the client application.

4 . The method of claim 1 , wherein the data further comprises at least one of a user characteristic and a client device characteristic.

5 . The method of claim 1 , wherein the first predictive model and the second predictive model each comprise a chain of predictive models, wherein each model in the chain is configured to make a prediction using data for a distinct user age.

6 . The method of claim 1 , wherein the predicted likelihood and the predicted revenue comprise predictions for an initial time after the client application was first provided to the new user.

7 . The method of claim 6 , wherein using the first predictive model and the second predictive model comprises:

extrapolating the predictions for the initial time to a later time using one or more multipliers.

8 . The method of claim 1 , wherein using the first predictive model and the second predictive model comprises:

providing the first predictive model and the second predictive model with input data comprising a history of interactions between the plurality of new users and the client application.

9 . The method of claim 1 , wherein the method of acquiring additional users comprises presenting content related to the client application to a set of prospective additional users.

10 . The method of claim 1 , wherein the client application comprises a multiplayer online game.

11 . A system, comprising:

one or more computer processors programmed to perform operations comprising:

obtaining data comprising a history of interactions between a plurality of users and a client application on a plurality of respective client devices;

developing, using the data, a first predictive model to predict a likelihood that a new user of the client application will be a payer;

developing, using the data, a second predictive model to predict an amount of revenue generated by the new user of the client application;

providing the client application to a plurality of new users;

using the first predictive model and the second predictive model to predict the likelihood and the revenue for each new user in the plurality of new users; and

adjusting, based on the predicted likelihood and the predicted revenue, a method of acquiring additional users of the client application.

12 . The system of claim 11 , wherein the history of interactions comprises a record of user activity in the client application.

13 . The system of claim 11 , wherein the data further comprises a record of user activity prior to installation of the client application.

14 . The system of claim 11 , wherein the first predictive model and the second predictive model each comprise a chain of predictive models, wherein each model in the chain is configured to make a prediction using data for a distinct user age.

15 . The system of claim 11 , wherein the predicted likelihood and the predicted revenue comprise predictions for an initial time after the client application was first provided to the new user.

16 . The system of claim 15 , wherein using the first predictive model and the second predictive model comprises:

extrapolating the predictions for the initial time to a later time using one or more multipliers.

17 . The system of claim 11 , wherein using the first predictive model and the second predictive model comprises:

providing the first predictive model and the second predictive model with input data comprising a history of interactions between the plurality of new users and the client application.

18 . The system of claim 11 , wherein the method of acquiring additional users comprises presenting content related to the client application to a set of prospective additional users.

19 . The system of claim 11 , wherein the client application comprises a multiplayer online game.

20 . An article, comprising:

a non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more computer processors, cause the one or more computer processors to perform operations comprising:

obtaining data comprising a history of interactions between a plurality of users and a client application on a plurality of respective client devices;

developing, using the data, a first predictive model to predict a likelihood that a new user of the client application will be a payer;

developing, using the data, a second predictive model to predict an amount of revenue generated by the new user of the client application;

providing the client application to a plurality of new users;

using the first predictive model and the second predictive model to predict the likelihood and the revenue for each new user in the plurality of new users; and

adjusting, based on the predicted likelihood and the predicted revenue, a method of acquiring additional users of the client application.