Machine-learning models to facilitate user retention for software applications

Abstract

An ordered combination of machine-learning models may be used to identify users who are likely to abandon use of an application, predict the reasons why those users are likely to abandon, and identify intervening actions that the application can perform to reduce the probability that the users will abandon the application. For example, a first machine-learning model determines a retention-prediction value indicating a probability that the user will complete a target action in the application before a session terminates. If the retention-prediction value satisfies a threshold condition, a second machine-learning model determines a reason why the session is likely to terminate before the user completes the target action. A third machine-learning model determines an intervention action for the application to perform to increase the probability that the user will complete the target action before the session terminates.

What is claimed is: 
     
         1 . A method, comprising:
 sending one or more web pages for display to a user via a network during an interaction session between the user and an application, wherein the one or more web pages include elements for collecting response data from the user;   receiving, via the web pages, response data from the user,   determining, via a first machine-learning model based on the response data, a predicted reason the interaction session is likely to terminate before the user completes a target action;   determining, via a second machine-learning model based on the response data and the predicted reason determined by the first machine-learning model, an intervention action for increasing a probability that the user will complete the target action before the interaction session terminates; and   performing, via the application, the intervention action.   
     
     
         2 . The method of  claim 1 , further comprising:
 determining, via a third machine-learning model based on the response data, a next action the user is anticipated to perform in the application; and   altering at least one aspect of the one or more web pages to facilitate user performance of the next action.   
     
     
         3 . The method of  claim 1 , wherein determining the intervention action via the second machine-learning model includes: inputting a set of input features including a value determined based on the response data into the second machine-learning model. 
     
     
         4 . The method of  claim 3 , further comprising:
 receiving, via the web pages, updated response data from the user; and   determining, based on the updated response data, an updated value.   
     
     
         5 . The method of  claim 4 , further comprising:
 subtracting the value from the updated value to determine a difference;   dividing the difference by a time interval to determine a rate of change; and   determining an updated time interval based on the rate of change.   
     
     
         6 . The method of  claim 1 , wherein performing the intervention action includes:
 opening, via the application, a messaging interface; and   establishing a network connection with a live support agent to allow the user to communicate with the live support agent through the messaging interface.   
     
     
         7 . The method of  claim 1 , further comprising collecting, via the application, additional data that characterizes user behavior during the interaction session, wherein the intervention action is determined based further on the additional data. 
     
     
         8 . A system comprising:
 one or more processors; and   a memory storing one or more instructions that, when executed on the one or more processors, cause the system to:
 send one or more web pages for display to a user via a network during an interaction session between the user and an application, wherein the one or more web pages include elements for collecting response data from the user; 
 receive, via the web pages, response data from the user, 
 determine, via a first machine-learning model based on the response data, a predicted reason the interaction session is likely to terminate before the user completes a target action; 
 determine, via a second machine-learning model based on the response data and the predicted reason determined by the first machine-learning model, an intervention action for increasing a probability that the user will complete the target action before the interaction session terminates; and 
 perform, via the application, the intervention action. 
   
     
     
         9 . The system of  claim 8 , wherein the instructions, when executed on the one or more processors, further cause the system to:
 determine, via a third machine-learning model based on the response data, a next action the user is anticipated to perform in the application; and   alter at least one aspect of the one or more web pages to facilitate user performance of the next action.   
     
     
         10 . The system of  claim 8 , wherein determining the intervention action via the second machine-learning model includes: inputting a set of input features including a value determined based on the response data into the second machine-learning model. 
     
     
         11 . The system of  claim 10 , wherein the instructions, when executed on the one or more processors, further cause the system to:
 receive, via the web pages, updated response data from the user; and   determine, based on the updated response data, an updated value.   
     
     
         12 . The system of  claim 11 , wherein the instructions, when executed on the one or more processors, further cause the system to:
 subtract the value from the updated value to determine a difference;   divide the difference by a time interval to determine a rate of change; and   determine an updated time interval based on the rate of change.   
     
     
         13 . The system of  claim 8 , wherein performing the intervention action includes:
 opening, via the application, a messaging interface; and   establishing a network connection with a live support agent to allow the user to communicate with the live support agent through the messaging interface.   
     
     
         14 . The system of  claim 8 , wherein the instructions, when executed on the one or more processors, further cause the system to collect, via the application, additional data that characterizes user behavior during the interaction session, wherein the intervention action is determined based further on the additional data. 
     
     
         15 . A method, comprising:
 sending one or more web pages for display to a user via a network during an interaction session between the user and an application, wherein the one or more web pages include elements for collecting response data from the user;   receiving, via the web pages, response data from the user,   determining, via a second machine-learning model based on the response data and a value determined by a first machine-learning model, a predicted reason the interaction session is likely to terminate before the user completes a target action;   determining, based on the response data and the predicted reason determined by the second machine-learning model, an intervention action for increasing a probability that the user will complete the target action before the interaction session terminates; and   performing, via the application, the intervention action.   
     
     
         16 . The method of  claim 15 , further comprising:
 determining, via a third machine-learning model based on the response data, a next action the user is anticipated to perform in the application; and   altering at least one aspect of the one or more web pages to facilitate user performance of the next action.   
     
     
         17 . The method of  claim 15 , further comprising:
 receiving, via the web pages, updated response data from the user; and   determining, via the first machine-learning model based on the updated response data, an updated value.   
     
     
         18 . The method of  claim 17 , further comprising:
 subtracting the value from the updated value to determine a difference;   dividing the difference by a time interval to determine a rate of change; and   determining an updated time interval based on the rate of change.   
     
     
         19 . The method of  claim 15 , wherein performing the intervention action includes:
 opening, via the application, a messaging interface; and   establishing a network connection with a live support agent to allow the user to communicate with the live support agent through the messaging interface.   
     
     
         20 . The method of  claim 15 , further comprising collecting, via the application, additional data that characterizes user behavior during the interaction session, wherein the value is further based on the additional data.