Systems and methods for automated interface-based alert delivery

Abstract

Systems and methods for feature-based alert triggering are disclosed herein. The system can include memory including a model database containing a machine-learning algorithm. The system can include a user device that can receive inputs from a user; and at least one server. The at least one server can: receive electrical signals from the user device, the electrical signals corresponding to a plurality of user inputs provided to the user device; automatically generate input-based features from the received electrical signals; input the input-based features into the machine-learning algorithm; automatically and directly generate a risk prediction with the machine-learning algorithm from the input-based features; and generate and display an alert when the risk prediction exceeds a threshold value.

What is claimed is: 
     
         1 . A system for delivery of a triggered alert, the system comprising:
 memory comprising a model database containing a machine-learning algorithm, wherein the machine-learning algorithm is configured to generate a risk prediction based on inputted features;   a first user device configured to receive inputs from a user;   a second user device; and   at least one server configured to:
 receive communications corresponding to a plurality of user inputs provided to the user device; 
 generate a risk prediction with the machine-learning algorithm based on features generated from the received communications; and 
 direct generation of a user interface on the second user device, the user interface comprising:
 a cohort view comprising at least one graphical depiction of the risk prediction for a set of at least some of a plurality of users in a cohort; 
 a sub-cohort view comprising at least one graphical depiction of the risk prediction for at least one of the users in the cohort; and 
 an individual view comprising at least one graphical depiction of risk sources for one user. 
 
   
     
     
         2 . The system of  claim 1 , wherein the at least one server is configured to switch between the cohort view, the sub-cohort view, and the individual view based on user inputs received from the second user device. 
     
     
         3 . The system of  claim 2 , wherein switching between the cohort view and the sub-cohort view comprises: receiving an input identifying a display sub-cohort from the second user device; generating the at least one graphical depiction of the risk prediction for the at least one of the users in the display sub-cohort; and directing the second user device to generate the sub-cohort view and display the generated at least one graphical depiction of the risk prediction for the at least one of the users in the display sub-cohort. 
     
     
         4 . The system of  claim 3 , wherein the at least one graphical depiction of the risk prediction for the at least one of the users in the display sub-cohort comprises: a graphical depiction of a risk category associated with identified display sub-cohort; an identification window comprising information identifying the at least one of the users in the sub-cohort; a time-dependent risk window displaying risk status over a period of time; and a risk bar identifying a current risk level. 
     
     
         5 . The system of  claim 2 , wherein switching to the individual view comprises: receiving an input identifying the one user; generating the at least one graphical depiction of risk sources for the identified one user; and directing the second user device to generate the individual view and display the generated at least one graphical depiction of risk sources for the identified one user. 
     
     
         6 . The system of  claim 5 , wherein the at least one graphical depiction of risk sources for the identified one user comprises: a time-dependent risk window configured to display risk status over a period of time; and a source window configured to identify sources of risk and parameters characterizing those sources of risk. 
     
     
         7 . The system of  claim 2 , wherein the at least one graphical depiction of the risk prediction for the set of at least some of the plurality of users in the cohort comprises: a cohort window configured to identify a current breakdown of users in the cohort into a plurality of risk-based sub-cohorts; and a trend window configured to display a depiction of time-dependent change to a size of the risk-based sub-cohorts. 
     
     
         8 . The system of  claim 7 , wherein the trend window is configured to display the depiction of the time-dependent change to the size of the risk-based sub-cohorts over a sliding temporal window. 
     
     
         9 . The system of  claim 8 , wherein the trend window is configured to automatically update as the size of the risk-based sub-cohorts changes and as the sliding temporal window shifts. 
     
     
         10 . The system of  claim 1 , wherein generating a risk prediction with the machine-learning algorithm based on features generated from the received communications comprises: generating a feature vector for each of the features; and inputting the feature vectors into the machine-learning algorithm. 
     
     
         11 . A method for delivery a triggered alert, the method comprising:
 receiving communications corresponding to a plurality user inputs provided to a user device by a user;   generating a risk prediction with a machine-learning algorithm based on features generated from the received communications; and   directing generation of a user interface on a second user device, the user interface comprising:
 a cohort view comprising at least one graphical depiction of the risk prediction for a set of at least some of a plurality of users in a cohort; 
 a sub-cohort view comprising at least one graphical depiction of the risk prediction for at least one of the users in the cohort; and 
 an individual view comprising at least one graphical depiction of risk sources for one user. 
   
     
     
         12 . The method of  claim 11 , further comprising switching between the cohort view, the sub-cohort view, and the individual view based on user inputs received from the second user device. 
     
     
         13 . The method of  claim 12 , wherein switching between the cohort view and the sub-cohort view comprises: receiving an input identifying a display sub-cohort from the second user device; generating the at least one graphical depiction of the risk prediction for the at least one of the users in the display sub-cohort; and directing the second user device to generate the sub-cohort view and display the generated at least one graphical depiction of the risk prediction for the at least one of the users in the display sub-cohort. 
     
     
         14 . The method of  claim 13 , wherein the at least one graphical depiction of the risk prediction for the at least one of the users in the display cohort comprises: a graphical depiction of a risk category associated with identified display sub-cohort; an identification window comprising information identifying the at least one of the users in the sub-cohort; a time-dependent risk window displaying risk status over a period of time; and a risk bar identifying a current risk level. 
     
     
         15 . The method of  claim 12 , wherein switching to the individual view comprises: receiving an input identifying the one user; generating the at least one graphical depiction of risk sources for the identified one user; and directing the second user device to generate the individual view and display the generated at least one graphical depiction of risk sources for the identified one user. 
     
     
         16 . The method of  claim 15 , wherein the at least one graphical depiction of risk sources for the identified one user comprises: a time-dependent risk window configured to display risk status over a period of time; and a source window configured to identify sources of risk and parameters characterizing those sources of risk. 
     
     
         17 . The method of  claim 12 , wherein the at least one graphical depiction of the risk prediction for the set of at least some of the plurality of users in the cohort comprises: a cohort window configured to identify a current breakdown of user in the cohort into a plurality of risk-based sub-cohorts; and a trend window configured to display a depiction of time-dependent change to a size of the risk-based sub-cohorts. 
     
     
         18 . The method of  claim 17 , wherein the trend window is configured to display the depiction of the time-dependent change to the size of the risk-based sub-cohorts over a sliding temporal window. 
     
     
         19 . The method of  claim 18 , wherein the trend window is configured to automatically update as the size of the risk-based sub-cohorts changes and as the sliding temporal window shifts. 
     
     
         20 . The method of  claim 11 , wherein generating a risk prediction with the machine-learning algorithm based on features generated from the received communications comprises: generating a feature vector for each of the features; and inputting the feature vectors into the machine-learning algorithm.