System and method for automated feature-based alert triggering

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 method of triggering an alert with a computing system, the method comprising:
 receiving electrical signals corresponding to a plurality of user inputs to a computing system;   automatically generating input-based features from the received electrical signals;   inputting the input-based features into a machine-learning algorithm;   automatically and directly generating a risk prediction with the machine-learning algorithm from the input-based features; and   generating and displaying an alert when the risk prediction exceeds a threshold value.   
     
     
         2 . The method of  claim 1 , wherein at least some of the input-based features are meaningful features. 
     
     
         3 . The method of  claim 2 , wherein the meaningful features are generated from substance identified in the received electrical signals. 
     
     
         4 . The method of  claim 3 , wherein at least some of the input-based features are non-meaningful features. 
     
     
         5 . The method of  claim 4 , wherein the non-meaningful features are independent of the substance identified in the received electrical signals. 
     
     
         6 . The method of  claim 5 , wherein the features comprise at least two from: a Hurst coefficient; a percent correct on first try; an average score; an average part score; a number of attempted parts; an average number of attempted parts; and an aggregation parameter. 
     
     
         7 . The method of  claim 6 , further comprising: generating a response from the received electrical signals; and automatically evaluating the response according to stored evaluation data. 
     
     
         8 . The method of  claim 7 , wherein the meaningful features are generated based on the generated response. 
     
     
         9 . The method of  claim 7 , wherein at least some of the meaningful features are generated based on the generated response and the evaluation of the response. 
     
     
         10 . The method of  claim 1 , wherein the machine-learning algorithm comprises at least one of: a Random Forrest algorithm; an AdaBoost algorithm; a Naïve Bayes algorithm; Boosting Tree, and a Support Vector Machine. 
     
     
         11 . A system for triggering an 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 user device configured to receive inputs from a user; and   at least one server configured to:
 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. 
   
     
     
         12 . The system of  claim 11 , wherein at least some of the input-based features are meaningful features. 
     
     
         13 . The system of  claim 12 , wherein the meaningful features are generated from substance identified in the received electrical signals. 
     
     
         14 . The system of  claim 13 , wherein at least some of the input-based features are non-meaningful features. 
     
     
         15 . The system of  claim 14 , wherein the non-meaningful features are independent of the substance identified in the received electrical signals. 
     
     
         16 . The system of  claim 15 , wherein the features comprise at least two from: a Hurst coefficient; a percent correct on first try; an average score; an average part score; a number of attempted parts; an average number of attempted parts; and an aggregation parameter. 
     
     
         17 . The system of  claim 16 , wherein the at least one server is further configured to: generate a response from the received electrical signals; and automatically evaluate the response according to stored evaluation data, wherein the alert comprises a graphical depiction of the risk prediction. 
     
     
         18 . The system of  claim 17 , wherein the meaningful features are generated based on the generated response. 
     
     
         19 . The system of  claim 17 , wherein at least some of the meaningful features are generated based on the generated response and the evaluation of the response. 
     
     
         20 . The system of  claim 11 , wherein the machine-learning algorithm comprises at least one of: a Random Forrest algorithm; an AdaBoost algorithm; a Naïve Bayes algorithm; Boosting Tree, and a Support Vector Machine.