Systems and methods for training and executing a recurrent neural network to determine resolutions

Abstract

Disclosed are methods, systems, and non-transitory computer-readable medium for training and using a neural network for subcluster classification. For example, a method may include receiving or generating a plurality of user data sets of users, grouping the plurality of user data sets into one or more clusters of user data sets, grouping each of the one or more clusters into a plurality of subclusters, training the neural network for each of the plurality of subclusters to associate the subcluster with sequential patterns found within the subcluster in order to generate a trained neural network, receiving a first series of transactions of a first user, inputting the first series of transactions into the trained neural network, and classifying the first user into a subcluster of the plurality of subclusters based on the first series of transactions of the first user input into the trained RNN.

1 - 20 . (canceled) 
     
     
         21 . A computer-implemented method for training and using a neural network for subcluster classification, the method comprising:
 receiving or generating, by one or more processors, a plurality of user data sets of users, wherein each user data set in the plurality of user data sets comprises a user identification data of a user and a detailed user data of the user;   grouping the plurality of the user data sets, by the one or more processors, into one or more clusters of user data sets;   grouping, by the one or more processors, each of the one or more clusters into a plurality of subclusters;   identifying, by the one or more processors, at least one model subcluster from the plurality of subclusters;   receiving, by the one or more processors, a request for a model user; and   selecting, by the one or more processors, the model user from the at least one model subcluster, wherein the model user is selected based on a first series of transactions from a first user.   
     
     
         22 . The method of  claim 21 , wherein the grouping each of the one or more clusters into the plurality of subclusters is based on a metric. 
     
     
         23 . The method of  claim 22 , wherein the metric associated with the identified at least one model subcluster from the plurality of subclusters exceeds a predetermined threshold. 
     
     
         24 . The method of  claim 23 , wherein the metric is based on one or more of a credit score, an account balance, an available credit, or a percentage of credit used of users in each of the one or more subclusters. 
     
     
         25 . The method of  claim 21 , wherein the method further comprises:
 based on the model user, generating, by the one or more processors, an indicator of a resolution associated with the model user.   
     
     
         26 . The method of  claim 25 , wherein the generating the indicator of the resolution further comprises converting the indicator into a natural language statement. 
     
     
         27 . The method of  claim 26 , wherein the method further comprises:
 displaying, by the one or more processors, the natural language statement on a device associated with the first user.   
     
     
         28 . The method of  claim 21 , wherein the grouping of the plurality of the user data sets into one or more clusters of user data sets of users is based on one or more of an annual income, an education level, a family size, or a job category of the users. 
     
     
         29 . The method of  claim 21 , wherein the step of receiving or generating a plurality of user data sets of users further comprises:
 removing, by the one or more processors, personally identifiable information from each of the plurality of user data sets.   
     
     
         30 . A computer system for training and using a neural network for subcluster classification, the system comprising:
 a memory having processor-readable instructions stored therein; and   at least one processor configured to access the memory and execute the processor-readable instructions, which when executed by the processor configures the processor to perform a plurality of functions, including functions for:
 receiving or generating a plurality of user data sets of users, wherein each user data set in the plurality of user data sets comprises a user identification data of a user and a detailed user data of the user; 
 grouping the plurality of the user data sets into one or more clusters of user data sets; 
 grouping each of the one or more clusters into a plurality of subclusters; 
 identifying at least one model subcluster from the plurality of subclusters; 
 receiving a request for a model user; and 
 selecting the model user from the at least one model subcluster, wherein the model user is selected based on a first series of transactions from a first user. 
   
     
     
         31 . The system of  claim 30 , wherein the grouping each of the one or more clusters into the plurality of subclusters is based on a metric. 
     
     
         32 . The system of  claim 31 , wherein the metric associated with the identified at least one model subcluster from the plurality of subclusters exceeds a predetermined threshold. 
     
     
         33 . The system of  claim 32 , wherein the metric is based on one or more of a credit score, an account balance, an available credit, or a percentage of credit used of users in each of the one or more subclusters. 
     
     
         34 . The system of  claim 30 , wherein the plurality of functions further comprises:
 based on the model user, generating an indicator of a resolution associated with the model user.   
     
     
         35 . The system of  claim 34 , wherein the generating the indicator of the resolution further comprises converting the indicator into a natural language statement. 
     
     
         36 . The system of  claim 35 , wherein the plurality of functions further comprises:
 displaying the natural language statement on a device associated with the first user.   
     
     
         37 . The method of  claim 30 , wherein the grouping of the plurality of the user data sets into one or more clusters of user data sets of users is based on one or more of an annual income, an education level, a family size, or a job category of the users. 
     
     
         38 . The system of  claim 30 , wherein the receiving or generating a plurality of user data sets of users further comprises:
 removing personally identifiable information from each of the plurality of user data sets.   
     
     
         39 . The method of  claim 37 , wherein the grouping of the each of the one or more clusters into a plurality of subclusters is based on one or more of credit score, an account balance, available credit, or percentage of credit used of users in each of the one or more clusters. 
     
     
         40 . A computer-implemented method for training and using a neural network for subcluster classification, the method comprising:
 receiving or generating, by one or more processors, a plurality of user data sets of users, wherein each user data set in the plurality of user data sets comprises a user identification data of a user and a detailed user data of the user, and wherein receiving or generating the plurality of user data sets includes removing, by the one or more processors, personally identifiable information from each of the plurality of user data sets;   grouping the plurality of the user data sets, by the one or more processors, into one or more clusters of user data sets, wherein the grouping of the plurality of the user data sets into one or more clusters of user data sets is based on one or more of an annual income, an education level, a family size, or a job category of the users;   grouping, by the one or more processors, each of the one or more clusters into a plurality of subclusters;   identifying, by the one or more processors, at least one model subcluster from the plurality of subclusters;   receiving, by the one or more processors, a request for a model user;   selecting, by the one or more processors, the model user from the at least one model subcluster, wherein the model user is selected based on a first series of transactions from a first user;   based on the model user, generating, by the one or more processors, an indicator of a resolution associated with the model user, wherein the generating the indicator of the resolution further comprises converting the indicator into a natural language statement; and   
       displaying, by the one or more processors, the natural language statement on a device associated with the first user.