| CPC G06F 16/21 (2019.01) [G06N 3/08 (2013.01); G06Q 40/02 (2013.01); G06F 21/6245 (2013.01)] | 20 Claims |
|
1. A system for determining whether an entity's shared databases include contractually required confidential information using a machine learning model, said entity including multiple separate divisions, said system comprising:
a repository including a plurality of databases that store data and information in a format accessible to users, said plurality of databases being accessible to personnel in all of the multiple divisions, said plurality of databases including a client interaction and transaction source that stores information and data obtained for each of the interactions and transactions between all of the entity's clients and the entity over all communications channels;
a back-end server operatively coupled to the repository and being responsive to the data and information from all of the databases, said back-end server including:
at least one processor for processing the data and information;
a communications interface communicatively coupled to the at least one processor; and
a memory device storing data and executable code that, when executed, causes the at least one processor to:
transform, via data cleaning, ingested data into a standardized training format for training machine learning models;
train, using training test data in the standardized training format, an unsupervised neural network utilizing interconnected nodes, the unsupervised neural network being trained to process data and information to determine whether databases include contractually required confidential information and determine whether an entity is violating regulatory requirements, the training including:
inserting the training test data into an iterative training and testing loop to predict a target variable; and
repeatedly predicting the target variable during multiple versions of the training and testing loop, each version of the multiple versions having differing weights applied to one or more nodes in one or more layers of the unsupervised neural network, each of the differing weights being updated with each of the multiple versions of the training and testing loop to reduce error in predicting the target variable, which improves predictability of the target variable and functionality of the unsupervised neural network;
deploy the unsupervised neural network;
collect data and information from the plurality of databases;
store the collected data and information in the memory device;
process the stored data and information using the deployed unsupervised neural network to determine whether the databases include contractually required confidential information that one division in the entity is contractually required to maintain secret or confidential from other divisions in the entity;
receive a result from the deployed unsupervised neural network of whether the databases do include contractually required confidential information;
transmit a communication on the interface identifying whether the databases do include contractually required confidential information;
determine that contractually required confidential information that one division is required to maintain secret or confidential from other divisions is being shared with another division, where remedial steps are taken to remove the confidential information from the databases if they are identified;
process the stored data using the deployed unsupervised neural network to determine whether the entity is violating regulatory requirements;
receive a result from the deployed unsupervised neural network that the entity is violating regulatory requirements; and
transmit a communication on the interface identifying that the entity is violating regulatory requirements, where remedial steps are taken to correct the violation of the regulatory requirements.
|