Performing an action based on predicted information

Patent metadata

Field	Value
Publication number	US-11514414-B2
Application number	US-202016774969-A
Country	US
Kind code	B2
Filing date	Jan 28, 2020
Priority date	Jan 28, 2020
Publication date	Nov 29, 2022
Grant date	Nov 29, 2022

Abstract

A device may obtain user information associated with a user and first account information associated with the user. The device may determine, based on the user information, user employment information and may determine, based on the first account information, user compensation information. The device may process, using a first machine learning model, the user employment information and the user compensation information to determine predicted future user compensation information. The device may obtain second account information associated with the user and may determine, based on the second account information, new user compensation information. The device may determine whether the new user compensation information is consistent with the predicted future user compensation information. The device may determine a predicted reason for the new user compensation information not being consistent with the predicted future user compensation information. The device may cause, based on the predicted reason, at least one action to be performed.

First claim

What is claimed is:

1. A method, comprising:
obtaining, by a device, user information associated with a user and first account information associated with the user;
determining, by the device and based on the user information, user employment information;
determining, by the device and based on the first account information, user compensation information;
processing, by the device and using a first machine learning model, the user employment information and the user compensation information to determine predicted future user compensation information,
wherein the first machine learning model is trained based on at least a neural network technique that performs pattern recognition with regard to patterns of particular historical information associated with at least one of a particular predicted compensation amount, a particular predicted compensation date, or a particular predicted compensation schedule;

determining, by the device and based on the predicted future user compensation information, a predicted compensation amount and a predicted compensation date;
obtaining, by the device and after determining the predicted future user compensation information, second account information associated with the user;
determining, by the device and based on the second account information, new user compensation information;
determining, by the device, that a difference between a compensation amount associated with the predicted compensation date and the predicted compensation amount is greater than or equal to a threshold,
wherein the compensation amount is determined based on the new user compensation information;

determining, by the device and based on determining that the difference between the compensation amount associated with the predicted compensation date and the predicted compensation amount is greater than or equal to the threshold, that the new user compensation information is not consistent with the predicted future user compensation information;
identifying, by the device and based on the user information, one or more information sources that are different from a source of the user information, the first account, and the second account information;
obtaining, by the device and based on determining that the new user compensation information is not consistent with the predicted future user compensation information, additional information concerning the user from the one or more information sources,
wherein the additional information associated with the user is obtained based on the device causing at least one of crawling or scraping the additional information from the one or more information sources;

processing, by the device and based on determining that the new user compensation information is not consistent with the predicted future user compensation information, the second account information and the additional information concerning the user by using a second machine learning model to determine a predicted reason for the new user compensation information not being consistent with the predicted future user compensation information; and
performing, by the device and based on the predicted reason, an action comprising:
identifying a communication device associated with a representative of an organization that is associated with at least one of the first account information or the second account information, and establishing a first communication session between the communication device and another device.

2. The method of claim 1 , wherein the first account information and the second account information are associated with an account of the user,
wherein causing the action to be performed further comprises:
enrolling the account of the user in an account protection plan.

3. The method of claim 1 , wherein the user information includes at least one of:
a name of the user;
at least one address associated with the user;
an employment status of the user;
an employment title of the user;
an employment type of the user;
a name of an employer of the user; or
at least one address associated with the employer of the user.

4. The method of claim 1 , wherein causing the action to be performed further comprises:
sending, to the other device, an instruction for the user to send another additional information concerning the user;
receiving, from the other device and based on sending the instruction, the other additional information concerning the user; and
causing the first machine learning model to be updated based on at least one of the other additional information concerning the user, the user information, the predicted future user compensation information, the first account information, or the second account information.

5. The method of claim 1 , wherein the first account information and the second account information are associated with a first account of the user,
wherein causing the action to be performed further comprises:
obtaining information concerning a bill;
causing assets of a second account of the user to be transferred to the first account of the user; and
scheduling a date for the bill to be paid using assets of the first account of the user.

6. The method of claim 1 , wherein the first account information and the second account information are associated with an account of the user,
wherein causing the action to be performed comprises:
obtaining information concerning a plurality of bills that are paid via the account of the user;
processing the first account information and the second account information using a third machine learning model to determine a bill payment priority plan; and
causing the plurality of bills to be paid based on the bill payment priority plan.

7. A device, comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, to:
obtain user information associated with a user and first account information associated with an account of the user;
determine, based on the user information, user employment information;
determine, based on the first account information, user compensation information;
process, using a first machine learning model, the user employment information and the user compensation information to determine predicted future user compensation information,
wherein the first machine learning model is trained based on at least a neural network technique that performs pattern recognition with regard to patterns of particular historical information associated with at least one of a particular predicted compensation amount, a particular predicted compensation date, or a particular predicted compensation schedule;

determine, based on the predicted future user compensation information, a predicted compensation amount and a predicted compensation date;
obtain, after determining the predicted future user compensation information, second account information associated with the account of the user;
determine, based on the second account information, new user compensation information;
determine that a difference between a compensation amount associated with the predicted compensation date and the predicted compensation amount is greater than or equal to a threshold,
wherein the compensation amount is determined based on the new user compensation information;

determine, based on determining that the difference between the compensation amount associated with the predicted compensation date and the predicted compensation amount is greater than or equal to the threshold, that the new user compensation information is not consistent with the predicted future user compensation information;
identify, based on the user information, one or more information sources that are different from a source of the user information, the first ac

Assignees

• Capital One Services Llc

Inventors

• Benkreira Abdelkader M'Hamed
• Gulati Latika
• Mossoba Michael

Classifications

• G06N3/08

  Learning methods · CPC title

• G06Q10/105

  Human resources · CPC title

• G06Q20/405

  Establishing or using transaction specific rules · CPC title

• G06Q40/02 Primary

  Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03) · CPC title

• G06Q20/102 Primary

  Bill distribution or payments · CPC title