IP Library › Granted Patent US 11,361,352
Granted Patent B2
US 11,361,352 · App. 16/828,097 · Granted Jun 14, 2022

Method, device, and medium for utilizing machine learning and transaction data to match boycotts of merchants to customers

Inventors: Michael Mossoba (Arlington, VA); Abdelkadar M'Hamed Benkreira (Washington, DC); Joshua Edwards (Philadelphia, PA)
Assignee: Capital One Services, LLC
G06Q30/0609G06Q30/0617
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,361,352
App. No.
16/828,097
Granted
Jun 14, 2022
Kind
B2
Abstract

A device receives third-party boycott data associated with a merchant, and receives customer preference data associated with a customer of the merchant. The device processes the third-party boycott data and the customer preference data, with a machine learning model, to identify a boycott of the merchant that is predicted to be of interest to the customer. The device provides, to a user device of the customer, information identifying the boycott of the merchant and information that solicits the customer to indicate whether the customer desires to join the boycott, and receives, from the user device, information indicating that the customer desires to join the boycott. The device causes a transaction account associated with the customer to be restricted from a transaction with the merchant when the information indicates that the customer desires to join the boycott.

Claims (103)

1. A method, comprising:

receiving, by a device, customer preference data associated with a customer of a merchant and third-party boycott data associated with the merchant;

processing, by the device, the third-party boycott data and the customer preference data, with a machine learning model trained using a particular feature set, to identify a boycott of the merchant that is predicted to be of interest to the customer,

wherein the particular feature set is generated based at least in part by performing dimensionality reduction of historical third-party boycott data and historical customer preferences data, and

wherein the machine learning model applies a classification technique to the particular feature set to determine an output to match boycotts of merchants to customers, of the merchants, that are predicted to have an interest in the boycotts;

determining, by the device, that the customer desires to join the boycott;

receiving, by the device, transaction data associated with the boycott and associated with the merchant;

determining, by the device and based on the transaction data and determining that the customer desires to join the boycott, whether the boycott is an active boycott or a passive boycott,

wherein the active boycott is associated with one or more customers of the merchant, and

wherein the passive boycott is associated with one or more non-customers of the merchant; and

performing, by the device, one or more actions based on the transaction data and information indicating whether the boycott is the active boycott or the passive boycott.

2. The method of claim 1 , further comprising:

receiving, from a user device, information indicating that the customer desires to join the boycott associated with the merchant; and

where determining that the customer desires to join the boycott comprises:

determining that the customer desires to join the boycott based on receiving the information.

3. The method of claim 1 , further comprising:

monitoring information about products associated with the merchant;

determining that information about a particular product, of the products, is negative; and

determining that there is a boycott of the particular product when a quantity of the negative information about the particular product exceeds a threshold amount.

4. The method of claim 1 , further comprising:

causing a transaction account of the customer to be restricted from a transaction with the merchant based on the customer joining the boycott, or

setting restrictions on a transaction card of the customer for transactions with the merchant.

5. The method of claim 1 , further comprising:

providing, to a user device, a notification indicating that a transaction account associated with the customer cannot be used for future purchases until the customer opts out of the boycott or the boycott ends.

6. The method of claim 1 , further comprising:

receiving, from server devices associated with the merchant and based on the third-party boycott data, prior transaction data and transaction data,

the prior transaction data associated with the merchant prior to the boycott,

the prior transaction data indicating one or more of:

historical quantities of products and services sold, or

historical revenue received from sales of the products and the services,

the transaction data associated with the merchant during the boycott, and

the transaction data indicating one or more of:

quantities of the products and services sold during the boycott, or

revenue received from the sales of the products and services during the boycott; and

determining an affect of sales of the products or the services of the merchant subject to the boycott based on the prior transaction data and the transaction data.

7. The method of claim 1 , further comprising:

tracking a quantity of customers that are boycotting the merchant based on the transaction data; and

determining an effect of sales on the merchant based on the tracking the quantity of customers.

8. A device, comprising:

one or more memories; and

one or more processors, communicatively coupled to the one or more memories, to:

receive customer preference data associated with a customer of a merchant and third-party boycott data associated with the merchant;

process the third-party boycott data and the customer preference data, with a machine learning model trained using a particular feature set, to identify a boycott of the merchant that is predicted to be of interest to the customer,

wherein the particular feature set is generated based at least in part by performing dimensionality reduction of historical third-party boycott data and historical customer preferences data, and

wherein the machine learning model applies a classification technique to the particular feature set to determine an output to match boycotts of merchants to customers, of the merchants, that are predicted to have an interest in the boycotts;

receive transaction data associated with the boycott and associated with the merchant; determine, based on the transaction data, whether the boycott is an active boycott or a passive boycott,

wherein the active boycott is associated with one or more customers of the merchant, and

wherein the passive boycott is associated with one or more non-customers of the merchant; and

perform one or more actions based on the transaction data and information indicating whether the boycott is the active boycott or the passive boycott.

9. The device of claim 8 , wherein the one or more processors are further to:

provide, to a user device, information identifying the boycott of the merchant; and

receive, from the user device, information indicating that the customer desires to join the boycott.

10. The device of claim 8 , wherein the one or more processors, when performing one or more actions, are to:

determine a cause of the boycott;

review one or more historical solutions based on the cause of the boycott; and

generate an action plan based on the one or more historical solutions.

11. The device of claim 8 , wherein the one or more processors are further to:

cause a transaction account of the customer to be restricted from a transaction with one or more subsidiaries of the merchant.

12. The device of claim 8 , wherein the one or more processors are further to:

monitor information about products associated with the merchant;

determine that information about a particular product, of the products, is negative; and

determine that there is a boycott of the particular product when a quantity of the negative information about the particular product exceeds a threshold amount.

13. The device of claim 8 , wherein the one or more processors are further to:

set controls on a transaction card of the customer for transactions with the merchant.

14. The device of claim 8 , wherein the one or more processors are further to:

receive, from one or more server devices associated with the merchant and based on the third-party boycott data, prior transaction data and transaction data,

the prior transaction data associated with the merchant prior to the boycott,

the prior transaction data indicating one or more of:

historical quantities of products and services sold, or

historical revenue received from sales of the products and the services,

the transaction data associated with the merchant during the boycott, and

the transaction data indicating one or more of:

quantities of the products and services sold during the boycott, or

revenue received from the sales of the products and services during the boycott; and

determine an effect of sales of the products or the services of the merchant subject to the boycott based on the prior transaction data and the transaction data.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors of a device, cause the one or more processors to:

receive customer preference data associated with a customer of a merchant and third-party boycott data associated with the merchant;

process the third-party boycott data and the customer preference data, with a machine learning model trained using a particular feature set, to identify a boycott of the merchant that is predicted to be of interest to the customer,

wherein the particular feature set is generated based at least in part by performing dimensionality reduction of historical third-party boycott data and historical customer preferences data, and

wherein the machine learning model applies a classification technique to the particular feature set to determine an output to match boycotts of merchants to customers, of the merchants, that are predicted to have an interest in the boycotts;

determine that the customer desires to join the boycott;

receive transaction data associated with the boycott and associated with the merchant;

determine, based on the transaction data and determining that the customer desires to join the boycott, whether the boycott is an active boycott or a passive boycott,

wherein the active boycott is associated with one or more customers of the merchant, and

wherein the passive boycott is associated with one or more non-customers of the merchant; and

perform one or more actions based on the transaction data and information indicating whether the boycott is the active boycott or the passive boycott.

16. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the one or more processors to perform the one or more actions, cause the one or more processors to:

prevent a transaction account from being used for a purchase from the merchant.

17. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the one or more processors to perform the one or more actions, cause the one or more processors to:

retrain the machine learning model based on one or more of:

the transaction data,

information identifying the merchant,

information identifying the customer,

the information indicating that the customer desires to join the boycott, or

the information identifying the boycott of the merchant.

18. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the one or more processors to receive the customer preference data, cause the one or more processors to:

receive information regarding an existing relationship between the customer and the merchant and information regarding one or more interests of the customer.

19. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the one or more processors to perform the one or more actions, cause the one or more processors to:

cause a transaction account of the customer to be restricted from a transaction with a supplier associated with the merchant.

20. The non-transitory computer-readable medium of claim 15 , wherein the instructions further comprise:

track a quantity of customers that are boycotting the merchant based on the transaction data; and

determine an effect of sales on the merchant based on the tracking the quantity of customers.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 24, 2020
From: MOSSOBA, MICHAEL; BENKREIRA, ABDELKADAR M'HAMED; EDWARDS, JOSHUA
To: CAPITAL ONE SERVICES, LLC
Reel/Frame 052211/0642 →
Continuity (2)
Continuation 16425116 · May 29, 2019
Related Publication 20200380577A1 · Dec 3, 2020