US 12,190,344 B2
Systems and methods for automatically providing customized financial card incentives
Jenny Melendez, Falls Church, VA (US); Joshua Peters, Charlottesville, VA (US); Zachary Sweeney, McLean, VA (US); Samuel Rapowitz, Roswell, GA (US); Steven Black, Arlington, VA (US); Bryant Yee, Silver Spring, MD (US); and Alexander Lin, Arlington, VA (US)
Assigned to CAPITAL ONE SERVICES, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Feb. 1, 2023, as Appl. No. 18/162,891.
Application 18/162,891 is a continuation of application No. 17/668,307, filed on Feb. 9, 2022, granted, now 11,599,900.
Prior Publication US 2023/0252517 A1, Aug. 10, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/0207 (2023.01); G06Q 20/38 (2012.01); G06Q 20/40 (2012.01)
CPC G06Q 30/0236 (2013.01) [G06Q 20/389 (2013.01); G06Q 20/4014 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to:
receive first transaction data regarding a first transaction associated with a user;
determine whether the first transaction was made during a predetermined date range;
responsive to determining that the first transaction was made during the predetermined date range:
retrieve user similarity data;
generate, using a k-means clustering algorithm, a value representing a confidence score that the user is a first type by comparing the user similarity data to data of users known to be the first type;
determine whether the value is greater than or equal to a predetermined threshold;
responsive to determining that the value is greater than or equal to the predetermined threshold:
receive or retrieve comprehensive user data;
classify, using a neural network, the user as the first type or a second type based on the comprehensive user data and the user similarity data; and
responsive to classifying the user as the first type:
 verify, using the first transaction data, that the first transaction is associated with the first type by:
 receiving, from a user device, image data of a receipt for the first transaction;
 processing, using optical character recognition (OCR), the image data to obtain receipt data; and
 verifying the first transaction is associated with the first type using the receipt data;
generate a first amount of rewards that the first transaction qualifies for based on the first transaction data; and
transmit, to a user device, an indication to update a graphical object to show that first transaction qualifies for an incentive; and
responsive to classifying the user as the second type, determining that the value is not greater than or equal to the predetermined threshold, or determining that the first transaction was not made during the predetermined date range, generate a second amount of rewards that the first transaction qualifies for based on the first transaction data, wherein the first amount of rewards is different from the second amount of rewards.