US 12,136,093 B2
Techniques to improve fraud detection at financial terminals
Vincent Pham, Champaign, IL (US); Austin Grant Walters, Savoy, IL (US); Jeremy Edward Goodsitt, Champaign, IL (US); Fardin Abdi Taghi Abad, Champaign, IL (US); and Anh Truong, Champaign, IL (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jun. 17, 2022, as Appl. No. 17/843,108.
Application 17/843,108 is a continuation of application No. 16/722,201, filed on Dec. 20, 2019, granted, now 11,403,642.
Prior Publication US 2022/0391913 A1, Dec. 8, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 20/40 (2012.01); G06Q 20/10 (2012.01); G06Q 30/00 (2023.01); G06Q 30/018 (2023.01); G06Q 40/02 (2023.01); G07F 19/00 (2006.01)
CPC G06Q 20/4016 (2013.01) [G06Q 20/1085 (2013.01); G06Q 20/4014 (2013.01); G06Q 30/0185 (2013.01); G06Q 40/02 (2013.01); G07F 19/207 (2013.01)] 20 Claims
OG exemplary drawing
 
9. A computer-implemented method executed on at least one processing circuit, the computer-implemented method comprising:
processing a first image captured by a first device to determine identity data to identify a user that corresponds to the first image, the first image corresponding to a first transaction being submitted via the first device against a first financial account with an associated financial institution;
analyzing one or more images associated with transactions against accounts that differ from the first financial account at different devices within a certain distance of the first device, within a certain time interval of the first transaction, or a combination thereof, to select a second image;
selecting the second image comprising the user based on facial data in the first image and facial data in the second image, the second image corresponding to a second transaction submitted against a second financial account by the user, and wherein the second financial account is different than the first financial account;
identifying a potential fraud associated with the first transaction in response to selection of the second image, wherein identification of the potential fraud comprises:
determining a probability value for fraudulent activity;
comparing the probability value for fraudulent activity against a first threshold value to determine whether to send a notification message to notify the associated financial institution of the potential fraud; and
comparing the probability value for fraudulent activity against a second threshold value to determine whether to send the notification message to instruct the associated financial institution to decline a pending transaction, wherein the pending transaction comprises the first transaction, the second transaction, a subsequent transaction, or a combination thereof by the user; and
communicating a notification message to the associated financial institution of the potential fraud.