US 12,327,252 B2
Utilizing card movement data to identify fraudulent transactions
Molly Johnson, Alexandria, VA (US); Adam Vukich, Springfield, VA (US); and James Zarakas, Centreville, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Mar. 20, 2024, as Appl. No. 18/610,842.
Application 18/052,235 is a division of application No. 16/947,358, filed on Jul. 29, 2020, granted, now 11,501,303, issued on Nov. 15, 2022.
Application 18/610,842 is a continuation of application No. 18/052,235, filed on Nov. 3, 2022, granted, now 11,961,086.
Prior Publication US 2024/0232894 A1, Jul. 11, 2024
Int. Cl. G06Q 20/40 (2012.01); G06Q 20/38 (2012.01)
CPC G06Q 20/4016 (2013.01) [G06Q 20/3821 (2013.01)] 20 Claims
OG exemplary drawing
 
7. A method, comprising:
receiving, by a first device, first data associated with a transaction conducted by a user associated with a second device;
receiving, by the first device and from the second device, a set of second data associated with behavioral data of the user during the transaction;
receiving, by the first device and from the second device, a set of third data relating to the behavioral data during the transaction,
wherein the set of second data and the set of third data are associated with at least one of biometric data or movement data associated with the second device;
processing, by the first device, the first data, the set of second data, and the set of third data, with a fraud detection model, to calculate a fraud score associated with the transaction; and
performing, by the first device, one or more actions based on determining whether the fraud score satisfies a threshold score, wherein the one or more actions comprise at least one of:
providing a notification that the fraud score satisfies the threshold score,
providing a notification authorizing or declining the transaction,
providing the fraud score to a financial institution associated with the second device,
prohibiting the transaction, or
retraining the fraud detection model based on the fraud score.