Computer-based systems having computing devices programmed to execute fraud detection routines based on feature sets associated with input from physical cards and methods of use thereof

Patent metadata

Field	Value
Publication number	US-2022253857-A1
Application number	US-202217677961-A
Country	US
Kind code	A1
Filing date	Feb 22, 2022
Priority date	Nov 26, 2019
Publication date	Aug 11, 2022
Grant date	—

Abstract

Systems and methods for performing fraud detection at POA devices based on analysis of feature sets are disclosed. In one embodiment, an exemplary method may comprise: obtaining, by a POS device, upon initiation of a transaction involving a card or a card and mobile device associated with an individual initiating the transaction, one or more sensory inputs and an identifier; mapping, by the POS device, the one or more sensory inputs to a first cluster position of a plurality of clusters; determining whether the cluster position of the cluster mapped for the transaction corresponds to a second cluster position of the at least one expected cluster associated with the known owner of the card and/or mobile device; and initiating, by the POS device, at least one second factor authentication process to establish that the individual is the known owner of the card and/or mobile device being used in the transaction.

First claim

1 .- 20 . (canceled)

21 . One or more computer-readable media containing and/or configured to execute computer-readable instructions, the computer-readable instructions comprising instructions that, when executed by one or more processors, cause the one or more processors to perform a method comprising:
obtaining, by a point-of-service (POS) device, upon initiation of a transaction involving (1) a card or (2) the card and a mobile device associated with an individual transacting with the POS device:
(i) one or more sensory inputs associated with a use of the one or both of the card and the mobile device for the transaction, the one or more sensory inputs comprising one or more card-acquired sensory inputs received from one or more sensors on the card;
wherein the one or more sensory inputs comprise sensory feedback measured by the one or more sensors based on usage of the card for the transaction; and
wherein the one or more sensory inputs are saved into the card as a feature set and transmitted to the POS device upon the initiation of the transaction; and

(ii) an identifier (1) associated with an owner of the one or both of the card and the mobile device and (2) used to determine whether the one or more sensory inputs are consistent with prior transaction behavior of the owner;
transforming, using a machine learning technique, the one or more sensory inputs associated with the transaction into feature information having a format configured for comparison against historical feature data established by applying the machine learning technique to historical card-usage information of the owner; performing sensory input mapping of the feature information to a cluster position of at least one particular cluster of a plurality of clusters, wherein the plurality of clusters defines sets of learned features regarding prior known interactions of owners of cards with POS devices; performing a fraud determination based on mapping of the cluster position of the at least one particular cluster to at least one expected cluster associated with the known owner of the one or both of the card and mobile device; and approving the transaction based on the fraud determination.

22 . The computer-readable media of claim 21 wherein the plurality of clusters are provided to the POS device via a smart card (SIM card) or other computer-readable medium that is provided from an entity associated with the one or both of the card and the mobile device and/or an entity involved with preventing fraudulent transactions.

23 . The computer-readable media of claim 21 wherein the plurality of clusters are provided to the POS device via download from one or more servers associated with at least one entity involved in the prevention of fraudulent transactions.

24 . The computer-readable media of claim 21 , wherein the method further comprises:
initiating, by the POS device, at least one second factor authentication process to establish that the individual transacting with the POS device is the known owner of the one or both of the card and the mobile device being used in the transaction when the first cluster position of the at least one particular cluster does not correspond to the second cluster position of the at least one expected cluster; and/or, optionally: wherein the second factor authentication is triggered via processing performed by the POS device, and the second factor authentication is performed at the POS device.

25 . The computer-readable media of claim 21 wherein the determining when the cluster position of the at least one particular cluster mapped for the transaction matches the second cluster position is performed at the POS device, such that the fraud determination may be performed on-site at the POS device without need for communicating with remote entities to make the fraud determination.

26 . The computer-readable media of claim 21 wherein the one or more inputs comprise one or more of:
(i) features of the card including one or more of dimension(s) of card, name on card, and/or material and/or color of card;
(ii) location and/or movement of the card and/or the mobile device; and/or
(iii) biometric or other information regarding the individual transacting with the card and/or mobile device.

27 . The computer-readable media of claim 21 wherein mapping the one or more sensory inputs to the first cluster position comprises direct mapping of the one or more sensory inputs to the first cluster position.

28 . The computer-readable media of claim 21 wherein mapping the one or more sensory inputs to the first cluster position comprises generating a feature set or model of the one or more sensory inputs, and mapping the feature set or model to the first cluster position.

29 . The computer-readable media of claim 21 , wherein the method further comprises:
receiving, by the mobile device, the one or more sensory inputs; utilizing, by the mobile device, a machine learning algorithm to generate, based on the one or more sensory inputs a feature set representing the one or more sensory inputs; and hashing, by the mobile device, the feature set to obtain an expected cluster that is specific to an individual associated with the mobile device.

30 . The computer-readable media of claim 29 wherein the machine learning algorithm is specifically configured to an individual associated with the mobile device.

31 . The computer-readable media of claim 21 , wherein the method further comprises:
authorizing the transaction when the first cluster position of the at least one particular cluster does correspond to the second cluster position of the at least one expected cluster.

32 . The computer-readable media of claim 21 , wherein the method further comprises:
implementing a second factor authentication process to approve the transaction, wherein the second factor authentication process comprises generating an alert to a merchant associated with the POS device.

33 . The computer-readable media of claim 21 , wherein the method further comprises:
implementing a second factor authentication process to approve the transaction, wherein the second factor authentication process comprises generating an alert to a financial services entity associated with one or more of the POS device, the card, and/or the owner of the mobile device.

34 . A point of service (POS) device comprising:
at least one card reading component configured to read information from a transaction card, the at least one card reading component comprising one or more of a magnetic stripe reader, a chip reader, and/or a first near field communication (NFC) component; at least one mobile device transceiver component configured to communicate, during execution of a purchase transaction, with a mobile device presented for payment, the mobile device transceiver component comprising a second NFC component; and one or more processing components and/or computer readable media configured for:
obtaining, from one or both of the transaction card and/or the mobile device, upon initiation of the transaction:
(i) one or more sensory inputs associated with a use of the one or both of the card and the mobile device for the transaction, the one or more sensory inputs comprising one or more card-acquired sensory inputs received from one or more sensors on the card;
wherein the one or more sensory inputs comprising sensory feedback measured by the one or more sensors based on usage of the card for the transaction; and
wherein the one or more sensory inputs are saved into the card as a feature set, and transmitted to the POS device upon the initiation of the transaction; and

Assignees

• Capital One Services Llc

Inventors

• Walters Austin
• Rafferty Galen
• Goodsitt Jeremy

Classifications

• G06Q20/4016 Primary

  involving fraud or risk level assessment in transaction processing · CPC title

• G06Q20/40145

  Biometric identity checks · CPC title

• G06Q20/341

  Active cards, i.e. cards including their own processing means, e.g. including an IC or chip · CPC title

• G06Q20/204

  comprising interface for record bearing medium or carrier for electronic funds transfer or payment credit · CPC title

• G06Q20/4014

  Identity check for transactions · CPC title