Utilizing card movement data to identify fraudulent transactions

Patent metadata

Field	Value
Publication number	US-11501303-B2
Application number	US-202016947358-A
Country	US
Kind code	B2
Filing date	Jul 29, 2020
Priority date	Jul 29, 2020
Publication date	Nov 15, 2022
Grant date	Nov 15, 2022

Abstract

A fraud detection platform may receive transaction data relating to a transaction conducted by a user with a transaction card. The fraud detection platform may receive, from a biometric sensor of the transaction card, biometric data relating to one or more biometric characteristics of the user during the transaction. The fraud detection platform may receive, from an accelerometer of the transaction card, card movement data relating to a measure of shaking of the transaction card by the user during the transaction. The fraud detection platform may process the transaction data, the biometric data, and the card movement data, with a fraud detection model, to determine a fraud score associated with the transaction. The fraud detection platform may perform one or more actions based on the fraud score.

First claim

What is claimed is:

1. A method, comprising:
training, by a device and based on historical transaction data relating to transactions conducted by a user with a transaction card, historical biometric data relating to one or more biometric characteristics that relate to a measure of nervousness of the user, and historical card movement data relating to a measure of shaking of the transaction card that relates to the measure of nervousness of the user, a fraud detection model to identify which items of the historical transaction data, the historical biometric data, and the historical card movement data are indicative of fraudulent activity,
wherein the transaction card comprises a biometric sensor and an accelerometer;

receiving, by the device, transaction data relating to a transaction conducted by the user with the transaction card;
receiving, by the device, based on sending a request associated with the transaction, and from the biometric sensor of the transaction card, biometric data relating to the one or more biometric characteristics of the user,
wherein the biometric data is detected by the biometric sensor within a first time frame associated with the transaction;

receiving, by the device, based on sending the request, and from the accelerometer of the transaction card, card movement data related to the measure of shaking of the transaction card by the user,
wherein the card movement data is detected by the accelerometer during a second time frame associated with the transaction;

processing, by the device, the transaction data, the biometric data, and the card movement data, with the fraud detection model, to determine a fraud score associated with the transaction,
wherein processing the transaction data, the biometric data, and the card movement data comprises inputting the transaction data, the biometric data, and the card movement data into the fraud detection model to cause the fraud detection model to output the fraud score; and

performing, by the device, one or more actions based on the fraud score.

2. The method of claim 1 , wherein performing the one or more actions comprises one or more of:
providing, to the transaction card, a notification authorizing the transaction when the fraud score fails to satisfy a threshold score;
providing, to the transaction card, a notification declining the transaction when the fraud score satisfies the threshold score; or
providing, to a client device of the user and based on the fraud score, a notification requesting user input that indicates whether the transaction is approved or unapproved by the user.

3. The method of claim 1 , wherein performing the one or more actions comprises one or more of:
providing the fraud score to a financial institution associated with the transaction card when the fraud score satisfies a threshold score;
causing law enforcement to be dispatched to a location of the user when the fraud score satisfies the threshold score; or
retraining the fraud detection model based on the fraud score.

4. The method of claim 1 , wherein processing the transaction data, the biometric data, and the card movement data comprises one or more of:
increasing the fraud score when the card movement data indicates that a hand of the user satisfies a shaking threshold during the transaction; or
increasing the fraud score when the biometric data indicates that a heart rate of the user satisfies a heart rate threshold.

5. The method of claim 1 , wherein processing the transaction data, the biometric data, and the card movement data comprises one or more of:
refraining from increasing the fraud score when the card movement data indicates that a hand of the user fails to satisfy a shaking threshold during the transaction; or
refraining from increasing the fraud score when the biometric data indicates that a heart rate of the user fails to satisfy a heart rate threshold.

6. The method of claim 1 , wherein performing the one or more actions comprises:
determining whether the transaction is fraudulent based on the fraud score; and
selectively:
preventing the transaction based on the fraud score; or
allowing the transaction based on the fraud score.

7. The method of claim 1 , wherein the transaction is withdrawing money from an automated teller machine; and
wherein performing the one or more actions comprises:
determining that the fraud score satisfies a fraud threshold, and
causing law enforcement to be dispatched to a location of the user based on determining that the fraud score satisfies the fraud threshold.

8. A device, comprising:
one or more processors configured to:
train a fraud detection model with historical transaction data relating to transactions conducted by a user with a transaction card, historical biometric data relating to one or more biometric characteristics that relate to a measure of nervousness of the user, and historical card movement data relating to a measure of shaking of the transaction card that relates to the measure of nervousness of the user,
wherein the transaction card comprises a biometric sensor and an accelerometer;

receive transaction data relating to a transaction conducted by the user with the transaction card;
receive, based on sending a request associated with the transaction, and from the transaction card, biometric data relating to the one or more biometric characteristics of the user,
wherein the biometric data is detected by the biometric sensor within a first time frame associated with the transaction;

receive, based on sending the request, and from the transaction card, card movement data relating to the measure of shaking of the transaction card by the user,
wherein the card movement data is detected by the accelerometer during a second time frame associated with the transaction;

process the transaction data, the biometric data, and the card movement data, with the fraud detection model, to determine a fraud score associated with the transaction,
wherein the one or more processors, when processing the transaction data, the biometric data, and the card movement data, are further configured to input the transaction data, the biometric data, and the card movement data into the fraud detection model to cause the fraud detection model to output the fraud score; and perform one or more actions based on the fraud score.

9. The device of claim 8 , wherein the one or more biometric characteristics include one or more of:
a heart rate of the user,
a perspiration level of the user,
a rate of breathing of the user, or
a shaky voice level of the user.

10. The device of claim 8 , wherein the fraud detection model includes one or more of:
a logistic regression model,
a decision tree model,
a random forest model, or
a neural network model.

11. The device of claim 8 , wherein the one or more processors, when processing the transaction data, the biometric data, and the card movement data, are configured to one or more of:
increase the fraud score when the card movement data indicates that a hand of the user satisfies a shaking threshold during the transaction; or
refrain from increasing the fraud score when the card movement data indicates that the hand of the user fails to satisfy the shaking threshold during the transaction.

12. The device of claim 8 , wherein the fraud detection model is configured to generate a higher score for the fraud score when the one or more biometric characteristics satisfy a biometric threshold and the card movement data satisfies a card movement threshold than when the one or more biometric characteristics fail to satisfy the biometric threshold or the card movement data fails to satisfy the

Assignees

• Capital One Services Llc

Inventors

• Johnson Molly
• Vukich Adam
• ZARAKAS James

Classifications

• G06Q20/4016 Primary

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

• G06Q20/40145

  Biometric identity checks · CPC title

• G06Q20/3821 Primary

  Electronic credentials · CPC title