Systems for securing transactions based on merchant trust score

Patent metadata

Field	Value
Publication number	US-12062052-B2
Application number	US-202318171021-A
Country	US
Kind code	B2
Filing date	Feb 17, 2023
Priority date	May 26, 2020
Publication date	Aug 13, 2024
Grant date	Aug 13, 2024

Abstract

Systems for securing transactions based on merchant trust score are disclosed. The system may receive information identifying a merchant from a user device and, in response, retrieve transaction data associated with the merchant and receive website data in response to receiving information identifying the merchant. The system may use a machine learning model to generate a merchant trust score for the merchant, and determine whether the merchant trust score is less than a predetermined threshold. The system may also generate or retrieve an alternative payment method and provide related information or a recommendation to the user device.

First claim

What is claimed is:

1. A system for securing transactions based on merchant trust scores, 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:
generate, using a machine learning model, a merchant trust score for a merchant, wherein the machine learning model comprises one or more of an artificial neural network, decision trees, support vector machines, a Bayesian network, or combinations thereof;
determine whether the merchant trust score is less than a predetermined threshold; and
responsive to determining that the merchant trust score is less than the predetermined threshold, generate or retrieve a temporary account number and send a first notification comprising the temporary account number to a user device.

2. The system of claim 1 , wherein generating the merchant trust score comprises receiving, from the merchant, merchant data comprising volume spend data, transaction data, or both, and wherein the merchant trust score is based on the merchant data.

3. The system of claim 1 , wherein the instructions are further configured to cause the system to retrieve, from a database, transaction data corresponding to the merchant, and wherein generating the merchant trust score is based on the transaction data.

4. The system of claim 3 , wherein the transaction data comprises one or more of merchant breach history, merchant rate of return, merchant volume, merchant card-not-present (CNP) versus card present (CP) ratio, or combinations thereof.

5. The system of claim 1 , wherein the temporary account number comprises a temporary credit card number.

6. The system of claim 1 , wherein generating the merchant trust score is conducted on a periodic basis, and wherein the instructions are further configured to cause the system to:
determine that a user has navigated to a website associated with the merchant; and
responsive to determining that the user has navigated to the website associated with the merchant, automatically display the merchant trust score via the website.

7. A system for securing transactions based on merchant trust scores, 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:
retrieve, via a web crawler, website data from a website associated with a merchant;
identify one or more features associated with the merchant based on the website data;
generate, using a machine learning model and based on the one or more features, a merchant trust score for the merchant;
determine whether the merchant trust score is less than a predetermined threshold; and
responsive to determining that the merchant trust score is less than the predetermined threshold, generate or retrieve a temporary account number and send a first notification comprising the temporary account number to a user device.

8. The system of claim 7 , wherein the one or more features comprise one or more of a URL, a contact page, a physical location, a phone number, an email address, or combinations thereof.

9. The system of claim 7 , wherein the web crawler comprises a visual web crawler trained to extract and store the one or more features.

10. The system of claim 9 , wherein the visual web crawler is trained to extract and store the one or more features based on relevancy of each feature.

11. The system of claim 7 , wherein retrieving the website data further comprises:
instructing an automated phone dialer to call a phone number listed on the website;
receiving a voice response during the call; and
determining whether the phone number is correctly associated with the merchant based on the voice response.

12. The system of claim 11 , wherein the merchant trust score is further based on determining whether the phone number is correctly associated with the merchant such that when the phone number is correctly associated with the merchant, the merchant trust score is positively influenced, and when the phone number is not correctly associated with the merchant or has no voice response, the merchant trust score is negatively influenced.

13. The system of claim 7 , wherein the instructions are further configured to cause the system to retrieve, from a database, transaction data corresponding to the merchant, and wherein generating the merchant trust score is further based on the transaction data.

14. The system of claim 13 , wherein the transaction data comprises one or more of merchant breach history, merchant rate of return, merchant volume, merchant card-not-present (CNP) versus card present (CP) ration, or combinations thereof.

15. The system of claim 7 , wherein the machine learning model comprises one or more of an artificial neural network, decision trees, support vector machines, a Bayesian network, or combinations thereof.

16. A system for securing transactions based on merchant trust scores, 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:
conduct a simulated checkout process via a website associated with a merchant;
determine one or more types of user information requested by the merchant during the simulated checkout process;
generate, using a machine learning model and based on the one or more types of user information, a merchant trust score for the merchant;
determine whether the merchant trust score is less than a predetermined threshold; and
responsive to determining that the merchant trust score is less than the predetermined threshold, generate or retrieve a temporary account number and send a first notification comprising the temporary account number to a user device.

17. The system of claim 16 , wherein the one or more types of user information comprise one or more of an account number, a social security number, a birthdate, a family member's maiden name, a pet's name, a school name, or combinations thereof.

18. The system of claim 16 , wherein the instructions are further configured to cause the system to retrieve, from a database, transaction data corresponding to the merchant, and wherein generating the merchant trust score is further based on the transaction data.

19. The system of claim 18 , wherein the transaction data comprises one or more of merchant breach history, merchant rate of return, merchant volume, merchant card-not-present (CNP) versus card present (CP) ration, or combinations thereof.

20. The system of claim 16 , wherein the machine learning model comprises one or more of an artificial neural network, decision trees, support vector machines, a Bayesian network, or combinations thereof.

Assignees

• Capital One Services Llc

Inventors

• Bhusri Nimma
• Zhu Xiaoguang
• Chatman Ljubica
• Cuan Lukiih

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• G06F21/313

  using a call-back technique via a telephone network · CPC title

• G06Q30/0609

  Qualifying participants for shopping transactions (payment transaction verification G06Q20/401) · CPC title

• G06Q20/351

  Virtual cards · CPC title