Systems and methods for fraud monitoring

Patent metadata

Field	Value
Publication number	US-2023059064-A1
Application number	US-202117409043-A
Country	US
Kind code	A1
Filing date	Aug 23, 2021
Priority date	Aug 23, 2021
Publication date	Feb 23, 2023
Grant date	—

Abstract

Systems and methods for fraud monitoring are disclosed, including: receiving a transaction request associated with a first instrument of a user; extracting, characteristics of the transaction request; identifying, by the first processor, user data based on the transaction request; determining a fraud severity value and notification value based on inputting the characteristics and user data into a fraud machine learning model; performing a first fraud action based on the fraud severity value; wherein the first fraud action is at least one selected from the group of locking the first instrument for a period of time, deactivating the first instrument, and electronically transmitting a first query message to a user device associated with the first instrument; and transmitting a fraud notification based on the notification value, wherein the fraud notification includes severity information associated with the fraud severity value.

First claim

1 . A computer-implemented method for fraud monitoring, comprising:
receiving, by a first processor, a transaction request associated with a first instrument of a user; identifying, by the first processor, a plurality of data fields in a received transaction request, the plurality of data fields representing a plurality of transaction characteristics comprising a merchant name, a merchant location, one or more transaction items, and a transaction amount; extracting, by the first processor, a data value for each of the plurality of transaction characteristics; identifying, by the first processor, user data from data extracted from the transaction request; retrieving one or more fraud application data from the first instrument of the user identified from the transaction request, wherein the fraud application data comprises current and historical location data associated with the first instrument of the user; determining, by the first processor, a fraud severity value and a fraud notification value based on inputting the data values for the plurality of transaction characteristics, the one or more fraud application data, and user data into a fraud machine learning model; performing a first fraud action, by the first processor, based on the fraud severity value; wherein the first fraud action is at least one selected from the group of locking the first instrument for a period of time, deactivating the first instrument, and electronically transmitting a first query message to the first instrument of the user; and upon determining that fraud notification value exceeds a first notification threshold, transmitting, by the first processor, a fraud notification to a second processor associated with a second instrument of the user over a network, wherein the fraud notification includes severity information associated with the fraud severity value.

2 . (canceled)

3 . The computer-implemented method of claim 1 further comprising:
electronically transmitting, by the first processor, a second query message to the first instrument of the user when the fraud notification value is less than the first notification threshold and greater than a second notification threshold.

4 . The computer-implemented method of claim 1 , wherein the fraud machine learning model is trained with a training set comprising transaction data associated with each of a plurality of instruments.

5 . The computer-implemented method of claim 4 , wherein the training set further comprises fraud impact data associated with each of the plurality of instruments.

6 . The computer-implemented method of claim 4 , wherein the training set further comprises at least one of a fraud status and fraud type associated with each of the plurality of instruments.

7 . The computer-implemented method of claim 4 , wherein the transaction data is retrieved by the first processor from a distributed ledger of a decentralized network.

8 . The computer-implemented method of claim 4 , wherein the transaction data includes information received from at least one second fraud notification transmitted by the second processor to the first processor over the network.

9 . The computer-implemented method of claim 1 , wherein the network is a financial consortium network.

10 . The computer-implemented method of claim 1 , wherein the first fraud action includes locking the first instrument for a period of time, and wherein the period of time is based on the fraud severity value.

11 . The computer-implemented method of claim 1 , further comprising:
receiving application data, by the first processor, from the first instrument of the user; and adjusting one of the fraud severity value and the fraud notification value based on the application data.

12 . (canceled)

13 . The computer-implemented method of claim 1 , further comprising:
receiving fraud preferences, by the first processor, from the first instrument of the user; and adjusting one of the fraud severity value and the fraud notification value based on fraud preferences.

14 . The computer-implemented method of claim 13 , wherein the performing a first fraud action, by the first processor, is based on the fraud preferences.

15 . A computer-implemented system for fraud monitoring, comprising:
a first processor configured to transmit information through a network; and a first server communicatively coupled to the first processor through the network, wherein the first processor is configured to:
receive a transaction request associated with a first instrument of a user;
identify a plurality of data fields in a received transaction request, the plurality of data fields representing a plurality of transaction characteristics comprising a merchant name, a merchant location, one or more transaction items, and a transaction amount;
extract a data value for each of the plurality of transaction characteristics;
identify user data from data extracted from the transaction request;
retrieve one or more fraud application data from the first instrument of the user identified from the transaction request, wherein the fraud application data comprises current and historical location data associated with the first instrument of the user;
determine a fraud severity value and a fraud notification value based on inputting the data values for the plurality of transaction characteristics, the one or more fraud application data and user data into a fraud machine learning model;
perform a first fraud action based on the fraud severity value; wherein the first fraud action is one of locking the first instrument for a period of time, deactivating the first instrument, and electronically transmitting a first query message to the first instrument; and
upon determining that fraud notification value exceeds a first notification threshold, transmit a fraud notification based on the fraud notification value to a second processor associated with a second instrument of the user over a network; wherein the fraud notification includes severity information associated with the fraud severity value.

16 . The computer-implemented system of claim 15 , wherein the first server is configured to transmit the electronic fraud notification to a plurality of financial institutions.

17 . The computer-implemented system of claim 16 , wherein the first server is configured to transmit the fraud notification based on fraud preferences.

18 . The computer-implemented system of claim 17 , wherein the fraud preferences are set by the user associated with instrument.

19 . The computer-implemented system of claim 15 , wherein the first and second instrument are associated with a same financial institution.

20 . A non-transitory computer-accessible medium having stored thereon computer-executable instructions, wherein the computer arrangement comprises a processor, and wherein, upon execution of the instructions, the computer arrangement is configured to perform procedures comprising:
receiving a transaction request associated with a first instrument of a user; identifying a plurality of data fields in a received transaction request, the plurality of data fields representing a plurality of transaction characteristics comprising a merchant name, a merchant location, one or more transaction items, and a transaction amount; extracting a data value for each of the plurality of transaction characteristics; identifying user data from data extracted from the transaction request; retrieving one or more fraud application data from a user device, the user d

Assignees

• Capital One Services Llc

Inventors

• Benkreira Abdelkader
• Maiman Tyler
• Way Brendan

Classifications

• G06N20/00

  Machine learning · CPC title

• G06Q20/4016 Primary

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

• G06Q20/407

  Cancellation of a transaction · CPC title

• G06Q20/405

  Establishing or using transaction specific rules · CPC title

• G06Q20/42

  Confirmation, e.g. check or permission by the legal debtor of payment · CPC title