# US 2021/0279729 A1 · Method and system for detecting fraudulent financial transaction

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0279729 A1
- Document ID: US20210279729A1
- Status: Published application
- Kind: A1
- Application number: 17/192,442
- Filed: 2021-03-04
- Published: 2021-09-09
- Earliest claimed: 2020-03-09
- Assignees: LINE Corporation
- Applicants: LINE Corporation
- Inventors: Changseon LEE; Jaeyong LIM
- Web page: https://patentgrep.com/patent/US20210279729A1

## CPC

- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G06Q 20/322: {Aspects of commerce using mobile devices [M-devices]}
- G06Q 20/405: {Establishing or using transaction specific rules}
- G06Q 40/12: Accounting
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Disclosed is a method and system for detecting a fraudulent financial transaction including collecting, by processing circuitry, transaction details from a financial institution, classifying, by the processing circuitry, each of a plurality of users into a respective set of groups among a plurality of groups for each of a plurality of transaction action types, the plurality of users corresponding to the transaction details, and determining, by the processing circuitry, whether a first user among the plurality of users is in a risk group based on a first set of groups among the plurality of groups into which the first user is classified.

## Claims

### Claim 1

A fraudulent financial transaction detection method performed by a computer apparatus comprising processing circuitry, the fraudulent financial transaction detection method comprising:
collecting, by the processing circuitry, transaction details from a financial institution;
classifying, by the processing circuitry, each of a plurality of users into a respective set of groups among a plurality of groups for each of a plurality of transaction action types, the plurality of users corresponding to the transaction details; and
determining, by the processing circuitry, whether a first user among the plurality of users is in a risk group based on a first set of groups among the plurality of groups into which the first user is classified.

### Claim 2 (depends on 1)

The fraudulent financial transaction detection method of claim 1, wherein the determining comprises determining whether the first user is in the risk group based on a sum of scores set for the first set of groups.

### Claim 3 (depends on 1)

The fraudulent financial transaction detection method of claim 1, wherein the plurality of transaction action types comprise at least two actions among Buy, Sell, Send, Receive, Deposit, Withdrawal, External Send, or External Receive.

### Claim 4 (depends on 1)

The fraudulent financial transaction detection method of claim 1, wherein the classifying comprises classifying each of the plurality of users into the respective set of groups by inputting the transaction details to a machine learning module trained to classify users into the plurality of groups for each of the plurality of transaction action types based on corresponding transaction details

### Claim 5 (depends on 4)

The fraudulent financial transaction detection method of claim 4, wherein the machine learning module is trained to output a score for each of the respective set of groups into which the users are classified.

### Claim 6 (depends on 1)

The fraudulent financial transaction detection method of claim 1, wherein the classifying comprises:
calculating an average value for each of a plurality of transaction action items corresponding to the plurality of transaction action types; and
classifying each of the plurality of users into the respective set of groups by clustering the plurality of users based on a distance between a value of each of the plurality of transaction action items and an average value of each of the plurality of transaction action items, the plurality of transaction action items corresponding to a plurality of transaction actions triggered by the plurality of users.

### Claim 7 (depends on 6)

The fraudulent financial transaction detection method of claim 6, wherein the classifying further comprises calculating a score of each of the plurality of groups using a distance formula based on the distance and a directivity.

### Claim 8 (depends on 1)

The fraudulent financial transaction detection method of claim 1, wherein the classifying comprises classifying the plurality of users into the plurality of groups for each of the transaction action types based on a value of each of a plurality of transaction action items and a standard deviation of each of the plurality of transaction action items, the plurality of transaction action items corresponding to a plurality of transaction actions triggered by the plurality of users.

### Claim 9 (depends on 1)

A non-transitory computer-readable record medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform the fraudulent financial transaction detection method of claim 1.

### Claim 10

A computer apparatus comprising:
processing circuitry configured to cause the computer apparatus to,
collect transaction details from a financial institution,
classify each of a plurality of users into a respective set of groups among a plurality of groups for each of a plurality of transaction action types, the plurality of users corresponding to the transaction details, and
determine whether a first user among the plurality of users is in a risk group based on a first set of groups among the plurality of groups into which the first user belongs is classified.

### Claim 11 (depends on 10)

The computer apparatus of claim 10, wherein the processing circuitry is configured to cause the computer apparatus to determine whether the first user is in the risk group based on a sum of scores set for the first set of groups.

### Claim 12 (depends on 10)

The computer apparatus of claim 10, wherein the processing circuitry is configured to cause the computer apparatus to classify each of the plurality of users into the respective set of groups by inputting the transaction details to a machine learning module trained to classify users into the plurality of groups for each of the plurality of transaction action types based on corresponding transaction details.

### Claim 13 (depends on 10)

The computer apparatus of claim 10, wherein the processing circuitry is configured to cause the computer apparatus to:
calculate an average value for each of a plurality of transaction action items corresponding to the plurality of transaction action types; and
classify each of the plurality of users into the respective set of groups by clustering the plurality of users based on a distance between a value of each of the plurality of transaction action items and an average value of each of the plurality of transaction action items.

### Claim 14 (depends on 10)

The computer apparatus of claim 10, wherein the processing circuitry is configured to cause the computer apparatus to classify the plurality of users into the plurality of groups for each of the transaction action types based on a value of each of a plurality of transaction action items and a standard deviation each of the plurality of transaction action items, the plurality of transaction action items corresponding to a plurality of transaction actions triggered by the plurality of users.

### Claim 15 (depends on 10)

The computer apparatus of claim 10, wherein the plurality of transaction action types comprise at least two actions among Buy, Sell, Send, Receive, Deposit, Withdrawal, External Send, or External Receive.

### Claim 16 (depends on 12)

The computer apparatus of claim 12, wherein the machine learning module is trained to output a score for each of the respective set of groups into which the users are classified.

### Claim 17 (depends on 13)

The computer apparatus of claim 13, wherein the processing circuitry is configured to cause the computer apparatus to calculate a score of each of the plurality of groups using a distance formula based on the distance and a directivity.

### Claim 18 (depends on 1)

The fraudulent financial transaction detection method of claim 1, further comprising:
generating a signal indicating that the first user is in the risk group in response to determining the first user is in the risk group.

### Claim 19 (depends on 18)

The fraudulent financial transaction detection method of claim 18, further comprising:
causing a requested transaction to be blocked by sending the signal to the financial institution.

### Claim 20 (depends on 1)

The fraudulent financial transaction detection method of claim 1, further comprising:
blocking a requested transaction in response to determining the first user is in the risk group.
