# US 12,217,256 B2 · Scaling transactions with signal analysis

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

- Number: US 12,217,256 B2
- Document ID: US12217256B2
- Status: Granted
- Kind: B2
- Application number: 17/064,627
- Filed: 2020-10-07
- Published: 2022-04-07
- Granted: 2025-02-04
- Earliest claimed: 2020-10-07
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Shuyan Lu; Yi-Hui Ma; Eugene Irving Kelton; John H. Walczyk, III; Brandon Harris
- Web page: https://patentgrep.com/patent/US12217256B2

## CPC

- G06Q 20/389: {Keeping log of transactions for guaranteeing non-repudiation of a transaction}
- G06F 9/3836: {Instruction issuing, e.g. dynamic instruction scheduling or out of order instruction execution}
- G06F 9/466: {Transaction processing}
- G06F 17/14: Fourier, Walsh or analogous domain transformations {, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms (for correlation function computation G06F17/156; spectrum analysers G01R23/16)}
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06Q 20/4015: {using location information}
- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G06Q 20/405: {Establishing or using transaction specific rules}
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises determining a pattern within received data based on a periodicity associated with the received data; in response to a calculated signal score associated with the determined pattern of the received data meeting or exceeding a predetermined threshold transaction amount, tracing at least one location associated with the received data; and dynamically suspending an action associated with an account that generated the received data in response to the traced location not being associated with a historical baseline of the account.

## Claims

### Claim 1

A computer-implemented method comprising:
transforming, by a processor set, received data from a time function to a frequency function of the received data;
applying, by the processor set, a filter to the frequency function to remove transactional noise;
utilizing, by the processor set, a fraud detection classification model to determine a pattern within the received data based on standardizing the received data and a periodicity associated with the frequency function of the received data;
generating, by the processor set, a signal score associated with the determined pattern of the received data based, at least in part, on an identified cycle value indicative of a complexity of the received data wherein the identified cycle value is based on an amount of time for a data cleaning algorithm to determine the periodicity;
in response to determining that the generated signal score meets or exceeds a predetermined threshold transaction amount, tracing, by the processor set, at least one location associated with the received data;
dynamically suspending, by the processor set, a processing of a computer-based transaction associated with an account that generated the received data in response to the traced location not being associated with a historical baseline of the account; and
in response to receiving a user input, processing, by the processor set, a suspended computer-based transaction.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein determining the pattern comprises:
calculating an auto-covariance associated with the received data by converting the received data from a time domain to a frequency domain;
identifying peaks within the calculated auto-covariance associated with the received data, wherein the identified peaks are a maximum amount over a concentrated period of time;
determining a periodicity of the identified peaks by applying a statistical standardization to the identified peaks within the calculated auto-covariance; and
determining a pattern associated with the received data based on the determined periodicity of the identified peaks.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein determining the periodicity of the determined pattern comprises:
converting the received data from the time domain to the frequency domain by applying a Fourier transform algorithm.

### Claim 4 (depends on 2)

The computer-implemented method of claim 2, wherein determining the periodicity of the determined pattern comprises:
tracing at least one location associated with the received data in response to a calculated frequency associated with the received data meeting or exceeding a predetermined threshold of transaction frequency.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, further comprising generating a line graph displaying the calculated auto-covariance and identified peaks of the received data.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, further comprising generating a second line graph by removing received data that does not meet or exceed the predetermined threshold transaction frequency.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the location is a physical location and a technical location.

### Claim 8

A computer program product comprising:
one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to transform received data from a time function to a frequency function of the received data;
program instructions to apply a filter to the frequency function to remove transactional noise;
program instructions to utilize a fraud detection classification model to determine a pattern within the received data based on standardizing the received data and a periodicity associated with the frequency function of the received data;
program instructions to generate a signal score associated with the determined pattern of the received data based, at least in part, on an identified cycle value indicative of a complexity of the received data wherein the identified cycle value is based on an amount of time for a data cleaning algorithm to determine the periodicity;
in response to determining that the generated signal score meets or exceeds a predetermined threshold transaction amount, program instructions to trace at least one location associated with the received data;
program instructions to dynamically suspend a processing of a computer-based transaction associated with an account that generated the received data in response to the traced location not being associated with a historical baseline of the account; and
in response to receiving a user input, processing, by the processor set, a suspended computer-based transaction.

### Claim 9 (depends on 8)

The computer program product of claim 8, wherein the program instructions to determine the pattern comprise:
program instructions to calculate an auto-covariance associated with the received data by converting the received data from a time domain to a frequency domain;
program instructions to identify peaks within the calculated auto-covariance associated with the received data, wherein the identified peaks are a maximum amount over a concentrated period of time;
program instructions to determine a periodicity of the identified peaks by applying a statistical standardization to the identified peaks within the calculated auto-covariance; and
program instructions to determine a pattern associated with the received data based on the determined periodicity of the identified peaks.

### Claim 10 (depends on 9)

The computer program product of claim 9, wherein the program instructions to determine the periodicity of the determined pattern comprise:
program instructions to convert the received data from the time domain to the frequency domain by applying a Fourier transform algorithm.

### Claim 11 (depends on 9)

The computer program product of claim 9, wherein the program instructions to determine the periodicity of the determined pattern comprise:
program instructions to trace at least one location associated with the received data in response to a calculated frequency associated with the received data meeting or exceeding a predetermined threshold of transaction frequency.

### Claim 12 (depends on 11)

The computer program product of claim 11, wherein the program instructions stored on the one or more computer readable storage media further comprise:
program instructions to generate a line graph displaying the calculated auto-covariance and identified peaks of the received data.

### Claim 13 (depends on 12)

The computer program product of claim 12, wherein the program instructions stored on the one or more computer readable storage media further comprise:
program instructions to generate a second line graph by removing received data that does not meet or exceed the predetermined threshold transaction frequency.

### Claim 14 (depends on 8)

The computer program product of claim 8, wherein the location is a physical location and a technical location.

### Claim 15

A computer system comprising:
one or more computer processors;
one or more computer readable storage media; and
program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising:
program instructions to transform received data from a time function to a frequency function of the received data;
program instructions to apply a filter to the frequency function to remove transactional noise;
program instructions to utilize a fraud detection classification model to determine a pattern within the received data based on standardizing the received data and a periodicity associated with the frequency function of the received data;
program instructions to generate a signal score associated with the determined pattern of the received data based, at least in part, on an identified cycle value indicative of a complexity of the received data wherein the identified cycle value is based on an amount of time for a data cleaning algorithm to determine the periodicity;
in response to determining that the generated signal score meets or exceeds a predetermined threshold transaction amount, program instructions to trace at least one location associated with the received data;
program instructions to dynamically suspend a processing of a computer-based transaction associated with an account that generated the received data in response to the traced location not being associated with a historical baseline of the account; and
in response to receiving a user input, processing, by the processor set, a suspended computer-based transaction.

### Claim 16 (depends on 15)

The computer system of claim 15, wherein the program instructions to determine the pattern comprise:
program instructions to calculate an auto-covariance associated with the received data by converting the received data from a time domain to a frequency domain;
program instructions to identify peaks within the calculated auto-covariance associated with the received data, wherein the identified peaks are a maximum amount over a concentrated period of time;
program instructions to determine a periodicity of the identified peaks by applying a statistical standardization to the identified peaks within the calculated auto-covariance; and
program instructions to determine a pattern associated with the received data based on the determined periodicity of the identified peaks.

### Claim 17 (depends on 16)

The computer system of claim 16, wherein the program instructions to determine the periodicity of the determined pattern comprise:
program instructions to convert the received data from the time domain to the frequency domain by applying a Fourier transform algorithm.

### Claim 18 (depends on 16)

The computer system of claim 16, wherein the program instructions to determine the periodicity of the determined pattern comprise:
program instructions to trace at least one location associated with the received data in response to a calculated frequency associated with the received data meeting or exceeding a predetermined threshold of transaction frequency.

### Claim 19 (depends on 18)

The computer system of claim 18, wherein the program instructions stored on the one or more computer readable storage media further comprise:
program instructions to generate a line graph displaying the calculated auto-covariance and identified peaks of the received data.

### Claim 20 (depends on 19)

The computer system of claim 19, wherein the program instructions stored on the one or more computer readable storage media further comprise:
program instructions to generate a second line graph by removing received data that does not meet or exceed the predetermined threshold transaction frequency.