# US 12,008,644 B2 · Guidance engine: an automated system and method for providing financial guidance

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

- Number: US 12,008,644 B2
- Document ID: US12008644B2
- Status: Granted
- Kind: B2
- Application number: 18/137,023
- Filed: 2023-04-20
- Published: 2023-08-10
- Granted: 2024-06-11
- Earliest claimed: 2019-11-12
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Katharine Schlesinger; John Rush; Zheyu Yang; Matthew Davis
- Web page: https://patentgrep.com/patent/US12008644B2

## CPC

- G06Q 40/03: Credit; Loans; Processing thereof
- G06F 16/258: {Data format conversion from or to a database}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Aspects described herein may allow for receiving, by a detection server, a plurality of configuration parameters, wherein each configuration parameter includes a type of a risk and an associated level of the risk, with a corresponding automated remediation action for each configuration parameter. A remediation management framework authenticates the detection server for access to the remediation management framework and initiates a scanning of a system of interest, based on the plurality of configuration parameters, by the detection server, to identify one or more risk findings. The remediation management framework receives the identified one more risk findings; and matches each of the one or more risk findings with the plurality of configuration parameters, which then triggers by the remediation management framework, the corresponding automated remediation action associated with each of the one or more risk findings.

## Claims

### Claim 1

A system comprising:
a data integration engine comprising:
one or more first processors; and
first memory storing first instructions that, when executed by the one or more first processors, cause the data integration engine to:
determine user data associated with an estimated monthly expenses of a user, an estimated monthly income of the user, an estimated emergency fund level of the user, and an estimated high interest debt level of the user, wherein at least a portion of the user data is in a non-compliant format; and
convert the portion of the user data in the non-compliant format into a compliant format;
a decision tree engine comprising:
one or more second processors; and
second memory storing second instructions that, when executed by the one or more second processors, cause the decision tree engine to:
receive, from the data integration engine, the user data having the converted portion;
determine, based on the user data having the converted portion, a financial action for the user, wherein determining the financial action comprises determining results for each branch of a decision tree that associates the financial action with combinations of values of the estimated monthly expenses, the estimated monthly income, the estimated emergency fund level, and the estimated high interest debt level; and
cause, via a guidance user interface, an output of the financial action.

### Claim 2 (depends on 1)

The system of claim 1, wherein:
the estimated monthly expenses are associated with total monthly fixed expenses incurred by the user to cover essential needs;
the estimated monthly income comprises a gross, a net, and a discretionary income;
the estimated emergency fund level is based on an amount of liquid assets available to cover the estimated monthly expenses; or
the estimated high interest debt level is associated with a loan with an interest rate above a pre-set threshold.

### Claim 3 (depends on 1)

The system of claim 1, wherein the first instructions, when executed by the one or more first processors, cause the data integration engine to determine the user data by causing the data integration engine to:
receive, via the guidance user interface, first input data associated with the user, wherein the first input data associated with the user comprises data corresponding to at least one of the user's monthly expenses, monthly income, emergency fund level, or high interest debt level;
receive, from one or more external data servers, second input data associated with the user, wherein the second input data associated with the user comprises data corresponding to at least one of the user's monthly expenses, monthly income, emergency fund level, or high interest debt level; and
generate, based on the first input data and the second input data, the user data.

### Claim 4 (depends on 3)

The system of claim 3, wherein the first instructions, when executed by the one or more first processors, further cause the data integration engine to:
based on the first input data and the second input data, generate second user data comprising:
a variability score for each of the estimated monthly expenses of the user, the estimated monthly income of the user, the estimated emergency fund level of the user, and the estimated high interest debt level of the user, wherein the variability score is based on a ratio of an interquartile range (IQR) or standard deviation to a value, and wherein the value is the estimated monthly expenses, the estimated monthly income, the emergency fund level or the high interest debt level; and
a reasonableness score for each of the estimated monthly expenses of the user, the estimated monthly income of the user, the estimated emergency fund level of the user, and the estimated high interest debt level of the user.

### Claim 5 (depends on 4)

The system of claim 4, wherein the second instructions, when executed by the one or more second processors, cause the decision tree engine to determine the financial action for the user by causing the decision tree engine to:
receive second user data; and
determine the financial action for the user further based on the second user data.

### Claim 6 (depends on 1)

The system of claim 1, wherein the first instructions, when executed by the one or more first processors, cause the data integration engine to convert the portion of the user data in the non-compliant format into the compliant format by further causing the data integration engine to:
validate the converted portion by generating a plurality of test cases to test compliance of the converted portion and applying the plurality of test cases to the converted portion.

### Claim 7 (depends on 6)

The system of claim 6, wherein the first instructions cause the data integration engine to generate the plurality of test cases by causing the data integration engine to generate test data configured to test a range of edge result cases associated with the converted portion.

### Claim 8 (depends on 1)

The system of claim 1, wherein the first instructions, when executed by the one or more first processors, further cause the data integration engine to determine the user data based on one or more of the following:
user augmented data;
merchant category code;
credit bureau data;
geographic benchmark estimates;
a cost of living estimate; or
a housing cost estimate.

### Claim 9 (depends on 1)

The system of claim 1, wherein the user data comprises one or more of the following:
an emergency fund savings goal based on a monetary value of one, three, or six months of committed monthly expenses;
an emergency fund shortfall based on an amount the user needs to save to reach the emergency fund savings goal;
an emergency fund save rate based on as a percentage of a discretionary income the user allocates to the estimated emergency fund level of the user; or
an emergency fund timescale based on a number of months to achieve the emergency fund savings goal.

### Claim 10 (depends on 1)

The system of claim 1, wherein the first instructions, when executed by the one or more second processors, cause the decision tree engine to determine the financial action for the user by causing the decision tree engine to:
generate a twelve-cell matrix based on:
an estimated high interest debt load of (1) none, (2) moderate, and (3) high, and
an estimated emergency fund level of (1) less than one month of the estimated monthly expenses, (2) less than three months of the estimated monthly expenses, (3) less than six months of the estimated monthly expenses, and (4) greater than six months of the estimated monthly expenses.

### Claim 11

A method comprising:
determining, by a data integration engine, user data associated with an estimated monthly expenses of a user, an estimated monthly income of the user, an estimated emergency fund level of the user, and an estimated high interest debt level of the user, wherein at least a portion of the user data is in a non-compliant format;
converting, by the data integration engine, the portion of the user data in the non-compliant format into a compliant format;
validating, by the data integration engine, the converted portion of the user data by generating a plurality of test cases to test compliance of the converted portion of the user data and applying the plurality of test cases to the converted portion of the user data;
sending, by the data integration engine and to a decision tree engine, the user data having the converted portion;
determining, by the decision tree engine and based on the user data having the converted portion, a financial action for the user, wherein determining the financial action comprises determining results for each branch of a decision tree that associates the financial action with combinations of values of the estimated monthly expenses, the estimated monthly income, the estimated emergency fund level, and the estimated high interest debt level; and
causing, by the decision tree engine and via a guidance user interface, an output of the financial action.

### Claim 12 (depends on 11)

The method of claim 11, wherein the user data comprises one or more of the following:
an emergency fund savings goal based on a monetary value of one, three, or six months of committed monthly expenses;
an emergency fund shortfall based on an amount the user needs to save to reach the emergency fund savings goal;
an emergency fund save rate based on as a percentage of a discretionary income the user allocates to the estimated emergency fund level of the user; or
an emergency fund timescale based on a number of months to achieve the emergency fund savings goal.

### Claim 13 (depends on 11)

The method of claim 11, wherein determining the user data comprises:
receiving, via the guidance user interface, first input data associated with a user, wherein the first input data associated with the user comprises data corresponding to at least one of the user's monthly expenses, monthly income, emergency fund level, or high interest debt level;
receiving, from one or more external data servers, second input data associated with the user, wherein the second input data associated with the user comprises data corresponding to at least one of the user's monthly expenses, monthly income, emergency fund level, or high interest debt level; and
generating, based on the first input data and the second input data, the user data.

### Claim 14 (depends on 13)

The method of claim 13, wherein determining the financial action further comprises:
based on the first input data and the second input data, generating, by the data integration engine, second user data comprising:
a variability score for each of the estimated monthly expenses of the user, the estimated monthly income of the user, the estimated emergency fund level of the user, and the estimated high interest debt level of the user, wherein the variability score is based on a ratio of an interquartile range (IQR) or standard deviation to a value, and wherein the value is the estimated monthly expenses, the estimated monthly income, the emergency fund level or the high interest debt level; and
a reasonableness score for each of the estimated monthly expenses of the user, the estimated monthly income of the user, the estimated emergency fund level of the user, and the estimated high interest debt level of the user;
receiving, by the decision tree engine and from the data integration engine, the second user data; and
determining, by the decision tree engine, the financial action for the user further based on the second user data.

### Claim 15 (depends on 11)

The method of claim 11, determining the financial action for the user comprises:
generating a twelve-cell matrix based on:
an estimated high interest debt load of (1) none, (2) moderate, and (3) high, and
an estimated emergency fund level of (1) less than one month of the estimated monthly expenses, (2) less than three months of the estimated monthly expenses, (3) less than six months of the estimated monthly expenses, and (4) greater than six months of the estimated monthly expenses.

### Claim 16

A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause a computing device to perform steps comprising:
determining, by a data integration engine, user data associated with an estimated monthly expenses of a user, an estimated monthly income of the user, an estimated emergency fund level of the user, and an estimated high interest debt level of the user, wherein at least a portion of the user data is in a non-compliant format;
converting, by the data integration engine, the portion of the user data in the non-compliant format into a compliant format;
validating, by the data integration engine, the converted portion of the user data by generating a plurality of test cases to test compliance of the converted portion of the user data and applying the plurality of test cases to the converted portion of the user data;
sending, by the data integration engine and to a decision tree engine, the user data having the converted portion;
determining, by the decision tree engine and based on the user data having the converted portion, a financial action for the user, wherein determining the financial action comprises determining results for each branch of a decision tree that associates the financial action with combinations of values of the estimated monthly expenses, the estimated monthly income, the estimated emergency fund level, and the estimated high interest debt level; and
causing, by the decision tree engine and via a guidance user interface, an output of the financial action.

### Claim 17 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the user data comprises one or more of the following:
an emergency fund savings goal based on a monetary value of one, three, or six months of committed monthly expenses;
an emergency fund shortfall based on an amount the user needs to save to reach the emergency fund savings goal;
an emergency fund save rate based on as a percentage of a discretionary income the user allocates to the estimated emergency fund level of the user; or
an emergency fund timescale based on a number of months to achieve the emergency fund savings goal.

### Claim 18 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the instructions cause the computing device to determine the user data by:
receiving, via the guidance user interface, first input data associated with a user, wherein the first input data associated with the user comprises data corresponding to at least one of the user's monthly expenses, monthly income, emergency fund level, or high interest debt level;
receiving, from one or more external data servers, second input data associated with the user, wherein the second input data associated with the user comprises data corresponding to at least one of the user's monthly expenses, monthly income, emergency fund level, or high interest debt level; and
generating, based on the first input data and the second input data, the user data.

### Claim 19 (depends on 18)

The non-transitory computer-readable medium of claim 18, wherein the instructions further cause the computing device to determine the financial action by:
based on the first input data and the second input data, generating, by the data integration engine, second user data comprising:
a variability score for each of the estimated monthly expenses of the user, the estimated monthly income of the user, the estimated emergency fund level of the user, and the estimated high interest debt level of the user, wherein the variability score is based on a ratio of an interquartile range (IQR) or standard deviation to a value, and wherein the value is the estimated monthly expenses, the estimated monthly income, the emergency fund level or the high interest debt level; and
a reasonableness score for each of the estimated monthly expenses of the user, the estimated monthly income of the user, the estimated emergency fund level of the user, and the estimated high interest debt level of the user;
receiving, by the decision tree engine and from the data integration engine, the second user data; and
determining, by the decision tree engine, the financial action for the user further based on the second user data.

### Claim 20 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the instructions cause the computing device to determine the financial action by:
generating a twelve-cell matrix based on:
an estimated high interest debt load of (1) none, (2) moderate, and (3) high, and an estimated emergency fund level of (1) less than one month of the estimated monthly expenses, (2) less than three months of the estimated monthly expenses, (3) less than six months of the estimated monthly expenses, and (4) greater than six months of the estimated monthly expenses.