# US 2022/0027983 A1 · Customized credit card debt reduction plans

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

- Number: US 2022/0027983 A1
- Document ID: US20220027983A1
- Status: Published application
- Kind: A1
- Application number: 16/937,400
- Filed: 2020-07-23
- Published: 2022-01-27
- Earliest claimed: 2020-07-23
- Assignees: Intuit Inc.
- Applicants: Intuit Inc.
- Inventors: Daniel Ben David; Yehezkel Shraga Resheff; Yair Horesh; Nirmala Ranganathan
- Web page: https://patentgrep.com/patent/US20220027983A1

## CPC

- G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03)
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06Q 40/03: Credit; Loans; Processing thereof
- 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

This disclosure relates to systems and methods for constructing a customized debt reduction plan for a user. In some implementations, a customized debt reduction system obtains a plurality of financial attributes of the user and a plurality of other users, where the plurality of financial attributes are indicative of credit card debt, and identifies users from the plurality of other users who successfully repaid their credit card debt based on their respective financial attributes and one or more repayment techniques that resulted in successful repayment of their credit card debt. The customized debt reduction system correlates the plurality of financial attributes of the user with the plurality of financial attributes of a number of the identified users and determines a personalized score for the user, using a trained machine learning model, based on the correlation to determine a customized debt reduction plan for the user based on the personalized score.

## Claims

### Claim 1

A method for reducing credit card debt of a user, the method performed by one or more processors of a computing device and comprising:
determining a set of financial attributes and a demographic profile of each of a plurality of consumers, each set of financial attributes indicative of credit card debt associated with a respective consumer of the plurality of consumers;
identifying a number of the consumers who successfully repaid credit card debt based at least in part on their respective sets of financial attributes;
determining a plurality of debt reduction plans used by the identified consumers to repay their respective credit card debts;
correlating one or more financial attributes and a demographic profile of the user with the sets of financial attributes and the demographic profiles, respectively, of the identified consumers;
training a machine learning model, using the correlations of financial attributes and demographic profiles between the user and the identified consumers, to determine a likelihood of the user repaying the credit card debt using each of the determined debt reduction plans; and
determining a customized debt reduction plan for the user based on the determined likelihoods.

### Claim 2 (depends on 1)

The method of claim 1, wherein each set of financial attributes includes one or more of an amount of previous credit card debt of a respective consumer, an amount of current credit card debt of the respective consumer, an annual percentage rate (APR) associated with the credit card debt of the respective consumer, payment due dates associated with the credit card debt of the respective consumer, net savings of the respective consumer, net cash flow of the respective consumer, or an intent of the respective consumer to pay-off the credit card debt.

### Claim 3 (depends on 2)

The method of claim 2, wherein the demographic profile for the respective consumer includes one or more of a profession, employment status, an age, a level of education, or an indication of a single-income family or a multi-income family.

### Claim 4 (depends on 1)

The method of claim 1, wherein the correlating comprises:
determining similarities between a selected group of the financial attributes and/or the demographic profile of the user and a corresponding group of the financial attributes and/or the demographic profile of each identified consumer.

### Claim 5 (depends on 1)

The method of claim 1, wherein the correlating comprises:
clustering the number of identified consumers into one or more groups based on their respective sets of financial attributes and demographic profiles; and
correlating the financial attributes and demographic profile of the user with respective sets of financial attributes and demographic profiles of each group of identified consumers.

### Claim 6 (depends on 1)

The method of claim 1, wherein the trained machine learning model comprises a neural network configured to determine a probability vector based on the determined likelihoods.

### Claim 7 (depends on 6)

The method of claim 6, wherein the probability vector indicates a likelihood of the user successfully repaying the credit card debt within a time period using each of the plurality of determined debt reduction plans.

### Claim 8 (depends on 6)

The method of claim 6, wherein determining the customized debt reduction plan further comprises:
ranking the plurality of determined debt reduction plans based on the probability vector using the neural network; and
determining a personalized debt reduction plan for the user based on the ranking using the neural network, the personalized debt reduction plan comprising portions of one or more of the plurality of determined debt reduction plans.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
determining feedback indicative of the user's progress in repaying the credit card debt using the customized debt reduction plan;
retraining the machine learning model based on the determined feedback; and
modifying the customized debt reduction plan using the retrained machine learning model.

### Claim 10 (depends on 1)

The method of claim 1, wherein the set of financial attributes of a respective consumer is extracted from one or more of financial transactions of an electronic payment service associated with the respective customer, financial transactions associated with the respective customer's credit cards, or credit score information of the respective customer.

### Claim 11

A system for reducing credit card debt of a user, the system comprising:
one or more processors;
a machine learning model communicatively coupled with the one or more processors; and
a memory communicatively coupled with the one or more processors and the machine learning model, the memory storing instructions that, when executed by the one or more processors in conjunction with the machine learning model, cause the system to:
determine a set of financial attributes and a demographic profile of each of a plurality of consumers, each set of financial attributes indicative of credit card debt associated with a respective consumer of the plurality of consumers;
identify a number of the consumers who successfully repaid credit card debt based at least in part on their respective sets of financial attributes;
determine a plurality of debt reduction plans used by the identified consumers to repay their respective credit card debts;
correlate one or more financial attributes and a demographic profile of the user with the sets of financial attributes and the demographic profiles, respectively, of the identified consumers;
train the machine learning model, using the correlations of financial attributes and demographic profiles between the user and the identified consumers, to determine a likelihood of the user repaying the credit card debt using each of the determined debt reduction plans; and
determine a customized debt reduction plan for the user based on the determined likelihoods.

### Claim 12 (depends on 11)

The system of claim 11, wherein each set of financial attributes includes one or more of an amount of previous credit card debt of a respective consumer, an amount of current credit card debt of the respective consumer, an annual percentage rate (APR) associated with the credit card debt of the respective consumer, payment due dates associated with the credit card debt of the respective consumer, net savings of the respective consumer, net cash flow of the respective consumer, or an intent of the respective consumer to pay-off the credit card debt.

### Claim 13 (depends on 12)

The system of claim 12, wherein the demographic profile for the respective consumer includes one or more of a profession, employment status, an age, a level of education, or an indication of a single-income family or a multi-income family.

### Claim 14 (depends on 11)

The system of claim 11, wherein execution of the instructions for determining the customized debt reduction plan further causes the system to:
determine similarities between a selected group of the financial attributes and/or the demographic profile of the user and a corresponding group of the financial attributes and/or the demographic profile of each identified consumer.

### Claim 15 (depends on 11)

The system of claim 11, wherein execution of the instructions for determining the customized debt reduction plan further causes the system to:
cluster the number of identified consumers into one or more groups based on their respective sets of financial attributes and demographic profiles; and
correlate the financial attributes and demographic profile of the user with respective sets of financial attributes and demographic profiles of each group of identified consumers.

### Claim 16 (depends on 11)

The system of claim 11, wherein the trained machine learning model comprises a neural network configured to determine a probability vector based on the determined likelihoods.

### Claim 17 (depends on 16)

The system of claim 16, wherein the probability vector indicates a likelihood of the user successfully repaying the credit card debt within a time period using each of the plurality of determined debt reduction plans.

### Claim 18 (depends on 16)

The system of claim 16, wherein execution of the instructions for determining the customized debt reduction plan further causes the system to:
rank the plurality of determined debt reduction plans based on the probability vector using the neural network; and
determine a personalized debt reduction plan for the user based on the ranking using the neural network, the personalized debt reduction plan comprising portions of one or more of the plurality of determined debt reduction plans.

### Claim 19 (depends on 11)

The system of claim 11, wherein execution of the instructions further causes the system to:
determine feedback indicative of the user's progress in repaying the credit card debt using the customized debt reduction plan;
retrain the machine learning model based on the determined feedback; and
modify the customized debt reduction plan using the retrained machine learning model.

### Claim 20 (depends on 11)

The system of claim 11, wherein the set of financial attributes of a respective consumer is extracted from one or more of financial transactions of an electronic payment service associated with the respective customer, financial transactions associated with the respective customer's credit cards, or credit score information of the respective customer.
