# US 2021/0241367 A1 · Debt management capability assessment system and method of analyzing debt management capability information using the same

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

- Number: US 2021/0241367 A1
- Document ID: US20210241367A1
- Status: Published application
- Kind: A1
- Application number: 17/132,705
- Filed: 2020-12-23
- Published: 2021-08-05
- Earliest claimed: 2020-01-30
- Assignees: Ajou University Industry-Academic Cooperation Foundation
- Applicants: Ajou University Industry-Academic Cooperation Foundation
- Inventors: Do Yeong KIM
- Web page: https://patentgrep.com/patent/US20210241367A1

## CPC

- G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03)
- 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)}
- G06F 18/23: Clustering techniques
- 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

A method of analyzing debt management capability information by a computing device working with a plurality of user equipments (UEs) and operating under the control of at least one processor includes receiving debt repayment information for each round from the plurality of UEs according to a debt assessment scenario set up with a plurality of rounds. The method further includes determining a number of groups into which users of the plurality of UEs are to be grouped, based on the debt repayment information, grouping the users into as many groups as the number of groups created based on the debt repayment information, and deriving characteristics of each of the groups according to debt management capability characteristics of the users.

## Claims

### Claim 1

A method of analyzing debt management capability information by a computing device working with a plurality of user equipments (UEs) and operating under the control of at least one processor, the method comprising:
receiving debt repayment information for each round from the plurality of UEs according to a debt assessment scenario set up with a plurality of rounds;
determining a number of groups into which users of the plurality of UEs are to be grouped, based on the debt repayment information;
grouping the users into as many groups as the number of groups created based on the debt repayment information; and
deriving characteristics of each of the groups according to debt management capability characteristics of the users.

### Claim 2 (depends on 1)

The method of claim 1, wherein the deriving of the characteristics of each group comprises
sorting out first debt repayment information of users forming a target group, which is one of the groups, and second debt repayment information of users forming a comparative group, which corresponds to the other groups than the target group,
performing a test algorithm for each of a plurality of variables included in each of the first debt repayment information and second debt repayment information, and
extracting a statistical value of a particular one of the plurality of variables.

### Claim 3 (depends on 2)

The method of claim 2, wherein the extracting of the statistical value comprises
determining a difference in distribution based on a histogram, and
deriving characteristics of each group based on the extracted statistical value of the particular variable.

### Claim 4 (depends on 3)

The method of claim 3, wherein the test algorithm comprises the Kolmogorov-Smirnov test algorithm.

### Claim 5 (depends on 4)

The method of claim 4, wherein each debt repayment information comprises user identification information, debt identification information, debt information for each round, interest rate information for each debt, final balance information for each debt, final balance information for each debt at the end of a round, a final interest rate, and variables which are debt capacity assessment scores, and
wherein the determining of the number of groups comprises
extracting object information to be analyzed from the debt repayment information, and
determining the number of groups by clustering the extracted object information to be analyzed.

### Claim 6 (depends on 5)

The method of claim 5, wherein the determining of the number of groups comprises
determining the number of groups using the elbow method algorithm which looks for the number of clusters.

### Claim 7 (depends on 1)

The method of claim 1, wherein the grouping comprises
grouping the users into at least one group using a plurality of grouping algorithms, and
analyzing grouping performance, and based on the analyzed performance, selecting one of the plurality of grouping algorithms as an algorithm for grouping,
wherein the plurality of grouping algorithms include a hierarchical cluster analysis algorithm, a K-means cluster analysis algorithm, or a dbscan algorithm, and the grouping performance is analyzed based on silhouette scores.

### Claim 8

A debt management capability assessment system comprising:
a communication interface receiving debt repayment information for each round from user equipments (UEs) participating in a debt assessment scenario; and
at least one processor,
wherein the at least one processor is configured to
determine a number of groups into which users of the UEs are to be grouped, based on the debt repayment information, group the users into as many groups as the number of groups created based on the debt repayment information, and derive characteristics of each of the groups according to debt management capability characteristics of the users.

### Claim 9 (depends on 8)

The debt management capability assessment system of claim 8, wherein the at least one processor is further configured to:
sort out first debt repayment information of users forming a target group, which is one of the groups, and second debt repayment information of users forming a comparative group, which corresponds to the other groups than the target group, and perform a test algorithm for each of a plurality of variables included in each of the first debt repayment information and second debt repayment information.

### Claim 10 (depends on 9)

The debt management capability assessment system of claim 9, wherein the at least one processor is further configured to:
extract statistics of particular ones of the plurality of variables and derive characteristics of each group based on the extracted statistics of the particular variables.

### Claim 11 (depends on 10)

The debt management capability assessment system of claim 10, wherein the at least one processor is further configured to
extract object information to be analyzed from the debt repayment information, and determine the number of groups by clustering the extracted object information to be analyzed.

### Claim 12 (depends on 11)

The debt management capability assessment system of claim 11, wherein the at least one processor is further configured to
determine the number of groups using the elbow method algorithm.