KR102533857B1 - Credit evaluation server with different models for each job type, control method of credit evaluation server with different models for each job type and computer-readable recording medium storing a program for performing credit evaluation through different models for each job type - Google Patents

Abstract

Disclosed is a credit evaluation server with different models for each occupation. The credit evaluation server with different models for each occupation comprises: an input unit receiving information of a loan applicant; a storage unit collecting and storing credit evaluation information for each occupation; and a processor generating a first credit evaluation model for each occupation based on the credit evaluation information for each occupation, generating a second credit evaluation model for each occupation by verifying the performance of the generated first credit evaluation model for each occupation, calculating a score card and building a credit rating system based on the generated second credit evaluation model for each occupation, detecting the occupation from the information of the loan applicant, and evaluating credit rating based on the second credit evaluation model corresponding to the detected occupation. Accordingly, an optimal credit evaluation model with high accuracy for each occupation can be generated, and accurate and objective loan amount limits or interest rates can be calculated by using the optimal credit evaluation model even in a non-face-to-face credit evaluation, so accurate credit evaluation and loan screening are possible.

Description

A computer-readable recording medium storing a credit evaluation server having different models for each occupational category, a control method for the credit evaluation server having different models for each occupational category, and a program for performing credit evaluation through different models for each occupational category {CREDIT EVALUATION SERVER WITH DIFFERENT MODELS FOR EACH JOB TYPE, CONTROL METHOD OF CREDIT EVALUATION SERVER WITH DIFFERENT MODELS FOR EACH JOB TYPE AND COMPUTER-READABLE RECORDING MEDIUM STORING A PROGRAM FOR PERFORMING CREDIT EVALUATION THROUGH DIFFERENT MODELS FOR EACH JOB TYPE}

The present invention relates to a credit rating server having different models for each occupational category, a control method for the credit rating server having different models for each occupational category, and a computer readable recording medium storing a program for performing credit evaluation through a different model for each occupational category, More specifically, a credit rating server having different models for each occupational category based on credit rating information for each occupational category, a control method for the credit evaluation server having different models for each occupational category, and a computer reading program storing a program for performing credit evaluation through different models for each occupational category. This is about possible recording media.

With the establishment of a credit society, the importance of credit rating is being emphasized more in the process of credit screening to determine whether to open or maintain a transaction. In particular, financial institutions dealing with financial products targeting individuals or companies are highly likely to suffer enormous damage when loans are given to any individual or company with poor credit status. By evaluating the credit rating of individuals or companies before handling products, it is possible to block handling of financial products for individuals or companies with bad credit, thereby minimizing unexpected risks.

In order to evaluate conventional credit quality, the FICO (Fair Isaac & Company) method is mainly used, and in the FICO method, an expert (model developer) independently bins individual variables for credit rating evaluation based on individual or corporate credit information So, a credit rating model is created using a logistic regression model.

Recently, various methods of non-face-to-face credit evaluation for non-face-to-face loan review have been developed, and non-face-to-face credit evaluation is being performed based on various personal information in addition to financial information.

In the case of non-face-to-face credit evaluation, the entire process, such as loan review, loan execution, loan amount limit and interest rate setting, is reviewed and conducted non-face-to-face, so the accuracy of the credit rating model is very important. The need to elevate has increased.

An object of the present invention is a credit evaluation server having different models for each job category based on credit rating determination information for each job category, a method for controlling the credit evaluation server having different models for each job category, and a computer storing a program for performing credit evaluation through different models for each job category. It is to provide a readable recording medium.

To achieve this object, the credit evaluation server having different models for each job type according to an embodiment of the present invention includes an input unit for receiving loan applicant information, a storage unit for collecting and storing credit rating determination information for each job category, and credit rating determination for each job category. Based on the information, a first credit rating model for each occupational category is generated, performance of the generated first credit evaluation model for each occupational category is verified to generate a second credit evaluation model for each occupational category, and the generated second credit evaluation model for each occupational category is verified. A processor that calculates a scorecard based on the model, constructs a credit rating system, detects an occupational category from information on the loan applicant, and evaluates credit rating based on a second credit rating model corresponding to the detected occupational category. .

Here, the credit rating determination information for each job category may include information on the number of loans, information on overdue experience, and financial soundness indicators for each job category.

In addition, the processor may build the credit rating system based on the calculated scorecard and information on the delinquency rate for each occupational category.

In addition, the processor may calculate a credit rating corresponding to the evaluated credit rating, and calculate a loan amount limit and an interest rate corresponding to the calculated credit rating.

In addition, the credit rating determination information for each occupational category is different from each other according to the occupational category, and the second credit rating models generated based on the credit rating determination information for each occupational category are different from each other according to the occupational category, and the scorecard calculated according to the second credit rating model and credit rating systems are also different depending on the job category.

In addition, the information on the number of loans includes information on the current status of credit loan amount and the number of lending institutions, the information on the overdue experience includes information on the current status of the number of overdue cases, and the financial soundness indicator by occupation type is related to sales and advertising expenses by occupation type. Including information, the credit loan amount status information, the number of lending institutions status information, the number of overdue cases status information, and the information on sales and advertising expenses for each job type are different depending on the job type.

And, the processor may periodically collect and update the credit rating determination information for each job category, and update the first credit rating model and the second credit evaluation model for each job category based on the updated credit rating determination information for each job category.

On the other hand, a control method of a credit rating server having different models for each job type according to an embodiment of the present invention includes collecting and storing credit rating determination information for each job category, receiving information of a loan applicant, generating a first credit rating model for each occupational category based on the generated first credit rating model for each occupational category, generating a second credit evaluation model for each occupational category by verifying the performance of the generated first credit rating model for each occupational category, and generating the second credit evaluation model for each occupational category. Calculating a scorecard based on the model and constructing a credit rating system, detecting an occupational category from information on the loan applicant, and evaluating credit rating based on a second credit rating model corresponding to the detected occupational category. do.

On the other hand, in a computer-readable recording medium storing a program for performing a credit evaluation through a different model for each job category according to an embodiment of the present invention, the program includes the steps of collecting and storing credit rating determination information for each job category, loan applicant Receiving information of the above, generating a first credit rating model for each occupational category based on the credit rating determination information for each occupational category, verifying the performance of the generated first credit rating model for each occupational category to obtain a second credit rating model for each occupational category. Generating a score card based on the second credit rating model for each job type and constructing a credit rating system based on the generated second credit rating model for each job type; and evaluating credit quality based on a credit evaluation model.

According to various embodiments of the present invention as described above, it is possible to generate an optimal credit rating model with high accuracy for each occupational category, and to calculate an accurate and objective loan amount limit or interest rate even in non-face-to-face credit rating by using this, Credit evaluation and loan screening will be possible.

1 is a configuration diagram of a credit evaluation server having different models for each type of job according to an embodiment of the present invention.
2 is a diagram for explaining a process of credit evaluation and loan review performed differently for each job category according to an embodiment of the present invention.
3 is a diagram illustrating information about the current status of credit loan amount by occupation according to an embodiment of the present invention.
4 is a diagram illustrating information about the current status of the number of lending institutions by job type according to an embodiment of the present invention.
5 is a diagram illustrating information about the current status of the number of overdue cases by job type according to an embodiment of the present invention.
6 is a diagram showing information about the score grade status for each job category according to an embodiment of the present invention.
7 is a diagram illustrating information about the status of credit ratings for each job category according to an embodiment of the present invention.
8 is a flowchart illustrating a control method of a credit evaluation server having different models for each job category according to an embodiment of the present invention.
9 is a diagram showing a detailed configuration of a credit evaluation server having different models for each type of job shown in FIG. 1 according to an embodiment of the present invention.
10 is a diagram showing the configuration of software modules stored in a storage unit according to an embodiment of the present invention.

First, terms used in the present specification and claims are general terms in consideration of functions in various embodiments of the present invention. However, these terms may vary depending on the intention of a technician working in the field, legal or technical interpretation, and the emergence of new technologies. Also, some terms may be terms arbitrarily selected by the applicant. These terms may be interpreted as the meanings defined in this specification, and if there is no specific term definition, they may be interpreted based on the overall content of this specification and common technical knowledge in the art.

In addition, the same reference numerals or numerals in each drawing attached to this specification indicate parts or components that perform substantially the same function. For convenience of explanation and understanding, the same reference numerals or symbols will be used in different embodiments. That is, even if all components having the same reference numerals are shown in a plurality of drawings, the plurality of drawings do not mean one embodiment.

Also, in the present specification and claims, terms including ordinal numbers such as 'first' and 'second' may be used to distinguish between elements. These ordinal numbers are used to distinguish the same or similar components from each other, and the meaning of the term should not be limitedly interpreted due to the use of these ordinal numbers. For example, elements combined with such ordinal numbers should not be construed as limiting the use order or arrangement order by the number. If necessary, each ordinal number may be used interchangeably.

In this specification, singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as 'comprise' or 'comprise' are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other It should be understood that the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Also, in an embodiment of the present invention, when a part is said to be connected to another part, this includes not only a direct connection but also an indirect connection through another medium. In addition, the meaning that a certain part includes a certain component means that it may further include other components rather than excluding other components unless otherwise specified.

Hereinafter, the present invention will be described in more detail with reference to the accompanying drawings.

1 is a configuration diagram of a credit evaluation server having different models for each type of job according to an embodiment of the present invention.

Referring to FIG. 1 , the credit evaluation server 100 having different models for each type of job includes an input unit 110 , a storage unit 120 and a processor 130 . Here, the server 100 refers to a computer program or device as a computer system that provides information or services to clients through a network. In particular, software that operates on a server is referred to as server software, and a credit evaluation algorithm according to an embodiment of the present invention can be regarded as an example of server software.

In addition, the input unit 110 may receive information of a loan applicant, and for example, the input unit 110 may use various communication methods through a wireless or wired network, such as the Internet, Bluetooth, beacon, ZigBee, satellite communication, and the like. Through the method, information of the loan applicant may be input.

Here, the loan applicant's information may include the loan applicant's identity information, financial information, credit information, social activity information, employment information, platform subscription information, etc., and may be largely divided into financial information, non-financial information, and public information. .

Also, the storage unit 120 may collect and store credit rating determination information for each job category. Here, the credit rating determination information for each job category may include information on the number of loans, information on overdue experience, and financial soundness indicators for each job type. It is assumed that they are different from each other.

Such credit rating judgment information for each job category is different depending on the job category, information on the number of loans may include information on the current status of credit loan amount and information on the number of loan institutions, information on overdue experience includes information on the number of overdue cases, and Financial soundness indicators may include information on sales and advertising expenses by job category.

In addition, information on current status of credit loan amount, current status information on the number of loan institutions, status information on the number of overdue cases, and information on sales and advertising expenses for each job type all have different characteristics depending on the type of job.

On the other hand, the processor 130 may generate a first credit evaluation model for each occupational category based on the credit rating determination information for each occupational category, and verify the performance of the generated first credit evaluation model for each occupational category to generate a second credit evaluation model for each occupational category. there is.

Specifically, the processor 130 generates a first credit rating model for each job category using training data based on the credit rating information for each job category, and measures the performance of the first credit evaluation model using the test data based on the credit rating information for each job category. Based on the verified and verified performance, a final second credit evaluation model for each job category may be generated.

In addition, the processor 130 calculates a scorecard based on the generated second credit evaluation model for each occupational category, constructs a credit rating system, detects an occupational category from information on a loan applicant, and second credit corresponding to the detected occupational category. Credit quality can be evaluated based on an evaluation model.

Specifically, the processor 130 may build a credit rating system based on the scorecard calculated based on the second credit evaluation model for each job category and information on the delinquency rate for each job category.

The credit rating system constructed in this way has characteristics of a credit rating system specialized for each occupational category, and accordingly, the processor 130 detects an occupational category from information on the loan applicant and calculates a credit rating through the credit rating system corresponding to the detected occupational category. will do

That is, the processor 130 detects the type of job in the information of the loan applicant, evaluates the credit rating based on the second credit evaluation model corresponding to the detected type of job, and evaluates the credit rating through the credit rating system corresponding to the detected type of job. A corresponding credit rating is calculated.

Then, the processor 130 calculates the limit and interest rate of the loan amount corresponding to the calculated credit rating.

Meanwhile, as described above, the credit rating judgment information for each job type is different from each other according to the job type, and the second credit rating model generated based on the credit rating judgment information for each job type is also different for each job type. The scorecard and credit rating system calculated according to the model also have different characteristics depending on the occupation.

For example, depending on whether the occupation is a manufacturing industry or a marketing industry, credit rating judgment information for each occupational category, that is, information on the number of loans, information on overdue experience, and financial soundness indicators for each occupational category may be different from each other, and the second credit evaluation model may be different from each other. It may vary depending on whether it is a manufacturing or marketing business, and the scorecard and credit rating system calculated depending on whether it is a manufacturing business or a marketing business may also differ from each other.

Meanwhile, the processor 130 may periodically collect and update credit rating determination information for each job category, and may update the first credit rating model and the second credit rating model for each job category based on the updated credit rating determination information for each job category.

For example, information on delinquency experience, that is, an increase in the number of overdue cases may be changed among the credit rating determination information for each type of job related to the first occupation, and the processor 130 determines the increase rate of the number of overdue cases related to the first occupation based on this. The first credit rating model and the second credit rating model may be modified, and the scorecard and credit rating system for the first occupation may be modified.

2 is a diagram for explaining a process of credit evaluation and loan review performed differently for each job category according to an embodiment of the present invention.

Referring to FIG. 2 , credit rating determination information 210 for each job category is collected and stored, and here, the credit rating determination information 210 for each job category may include information on the number of loans, overdue experience, and financial soundness indicators for each job category.

In addition, the credit rating determination information 210 for each occupational category is classified by occupational category and used to generate credit evaluation models (220-1, 220-2...220-N-1, 220-N) specialized for each occupational category.

Specifically, the credit rating judgment information for job 1 is used to generate a job 1-specific credit evaluation model (220-1), and first, the first credit for job 1 is obtained by using training data based on the credit rating information for job 1. An evaluation model is generated, performance verification is performed on the generated first credit rating model using test data based on occupational category 1, and then a second credit evaluation model related to occupational category 1 is generated.

Thereafter, a scorecard for occupation 1 is calculated through the generated second credit rating model for occupation 1, and credit for occupation 1 is based on the calculated scorecard for occupation 1 and information on the delinquency rate for occupation 1. Build a rating system.

Through the above process, the occupational type 1 specialized credit rating 230 is calculated, and the processor 130 detects the occupational category from information of the loan applicant when there is a loan application, and if the detected occupational category is occupational category 1, the processor 130 detects the occupational category 1 The credit rating is evaluated through the second credit rating model, and the credit rating is calculated through the credit rating 230 for the first occupation.

Then, the processor 130 proceeds with the loan review 240 corresponding to the calculated credit rating, and specifically calculates and provides loan approval, loan rejection, and the limit and interest rate of the loan amount corresponding to the calculated credit rating. do.

The above process is the same for the credit rating model (220-1) for job category 2, the credit evaluation model (220-N-1) for job category N-1, and the credit evaluation model (220-N) for job category N. can be applied

Meanwhile, FIGS. 3 to 5 are examples of credit rating determination information for each job category.

3 is a diagram illustrating information about the current status of credit loan amount by occupation according to an embodiment of the present invention.

Referring to FIG. 3, information on the current status of credit loan amount by job category is classified according to job category 1 (310), job category 2 (320), job category 3 (330), and job category N (340), and credit loan amount intervals for each job category. It includes information on the number of people subject to each category, the number of people who are currently in overdue, and the delinquency rate (%).

As shown in FIG. 3, it can be seen that the number of people subject to credit loan amount for each occupation, the number of people currently in overdue, and the delinquency rate (%) are different from each other. In addition, the information on the current status of credit loan amounts for each different occupational category can be utilized so that a credit evaluation model, scorecard, and credit rating system for each occupational category can be generated differently.

4 is a diagram illustrating information about the current status of the number of lending institutions by job type according to an embodiment of the present invention.

Referring to FIG. 4, information on the current status of the number of loan institutions by job type is classified according to job type 1 (410), job type 2 (420), job type 3 (430), and job type N (440). It includes information on the number of people, currently overdue people, and delinquency rate (%).

As shown in FIG. 4 , it can be seen that the target number of people, currently overdue people, and delinquency rate (%) are different from each other according to the number of lending institutions for each job type. In addition, information on the current status of the number of lending institutions for each different occupational category can be utilized so that different credit evaluation models, scorecards, and credit rating systems can be created for each occupational category.

5 is a diagram illustrating information about the current status of the number of overdue cases by job type according to an embodiment of the present invention.

Referring to FIG. 5, information on the status of the number of overdue cases by occupational category is classified according to occupational category 1 (510), occupational category 2 (520), occupational category 3 (530), and occupational category N (540), and for each occupational category, the number of past arrears, target It contains information about the number of people, the number of people currently in overdue, and the delinquency rate (%).

As shown in FIG. 5 , it can be seen that the target number of people according to the number of past delinquent cases, the current number of people in overdue, and the delinquency rate (%) are different for each job type. In addition, the information on the current state of the number of delinquent cases for each different occupational category can be utilized so that a credit evaluation model, scorecard, and credit rating system for each occupational category can be generated differently.

6 is a diagram showing information about the score grade status for each job category according to an embodiment of the present invention.

Referring to FIG. 6, information on the current score grade by job type is classified according to job category 1 (610), job category 2 (620), job category 3 (630), and job category N (640), and non-face-to-face linked loan scores for each job category. It includes information on grade, target number of people, currently overdue number of people, and delinquency rate (5).

As shown in Figure 6, the number of people subject to non-face-to-face linked loan score grades, the number of people currently in arrears, and the delinquency rate (%) are different for each job category, which is information on the current status of credit loans by job category, the current status of the number of lenders by job category This is because the score grades for each job type calculated based on the second credit evaluation model for each job category generated based on the information about and the information on the current status of the number of delinquent cases for each job category are different for each job category as shown in FIG. 6 .

7 is a diagram illustrating information about the status of credit ratings for each job category according to an embodiment of the present invention.

Referring to FIG. 7, information on the status of credit ratings by job type is classified according to occupational category 1 (710), occupational category 2 (720), occupational category 3 (730), and occupational category N (740). , the number of people currently in overdue, and the delinquency rate (%).

As shown in FIG. 7, the number of people subject to the credit rating, the number of people currently in arrears, and the delinquency rate (%) are different for each occupational category, which is information on the current status of credit loan amount by occupational category, information on the current status of the number of lending institutions by occupational category, As shown in FIG. because it does

Meanwhile, as another embodiment of the present invention, it may be assumed that a plurality of occupational types are detected as a result of detecting occupational types from information on a loan applicant.

When two types of jobs are detected among the loan applicant's information, the processor 130 may evaluate the credit rating through each of the second credit evaluation models corresponding to the detected jobs.

For example, if the detected occupations among the information of the loan applicant are occupation 1 and occupation 2, the processor 130 may evaluate the credit rating associated with occupation 1 through a second credit evaluation model corresponding to the detected occupation 1, A credit rating related to occupation 1 can be calculated through the credit rating system built through the second credit rating model corresponding to occupation 1.

In addition, the processor 130 may evaluate the credit rating related to job 2 through the second credit rating model corresponding to the detected job 2, and through the credit rating system built through the second credit evaluation model corresponding to job 2. A credit rating related to job 2 can be calculated.

Then, the processor 130 may calculate the final credit rating of the loan applicant having the occupation 1 and the occupation 2 by adding weights to the calculated credit ratings related to the occupation 1 and the credit ratings related to the occupation 2, respectively. there is.

Specifically, the processor 130 may determine sales, advertising expenses, etc. for each of job 1 and job 2 by referring to the financial soundness indicator for each job category among the credit rating determination information for each job category, and based on this, the amount of income for job 1 and job 2 It is possible to calculate the amount of income for

Further, the processor 130 may set the first weight and the second weight in proportion to the ratio of the income amount related to occupational category 1 and the income amount related to occupational category 2, and assign a first weight to the credit rating related to occupational category 1 calculated as described above. A final credit rating may be calculated by calculating a weight and calculating a second weight for the credit rating related to the second occupation.

For example, it is assumed that the job of the loan applicant is detected as job 1 and job 2, the credit rating related to job 1 is 4 grades, and the credit rating related to job 2 is calculated as 1 grade.

At this time, the processor 130 may calculate the income for occupation 1 as 50 million won and the income for occupation 2 as 100 million won by referring to the financial soundness indicator for each occupation. In this case, the first weight and the second weight are 1:2. can be set as a percentage of That is, the processor 130 may set the first weight to 1/3 and the second weight to 2/3.

Accordingly, the processor 130 calculates the first weight, 1/3, to the credit rating, grade 4, related to occupational category 1, and calculates the second weight, 2/3, to the credit rating, grade 1, related to occupational category 2, 1.33 and 0.66 are calculated, respectively, and when they are summed, 1.99 is finally calculated, and the final credit rating can be calculated as the second grade.

As described above, even when a plurality of occupational types are detected, the credit rating and credit rating can be evaluated through the credit rating model for each occupational category and calculated by applying a weight to each evaluated credit rating. Two examples were given, but the same can be applied even if there are more.

8 is a flowchart illustrating a control method of a credit evaluation server having different models for each job category according to an embodiment of the present invention.

Referring to FIG. 8 , the control method of a credit evaluation server having different models for each job category according to an embodiment of the present invention includes collecting and storing credit rating determination information for each job category (S810), receiving loan applicant information ( S820), generating a first credit rating model for each occupational category based on the credit rating determination information for each occupational category (S830), generating a second credit evaluation model for each occupational category by verifying the performance of the generated first credit rating model for each occupational category. (S840), calculating a scorecard based on the generated second credit evaluation model for each occupational category and constructing a credit rating system (S850), and detecting an occupational category from information on a loan applicant and a second credit corresponding to the detected occupational category. and evaluating credit quality based on the evaluation model (S860).

In addition, as described above, all of the processes performed by the processor 130 may be equally performed by a control method of a credit evaluation server having a different model for each type of job.

9 is a diagram showing a detailed configuration of a credit evaluation server having different models for each type of job shown in FIG. 1 according to an embodiment of the present invention.

The credit evaluation server 100 having different models for each type of job includes an input unit 110 , a storage unit 120 and a processor 130 .

The processor 130 controls the overall operation of the credit evaluation server 100 having different models for each type of job.

Specifically, the processor 130 includes a RAM 131, a ROM 132, a main CPU 133, a graphic processing unit 134, first to n interfaces 135-1 to 135-n, and a bus 136. include

The RAM 131 , the ROM 132 , the main CPU 133 , the graphics processing unit 134 , the first to n interfaces 135 - 1 to 135 - n may be connected to each other through a bus 136 .

The first to n interfaces 135-1 to 135-n are connected to the various components described above. One of the interfaces may be a network interface connected to an external device through a network.

The main CPU 133 accesses the storage unit 130 and performs booting using the O/S stored in the storage unit 120 . In addition, various operations are performed using various programs, contents, data, and the like stored in the storage unit 120 .

In particular, the main CPU 133 generates a first credit rating model for each occupational category based on the credit rating determination information for each occupational category, verifies the performance of the generated first credit evaluation model for each occupational category, and generates a second credit evaluation model for each occupational category. , Calculate a scorecard based on the generated second credit rating model for each occupational category, construct a credit rating system, detect the occupational category from information on the loan applicant, and credit rating based on the second credit evaluation model corresponding to the detected occupational category. can be evaluated.

The ROM 132 stores command sets for system booting and the like. When a turn-on command is input and power is supplied, the main CPU 133 copies the O/S stored in the storage 120 to the RAM 131 according to the command stored in the ROM 132 and executes the O/S. boot up the system When booting is completed, the main CPU 133 copies various application programs stored in the storage unit 120 to the RAM 131 and executes the copied application programs in the RAM 131 to perform various operations.

The graphic processing unit 134 uses a calculation unit (not shown) and a rendering unit (not shown) to create a screen including various objects such as icons, images, and text. The calculation unit (not shown) calculates attribute values such as coordinate values, shape, size, color, and the like of each object to be displayed according to the layout of the screen based on the received control command. The rendering unit (not shown) creates screens of various layouts including objects based on the attribute values calculated by the calculation unit (not shown).

In particular, the graphic processing unit 134 may implement an object created by the main CPU 133 as a GUI (Graphic User Interface), an icon, a user interface screen, or the like.

Meanwhile, the above-described operation of the processor 130 may be performed by a program stored in the storage unit 120 .

The storage unit 120 stores various data such as an O/S (Operating System) software module and various multimedia contents for driving the credit evaluation server 100 having different models for each type of job.

In particular, the storage unit 120 generates a first credit evaluation model for each occupational category based on the credit rating determination information for each occupational category, verifies the performance of the generated first credit evaluation model for each occupational category, and generates a second credit evaluation model for each occupational category. , Calculate a scorecard based on the generated second credit rating model for each occupational category, construct a credit rating system, detect the occupational category from information on the loan applicant, and credit rating based on the second credit evaluation model corresponding to the detected occupational category. It may include a software module for evaluating.

10 is a diagram showing the configuration of software modules stored in a storage unit according to an embodiment of the present invention.

Referring to FIG. 10 , the storage unit 120 includes a first credit rating model creation module 121, a second credit rating model creation module 122, a scorecard calculation module 123, and a credit rating system construction module 124. , Programs such as a credit rating calculation module 125 and a loan amount limit and interest rate calculation module 126 may be stored.

Meanwhile, the above-described operation of the processor 130 may be performed by a program stored in the storage unit 120 . Hereinafter, detailed operations of the processor 130 using programs stored in the storage unit 120 will be described in detail.

Specifically, the first credit evaluation model generation module 121 may generate a first credit evaluation model for each job category based on the credit rating determination information for each job category.

In addition, the second credit evaluation model generation module 122 may generate a second credit evaluation model for each job category by verifying the performance of the generated first credit evaluation model for each job category.

In addition, the scorecard calculation module 123 may calculate a scorecard for each occupational category based on the generated second credit evaluation model for each occupational category.

In addition, the credit rating system construction module 124 may build a credit rating system for each job category based on the calculated scorecard and information on the delinquency rate for each job category.

In addition, the credit rating calculation module 125 may calculate a credit rating from a credit rating system for each occupation according to the credit rating evaluated through the second credit rating model.

In addition, the loan amount limit and interest rate calculation module 126 may calculate the loan amount limit and interest rate corresponding to the calculated credit rating for each occupation.

Meanwhile, a non-transitory computer readable medium storing a program for sequentially performing the control method according to the present invention may be provided.

A non-transitory readable medium is not a medium that stores data for a short moment, such as a register, cache, or memory, but a medium that stores data semi-permanently and can be read by a device. Specifically, the various applications or programs described above may be stored and provided in non-transitory readable media such as CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, and the like.

In addition, although a bus is not shown in the above-described block diagram showing the credit rating server having different models for each job type on the drawing, communication between components in the credit rating server having different models for each job type is performed through a bus. may be done In addition, each device may further include a processor such as a CPU or a microprocessor that performs the various steps described above.

In addition, although the preferred embodiments of the present invention have been shown and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the present invention belongs without departing from the gist of the present invention claimed in the claims. Of course, various modifications are possible by those skilled in the art, and these modifications should not be individually understood from the technical spirit or perspective of the present invention.

100: Credit evaluation server with different models for each occupation
110: input unit 120: storage unit
130: processor

Claims (9)

In the credit evaluation server having different models for each occupational category,
an input unit for receiving loan applicant information;
a storage unit that collects and stores credit rating determination information for each occupational category; and
A first credit rating model for each occupational category is generated based on the credit rating determination information for each occupational category, and a second credit evaluation model for each occupational category is generated by verifying the performance of the generated first credit evaluation model for each occupational category. Calculating a scorecard based on a second credit rating model, constructing a credit rating system, detecting an occupational category from among the information of the loan applicant, and evaluating credit rating based on a second credit rating model corresponding to the detected occupational category Including a processor;
the processor,
If the occupations detected from the information of the loan applicant are plural including the first occupation and the second occupation,
Based on the second credit rating model corresponding to each of the first and second occupations, a credit rating for each of the first and second occupations is calculated, and the financial soundness index for each occupation is referred to for the first occupation. Calculate the amount of income and the amount of income for the second occupation,
Setting a first weight for the first occupation and a second weight for the second occupation in proportion to the ratio of the income for the first occupation and the income for the second occupation;
The first weight is calculated for the calculated credit rating of the first occupation, the second weight is calculated for the calculated credit rating for the second occupation, and the first weight is calculated for the credit rating for the first occupation. A credit rating server having a different model for each type of job, which is to calculate a final credit rating by adding the result of calculating the second weight to the credit rating of the second type of job and one result. According to claim 1,
The credit rating judgment information for each occupational category is:
A credit evaluation server having different models for each job type, including information on the number of loans, information on overdue experience, and the financial soundness index for each job type. According to claim 2,
the processor,
A credit rating server having different models for each occupational category, wherein the credit rating system is constructed based on the calculated scorecard and information on the delinquency rate for each occupational category. According to claim 3,
the processor,
A credit rating server having different models for each type of job, which calculates a credit rating corresponding to the evaluated credit rating and calculates a limit and interest rate of the loan amount corresponding to the calculated credit rating. According to claim 4,
The credit rating determination information for each occupational category is different from each other according to the occupational category, and the second credit evaluation model generated based on the creditworthiness determination information for each occupational category is different from each other according to the occupational category, and the scorecard and credit calculated according to the second credit evaluation model A credit rating server having different models for each job type, in which the rating system is also different for each job type. According to claim 5,
The information on the number of loans includes information on the current status of credit loan amount and the number of lending institutions, the information on the overdue experience includes information on the current status of the number of overdue cases, and the financial soundness index by occupation type is information on sales and advertising expenses by occupation type. including,
The credit evaluation server having different models for each job category, wherein the credit loan amount status information, the number of loan institutions status information, the number of overdue status information, and the information on sales and advertising expenses for each job category are different from each other according to the job category. According to claim 6,
the processor,
Credit having different models for each occupational category, wherein the credit rating determination information for each occupational category is periodically collected and updated, and the first credit rating model and the second credit rating model are updated for each occupational category based on the updated creditworthiness determination information for each occupational category. evaluation server. In the control method of a credit evaluation server having a different model for each occupational category,
Collecting and storing credit rating determination information for each job category;
Receiving information of a loan applicant;
generating a first credit evaluation model for each occupational category based on the credit rating determination information for each occupational category;
generating a second credit evaluation model for each job category by verifying the performance of the generated first credit evaluation model for each job category;
Calculating a score card based on the generated second credit rating model for each job type and constructing a credit rating system; and
Detecting an occupational category from among the information of the loan applicant, and evaluating credit rating based on a second credit evaluation model corresponding to the detected occupational category;
Evaluating the credit rating based on the second credit evaluation model corresponding to the detected occupational category,
If the occupations detected from the information of the loan applicant are plural including the first occupation and the second occupation,
Based on the second credit rating model corresponding to each of the first and second occupations, a credit rating for each of the first and second occupations is calculated, and the financial soundness index for each occupation is referred to for the first occupation. Calculate the amount of income and the amount of income for the second occupation,
Setting a first weight for the first occupation and a second weight for the second occupation in proportion to the ratio of the income for the first occupation and the income for the second occupation;
The first weight is calculated for the calculated credit rating of the first occupation, the second weight is calculated for the calculated credit rating for the second occupation, and the first weight is calculated for the credit rating for the first occupation. A control method of a credit rating server having a different model for each type of job, which is to calculate a final credit rating by adding a result and a result of calculating the second weight to the credit rating of the second type of job. In a computer-readable recording medium in which a program for performing credit evaluation through a different model for each occupation is stored,
on the computer,
Collecting and storing credit rating determination information for each job category;
Receiving information of a loan applicant;
generating a first credit evaluation model for each occupational category based on the credit rating determination information for each occupational category;
generating a second credit evaluation model for each job category by verifying the performance of the generated first credit evaluation model for each job category;
Calculating a score card based on the generated second credit rating model for each job type and constructing a credit rating system; and
Detecting an occupational category from among the information of the loan applicant, and evaluating credit rating based on a second credit evaluation model corresponding to the detected occupational category;
Evaluating the credit rating based on the second credit evaluation model corresponding to the detected occupational category,
If the occupations detected from the information of the loan applicant are plural including the first occupation and the second occupation,
Based on the second credit rating model corresponding to each of the first and second occupations, a credit rating for each of the first and second occupations is calculated, and the financial soundness index for each occupation is referred to for the first occupation. Calculate the amount of income and the amount of income for the second occupation,
Setting a first weight for the first occupation and a second weight for the second occupation in proportion to the ratio of the income for the first occupation and the income for the second occupation;
The first weight is calculated for the calculated credit rating of the first occupation, the second weight is calculated for the calculated credit rating for the second occupation, and the first weight is calculated for the credit rating for the first occupation. A computer-readable recording medium having recorded thereon a computer program for executing the calculation of the final credit rating by adding the result obtained by calculating the second weight to the credit rating of the second occupation.

Images