KR101597939B1 - Apparatus and method for predicting industrial credit risk using macro-economic indicator - Google Patents

Apparatus and method for predicting industrial credit risk using macro-economic indicator Download PDF

Info

Publication number
KR101597939B1
KR101597939B1 KR1020150094516A KR20150094516A KR101597939B1 KR 101597939 B1 KR101597939 B1 KR 101597939B1 KR 1020150094516 A KR1020150094516 A KR 1020150094516A KR 20150094516 A KR20150094516 A KR 20150094516A KR 101597939 B1 KR101597939 B1 KR 101597939B1
Authority
KR
South Korea
Prior art keywords
industry
indicators
industrial
default rate
candidate
Prior art date
Application number
KR1020150094516A
Other languages
Korean (ko)
Inventor
김태영
김연진
안병건
홍경민
송지현
이호열
Original Assignee
한국기업데이터 주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 한국기업데이터 주식회사 filed Critical 한국기업데이터 주식회사
Priority to KR1020150094516A priority Critical patent/KR101597939B1/en
Application granted granted Critical
Publication of KR101597939B1 publication Critical patent/KR101597939B1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Technology Law (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present invention relates to an apparatus and a method for predicting a degree of industrial credit risk using a macro-economic indicator. According to an embodiment of the present invention, the method for predicting a degree of industrial credit risk using a macro-economic indicator comprises the steps of: collecting a macro-economic indicator defined for each industry and configuring a candidate indicator pool for each industry; defining a target stock and classifying the defined target stock into a plurality of segments according to industrial classification; selecting, for each segment, one or more final indicators through analysis of a correlation between the candidate indicators of the corresponding industry and fitting a regression model in which the selected one or more final indicators are used as an independent variable and an observed default rate is used as a dependent variable; and calculating, for each segment, a prediction default rate based on the corresponding regression model and calculating an industrial risk index based on the calculated prediction default rate. According to an embodiment of the present invention, since the industrial credit risk is predicted by using the macro-economic indicator based on a supply chain theory, it is possible to more accurately predict the risk and more effectively cope with the risk.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus and a method for predicting credit risk of an industry using macroeconomic indicators,

At least some embodiments of the present disclosure relate to an apparatus and method for predicting industry-specific credit risk using macroeconomic indicators.

As the awareness of risk management spreads in line with the development of the financial industry, the need for regulatory capital by the International Settlement Agency has been raised mainly in banknotes. Financial institutions have recognized the importance of risk management through various financial crises and have made many advances in their application techniques.

In the industrial technology field, competition among companies in the market has intensified, making it difficult to predict the future creditworthiness of the company. In terms of financial institutions, how effectively such credit risk can be managed and transferred is an important factor in competitiveness. In addition, there is a need for evaluation of credit risk as a method for this.

KR 10-2014-0133341 A KR 10-2009-0006489 A

One embodiment of the present disclosure is directed to providing an industry-specific credit risk prediction apparatus and method using macroeconomic indicators.

According to one embodiment of the present invention, the industry-specific credit risk prediction method utilizing macroeconomic indicators comprises: collecting macroeconomic indicators defined by each industry and constructing a pool of industrial candidate indicators; Defining a target borrower and classifying the defined target borrower into a plurality of segments according to an industry classification; Selecting one or more final indicators by analyzing correlations between candidate indices of the industry for each segment, fitting a regression model having the selected at least one final indicator as an independent variable and the observed default rate as a dependent variable; And calculating a predicted default rate based on the regression model for each segment and calculating an industrial risk index based on the calculated predicted default rate.

According to an embodiment of the present invention, an industry-specific credit risk prediction apparatus utilizing macroeconomic indicators includes a collecting unit for collecting macroeconomic indicators defined for each industry and constituting a pool of industrial candidate indices; A classifier for defining a target borrower and classifying the defined target borrower into a plurality of segments according to an industrial classification; A regression model fitting unit that selects one or more final indicators by analyzing correlation between candidate indices of the industry by segments and adapts a regression model in which the selected at least one final indicator is an independent variable and the observation default rate is a dependent variable; And an industrial risk index calculating unit for calculating a predicted default rate based on the regression model for each segment and calculating an industrial risk index based on the calculated predicted default rate.

According to one embodiment of the present invention, an industry-specific credit risk prediction apparatus and method using macroeconomic indicators can be provided.

The focus of enterprise risk is being redefined as an industry value chain (supply chain) risk consisting of inter-firm linkage networks centering on a single entity. By using macroeconomic indicators based on this supply chain theory, industry-specific credit risks can be predicted, allowing for more precise risk prediction and thus better responding to risks.

1 is a block diagram of an industry-specific credit risk prediction apparatus utilizing macroeconomic indicators according to an embodiment of the present invention.
2 is a flow chart of a method for predicting industry credit risk using macroeconomic indicators in accordance with one embodiment of the present disclosure;
Figures 3, 4, and 5 are illustrations of a segment classification method in accordance with one embodiment of the present disclosure.
6 is a diagram illustrating the results of applying an industry risk index to an early warning score in accordance with one embodiment of the present disclosure.

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

In describing the embodiments, descriptions of techniques which are well known in the technical field to which this specification belongs and which are not directly related to this specification are not described. This is for the sake of clarity without omitting the unnecessary explanation and without giving the gist of the present invention.

For the same reason, some of the components in the drawings are exaggerated, omitted, or schematically illustrated. Also, the size of each component does not entirely reflect the actual size. In the drawings, the same or corresponding components are denoted by the same reference numerals.

1 is a block diagram of an industry-specific credit risk prediction apparatus utilizing macroeconomic indicators according to an embodiment of the present invention.

1, an industry-specific credit risk prediction apparatus using macroeconomic indicators according to an embodiment of the present invention includes a collecting unit 100, a classifying unit 110, a regression model fitting unit 120, An exponent calculating unit 130, and an early warning score calculating unit 140. [

The collecting unit (100) collects industry defined macroeconomic indicators and constitutes a pool of industry-specific candidate indicators. For example, macroeconomic indicators can be defined by industry codes according to standard industrial classification systems (ie, small, middle, and major categories).

The classifier 110 defines a target borrower and classifies the target borrower defined above into a plurality of segments according to an industry classification according to one embodiment. For example, the classification unit 110 determines whether or not the industry code corresponding to the business type of the target borrower is included in the industrial code list corresponding to the classification system based on the standard industry classification (i.e., the small classification, the middle classification, , The target borrower can be classified into segments corresponding to the corresponding industry codes in the selected classification system. Or in accordance with another embodiment, the target borrower as defined above, along with the industry classification (eg, external (over $ 10 billion), non-external (over $ 1 billion, $ 10 billion), small business ), And the whole).

The regression model fitting unit 120 selects one or more final indicators by analyzing correlations among candidate indicators of the industry for each segment, calculates a regression model in which the selected at least one final indicator is used as an independent variable, and the observation default rate is used as a dependent variable . Here, among the one or more final indicators selected, the indicator that generates multi-collinearity is excluded when the regression model is adopted. The regression model fitting unit 120 derives a regression equation by estimating a regression coefficient in a regression model based on the observation default rate for a predetermined period on a segment-by-segment basis, and thereby, a predicted default rate is calculated based on the derived regression equation .

Here, the regression model adaptation unit 120 selects a time lag having the highest explanatory power (R-square) of the actual default rate for each candidate indicator of each industry for each segment, The candidate indicators having a correlation of at least a predetermined value are compared with each other, and a candidate indicator having a relatively high explanatory power corresponding to the selected time lag is selected as a final indicator. Here, the time lag less than the reference value (for example, 3) is excluded from the selection. A candidate indicator having a correlation of at least a predetermined value means that the candidate indicators are similar information, and therefore, only one candidate indicator is selected as the final indicator.

The regression model fitting unit 120 selects one or more final indicators by analyzing the correlations between the candidate indicators on the entirety of the candidate industry indicator pools constituted when the candidate indicators of the industry do not exist.

The industrial risk index calculating unit 130 calculates a predicted default rate based on the regression model for each segment, and calculates an industrial risk index based on the calculated default rate. Here, the industrial risk index is calculated based on the average and standard deviation of the calculated default rate and the observed default rate.

The early warning score calculation unit 140 may calculate an early warning score for each target borrower based on at least one of a financial statement, financial transaction information, and representative credit information for each segment, If the calculated default rate is higher than the long-term average default rate, which is the average of the observed default rates during a predetermined period of time, and if the calculated default rate is lower than the long-term average default rate , The target earner's early warning score is lowered.

2 is a flow chart of a method for predicting industry credit risk using macroeconomic indicators in accordance with one embodiment of the present disclosure;

Referring to FIG. 2, in step 201, the industry-specific credit risk prediction apparatus collects industry-specific macroeconomic indicators and constructs industrial-specific candidate indicator pools.

In step 203, the industry-specific credit risk prediction device collects credit-based credit information.

In step 205, the industry-specific credit risk prediction device defines a target borrower and classifies the defined target borrower into a plurality of segments according to an industry classification. For example, it is possible to identify whether the industry code corresponding to the target borrower industry is included in the list of industrial codes according to the classification system (ie, small classification, middle classification, and large classification) according to the standard industry classification, After selecting the lowest classification scheme that contains the code, the target borrower can be classified into segments corresponding to the corresponding industry code in the selected classification scheme. According to another embodiment, the defined target borrower may be classified into a plurality of segments according to the asset size (e.g., external, external, small business, whole) together with the industrial classification. In this case, Need to collect in advance.

In step 207, the industry-specific credit risk prediction apparatus selects one or more final indicators by analyzing correlations among candidate indicators of the industry for each segment, and calculates a regression result of the selected one or more final indicators as independent variables and the observation default rate as dependent variables Fits the model.

Here, the industry-specific credit risk prediction apparatus selects a time lag having the highest explanatory power for the actual default rate for each candidate indicator of each industry, analyzes the correlation between the candidate indicators of the industry, , And selects a candidate index having a relatively high explanatory power corresponding to the selected time lag as a final index. Here, a time lag less than a predetermined value (for example, 3) is excluded from the selection.

The industry-specific credit risk prediction device selects one or more final indicators by analyzing the correlation between the candidate indicators for all the pools of the candidate industry indicators constituted when the candidate indicators of the industry do not exist.

In step 209, the industry-specific credit risk prediction apparatus calculates a predicted default rate based on the regression model for each segment, and calculates an industrial risk index based on the calculated predicted default rate.

Here, the industrial risk index is calculated according to Equation (1) based on the average and standard deviation of the calculated default rate and the observed default rate.

Figure 112015106484395-pat00010

Here, SUR t (standardized unexpected industry risk) is a standardized standard deviation of the default and observed default rates, which means the industrial risk index at time t, EDR means forecasted default rate, and ADR means observed default rate . For example, t + 3 for the month means the base month + 3 months, and t-1 means the month of the base month.

In step 211, the industry-specific credit risk prediction apparatus applies the calculated industrial risk index to the earliest alarm score of the target borrower calculated based on at least one of financial statement, financial transaction information, and representative credit information on a segment-by-segment basis. That is, by multiplying the calculated early warning score for each target borrower calculated based on at least one of financial statement, financial transaction information and representative credit information by the calculated industrial risk index for each segment, And if the calculated default rate is lower than the long-term average default rate, the target early-warning score of the target borrower is lowered.

Figures 3, 4, and 5 are illustrations of a segment classification method in accordance with one embodiment of the present disclosure.

The target for the development is corporation company ('81' <= number of company number = '88') and forecasted default rate is calculated from June 2009 to December 2014 (67 months in total) And the macroeconomic indicators are collected from July 2008 to December 2014, and when the Basel II default definition is applied using the bankruptcy information of the Federation of Korean Banks, the classification system based on the standard industrial classification (ie, sub-classification, 3, 4 and 5, if the target borrower is classified into a plurality of segments according to an industry code and an asset scale (for example, external appearance, non-external appearance, small business, whole) Here, segments with less than 10 cases or explanatory power (R-Square) of 0.5 or less are excluded. If there is no segment of the lower category, the upper category is applied. If there is no segment with the corresponding asset size, Industry segments are applied.

3, the target borrower's business categories are classified into 12 business categories in the business major category, and the target borrowers are divided into 33 segments, i.e., 4 outward expressions, 5 outs, 11 small businesses, and 13 segments in total.

Next, referring to FIG. 4, the business type of the target borrower is divided into 26 business types in the subdivision type of business, and according to the 26 types of businesses and the asset size, the target borrower has 47 segments, 5 non-emotions, 18 small businesses, and 24 segments in total.

Finally, referring to FIG. 5, the target borrowers are classified into 27 sectors in the sub-category of business, and the target borrowers are classified into 27 segments according to the 27 types of sectors .

6 is a diagram illustrating the results of applying an industry risk index to an early warning score in accordance with one embodiment of the present disclosure.

Referring to FIG. 6, by applying the industrial risk index to the early warning score, the incidence rate increased by 2% as compared with the case where it was not applied. In the actual number of borrowers, 2,058 cases of the normal borrower, , 239 more alarms were generated, and 239 delinquent borrowers could be detected in advance.

In addition, when the first occurrence of a non-normal signal in the early warning score of a defaulting borrower is not applied to the early warning score, 7.3 months before the default, but the industrial risk index is applied to the early warning score, It can be confirmed that the alarm occurs earlier than 7.6 months before the bankruptcy occurs.

The apparatus and method for predicting the credit risk of each industry utilizing the macroeconomic indicators according to the embodiments described above can predict the credit risk of each industry by utilizing macroeconomic indicators based on the supply chain theory, It can cope more effectively.

At this point, it will be appreciated that the combinations of blocks and flowchart illustrations in the process flow diagrams may be performed by computer program instructions. These computer program instructions may be loaded into a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, so that those instructions, which are executed through a processor of a computer or other programmable data processing apparatus, Thereby creating means for performing functions. These computer program instructions may also be stored in a computer usable or computer readable memory capable of directing a computer or other programmable data processing apparatus to implement the functionality in a particular manner so that the computer usable or computer readable memory The instructions stored in the block diagram (s) are also capable of producing manufacturing items containing instruction means for performing the functions described in the flowchart block (s). Computer program instructions may also be stored on a computer or other programmable data processing equipment so that a series of operating steps may be performed on a computer or other programmable data processing equipment to create a computer- It is also possible for the instructions to perform the processing equipment to provide steps for executing the functions described in the flowchart block (s).

In addition, each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing the specified logical function (s). It should also be noted that in some alternative implementations, the functions mentioned in the blocks may occur out of order. For example, two blocks shown in succession may actually be executed substantially concurrently, or the blocks may sometimes be performed in reverse order according to the corresponding function.

Herein, the term &quot; part &quot; used in the present embodiment means a hardware component such as software or an FPGA or an ASIC, and 'part' performs certain roles. However, 'part' is not meant to be limited to software or hardware. &Quot; to &quot; may be configured to reside on an addressable storage medium and may be configured to play one or more processors. Thus, by way of example, 'parts' may refer to components such as software components, object-oriented software components, class components and task components, and processes, functions, , Subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and components may be further combined with a smaller number of components and components, or further components and components. In addition, the components and components may be implemented to play back one or more CPUs in a device or a secure multimedia card.

It will be understood by those skilled in the art that the present specification may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. The scope of the present specification is defined by the appended claims rather than the foregoing detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents are included in the scope of the present specification Should be interpreted.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, It is not intended to limit the scope of the specification. It will be apparent to those skilled in the art that other modifications based on the technical idea of the present invention are possible in addition to the embodiments disclosed herein.

100: collecting unit 110:
120: regression model fitting part 130: industrial risk index calculating part
140: early warning score calculating section

Claims (15)

Collecting department collecting industry defined macroeconomic indicators and constructing a pool of industry-specific candidate indicators;
The classifier defines a target borrower and classifies the defined target borrower into a plurality of segments according to an industry classification;
The regression model fitting section selects one or more final indicators by analyzing correlations between candidate indicators of the industry for each segment and adapts a regression model in which the selected at least one final indicator is used as an independent variable and the observation default rate is used as a dependent variable step; And
Calculating an industrial risk index based on the regression model, and calculating an industrial risk index based on the calculated expected default rate;
/ RTI &gt;
The industrial risk index is calculated based on the average and standard deviation of the calculated default rate and the default rate,
The industrial risk index SUR is calculated on the basis of the following equation:
&Lt; Equation &
Figure 112015106484395-pat00011

Here, SUR denotes the industrial risk index, EDR denotes the predicted default rate, ADR denotes the observed default rate, t denotes the base month, and t + 3 denotes the default monthly rate , T-1 means one month before the base month, and t and n are the unit of the credit risk prediction method by industry using monthly macroeconomic indicators.
The method according to claim 1,
Wherein the selecting one or more final indicators comprises:
Selecting the time lag having the highest explanatory power for the actual default rate for each candidate indicator of the industry;
Analyzing a correlation between candidate indices of the industry; And
Comparing the candidate indicators having a degree of correlation greater than or equal to a predetermined value and selecting a candidate indicator having a relatively high explanatory power corresponding to the selected time lag as a final indicator;
A method for predicting credit risk by industry using macroeconomic indicators.
delete delete The method according to claim 1,
The early warning score calculating unit may multiply the calculated early warning score by the calculated target borrower based on at least one of financial statement, financial transaction information and representative credit information for each segment by the calculated industrial risk index, Increasing the early warning score of the target borrower if the calculated average default rate of the target borrower is higher than the long-term average default rate of the observed borrowing rate for the determined time, and lowering the early warning score of the target borrower if the calculated defaulting default rate is lower than the long-
To-risk credit risk prediction using industry-specific macroeconomic indicators.
The method according to claim 1,
Wherein the step of classifying the defined target carousel into a plurality of segments according to an industry classification comprises:
The classifier classifying the defined target borrower into a plurality of segments according to an asset scale together with an industry classification;
A method for predicting credit risk by industry using macroeconomic indicators.
The method according to claim 1,
Wherein the selecting one or more final indicators comprises:
If there is no candidate indicator of the corresponding industry, the regression model adaptation unit selects at least one final indicator through correlation analysis between candidate indices for the entire industrial candidate indices pool constituted as described above;
A method for predicting credit risk by industry using macroeconomic indicators.
The method according to claim 1,
Wherein the step of classifying the defined target carousel into a plurality of segments according to an industry classification comprises:
The classification unit identifies whether the industry code corresponding to the target borrower industry is included in the list of industrial codes according to the classification system based on the standard industry classification and determines the lowest classification system including the industry code corresponding to the target borrower industry Classifying the target borrower into segments corresponding to the corresponding industry codes in the selected classification system;
A method for predicting credit risk by industry using macroeconomic indicators.
A collecting unit collecting macroeconomic indicators defined by industry and constituting a pool of industrial candidate indicators;
A classifier for defining a target borrower and classifying the defined target borrower into a plurality of segments according to an industrial classification;
A regression model fitting unit that selects one or more final indicators by analyzing correlation between candidate indices of the industry by segments and adapts a regression model in which the selected at least one final indicator is an independent variable and the observation default rate is a dependent variable; And
An industrial risk index calculating unit for calculating a predicted default rate based on the regression model for each segment and calculating an industrial risk index based on the calculated predicted default rate;
/ RTI &gt;
The industrial risk index is calculated based on the average and standard deviation of the calculated default rate and the default rate,
The industrial risk index SUR is calculated on the basis of the following equation:
&Lt; Equation &
Figure 112015106484395-pat00012

Here, SUR denotes the industrial risk index, EDR denotes the predicted default rate, ADR denotes the observed default rate, t denotes the base month, and t + 3 denotes the default monthly rate , T-1 means one month before the base month, and t and n are the unit of the credit risk prediction system by industry using monthly macroeconomic indicators.
10. The method of claim 9,
The regression model fitting unit,
A time lag having the highest explanatory power for the actual default rate for each candidate indicator of the industry is selected for each segment, the correlation between the candidate indicators of the industry is analyzed, and the candidate indicators whose correlation degrees are equal to or greater than a predetermined value are compared, An industry-specific credit risk prediction system that utilizes macroeconomic indicators to select candidate indicators with relatively high explanatory power corresponding to selected time lag as final indicators.
delete delete 10. The method of claim 9,
Wherein the preliminary default rate is calculated by multiplying the calculated early warning score for each target borrower based on at least one of financial statement, financial transaction information, and representative credit information by segment, An early warning score calculator for increasing an early warning score of the target borrower and decreasing an early warning score of the target borrower if the calculated defaulting default rate is lower than the long term average default rate;
The credit risk prediction system for each industry using macroeconomic indicators further includes.
10. The method of claim 9,
Wherein,
An industry-specific credit risk prediction system utilizing macroeconomic indicators that classify the defined target borrowers into multiple segments according to asset size along with industry classification.
10. The method of claim 9,
The regression model fitting unit,
An industry-specific credit risk prediction apparatus utilizing macroeconomic indicators that select one or more final indicators through correlation analysis between candidate indicators for all the pools of candidate industrial indicators constituted when the industry candidate indicators do not exist.
KR1020150094516A 2015-07-02 2015-07-02 Apparatus and method for predicting industrial credit risk using macro-economic indicator KR101597939B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150094516A KR101597939B1 (en) 2015-07-02 2015-07-02 Apparatus and method for predicting industrial credit risk using macro-economic indicator

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150094516A KR101597939B1 (en) 2015-07-02 2015-07-02 Apparatus and method for predicting industrial credit risk using macro-economic indicator

Publications (1)

Publication Number Publication Date
KR101597939B1 true KR101597939B1 (en) 2016-02-25

Family

ID=55446228

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150094516A KR101597939B1 (en) 2015-07-02 2015-07-02 Apparatus and method for predicting industrial credit risk using macro-economic indicator

Country Status (1)

Country Link
KR (1) KR101597939B1 (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107644276A (en) * 2017-10-27 2018-01-30 常州工学院 Society based on quadratic term fitting GM (1,1), which always brings up, compares forecast model
CN107767259A (en) * 2017-09-30 2018-03-06 平安科技（深圳）有限公司 Loan risk control method, electronic installation and readable storage medium storing program for executing
KR20190064749A (en) * 2017-12-01 2019-06-11 신한금융투자 주식회사 Method and device for intelligent decision support in stock investment
KR20200053004A (en) * 2018-10-30 2020-05-18 주식회사 알스피릿 Method and device for context recognition regarding predicting sensing of crisis using business index
US11113360B2 (en) 2018-02-07 2021-09-07 Doosan Heavy Industries & Construction C Plant abnormality prediction system and method
KR102633684B1 (en) * 2023-05-09 2024-02-06 주식회사 어니스트펀드 Method for automatic credit scoring calibration considering macro-economic index and recofding medium storing program to execute the method

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20090006489A (en) 2007-07-11 2009-01-15 고려대학교 산학협력단 Toolkit of constructing credit risk model, method of managing credit risk using credit risk model construction and recording medium thereof
KR20140093532A (en) * 2013-01-18 2014-07-28 주식회사 에프앤가이드 A method and an apparatus for calculating crisis index for an industrial estate
KR20140133341A (en) 2013-05-10 2014-11-19 주식회사 신한은행 Method and apparatus for predicting industry risk using industrial warning signs

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20090006489A (en) 2007-07-11 2009-01-15 고려대학교 산학협력단 Toolkit of constructing credit risk model, method of managing credit risk using credit risk model construction and recording medium thereof
KR20140093532A (en) * 2013-01-18 2014-07-28 주식회사 에프앤가이드 A method and an apparatus for calculating crisis index for an industrial estate
KR20140133341A (en) 2013-05-10 2014-11-19 주식회사 신한은행 Method and apparatus for predicting industry risk using industrial warning signs

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
김대철 외 2인. "거시경제변수를 고려한 기술평가모형의 개선 : 기술보증기금의 사례", 한국경영과학회, 2013년 7월, 경영과학, 제30권, 제2호, pp.117-132.* *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107767259A (en) * 2017-09-30 2018-03-06 平安科技（深圳）有限公司 Loan risk control method, electronic installation and readable storage medium storing program for executing
CN107644276A (en) * 2017-10-27 2018-01-30 常州工学院 Society based on quadratic term fitting GM (1,1), which always brings up, compares forecast model
KR20190064749A (en) * 2017-12-01 2019-06-11 신한금융투자 주식회사 Method and device for intelligent decision support in stock investment
KR102105744B1 (en) * 2017-12-01 2020-05-29 신한금융투자 주식회사 Method and device for intelligent decision support in stock investment
US11113360B2 (en) 2018-02-07 2021-09-07 Doosan Heavy Industries & Construction C Plant abnormality prediction system and method
KR20200053004A (en) * 2018-10-30 2020-05-18 주식회사 알스피릿 Method and device for context recognition regarding predicting sensing of crisis using business index
KR102178427B1 (en) 2018-10-30 2020-11-18 주식회사 알스피릿 Method and device for context recognition regarding predicting sensing of crisis using business index
KR102633684B1 (en) * 2023-05-09 2024-02-06 주식회사 어니스트펀드 Method for automatic credit scoring calibration considering macro-economic index and recofding medium storing program to execute the method

Similar Documents

Publication Publication Date Title
KR101597939B1 (en) Apparatus and method for predicting industrial credit risk using macro-economic indicator
US11657455B2 (en) Systems and methods for measuring relationships between investments and other variables
US20210118054A1 (en) Resource exchange system
US20160148321A1 (en) Simplified screening for predicting errors in tax returns
JP2003316950A (en) System and method for credit evaluation
US8984022B1 (en) Automating growth and evaluation of segmentation trees
WO2020118019A1 (en) Adaptive transaction processing system
US8285616B2 (en) Method and system for dynamically producing detailed trade payment experience for enhancing credit evaluation
WO2014036396A1 (en) Systems and methods for measuring relationships between investments and other variables
JP6251383B2 (en) Calculating the probability of a defaulting company
CN113538154A (en) Risk object identification method and device, storage medium and electronic equipment
Shawon et al. Assessing Geopolitical Risks and Their Economic Impact on the USA Using Data Analytics
CN114493853A (en) Credit rating evaluation method, credit rating evaluation device, electronic device and storage medium
KR20130098753A (en) Technology credit scoring method, system and recording medium thereof
CN117391436A (en) Enterprise risk monitoring method and device
Zang Construction of Mobile Internet Financial Risk Cautioning Framework Based on BP Neural Network
KR20140133341A (en) Method and apparatus for predicting industry risk using industrial warning signs
KR20230103025A (en) Method, Apparatus, and System for provision of corporate credit analysis and rating information
CN114418776A (en) Data processing method, device, terminal equipment and medium
TWI634508B (en) A system and method using multi-dimensional rating to determine an entity&#39;s future commercial viability
Sarhadi et al. Efficiency of externally adjusted bankruptcy prediction patterns by bankruptcy prediction of Iranian organizations
Scandizzo et al. Loss given default models
CN115099957A (en) Enterprise information data processing method and device
Dichev Discriminative Ability In Estimating Probability Of Default With Certain Machine Learning Algorithms
Айтим et al. DEVELOPMENT OF SYSTEMS FOR EFFECTIVE ESTIMATION OF CREDIT SCORES

Legal Events

Date Code Title Description
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20190129

Year of fee payment: 4