CN113657991A - Credit risk early warning method, system and storage medium based on graph rule engine - Google Patents
Credit risk early warning method, system and storage medium based on graph rule engine Download PDFInfo
- Publication number
- CN113657991A CN113657991A CN202110924127.2A CN202110924127A CN113657991A CN 113657991 A CN113657991 A CN 113657991A CN 202110924127 A CN202110924127 A CN 202110924127A CN 113657991 A CN113657991 A CN 113657991A
- Authority
- CN
- China
- Prior art keywords
- risk
- graph
- enterprise
- enterprises
- total
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of credit risk assessment, in particular to a credit risk early warning method and system based on a graph rule engine and a storage medium. According to the method, a graph database comprising information of a plurality of enterprises, natural persons and risk events can be formed through a graph rule engine, a subdata graph is extracted from the graph database as required, the total risk of the enterprises to be evaluated is obtained according to a set risk value, a conduction coefficient and a calculation rule, and then the risk condition of the enterprises to be evaluated can be judged by comparing the total risk with a set threshold value, so that the current conduction risk of the enterprises can be used as a supplement of credit wind control indexes for pre-loan audit and post-loan management links, the wind control level of financial institutions is improved, and the credit risk evaluation is more accurate and complete.
Description
Technical Field
The invention relates to the field of credit risk assessment, in particular to a credit risk early warning method and system based on a graph rule engine and a storage medium.
Background
Credit assessment is the basis for credit and is used to solve the repayment risk measurement problem during lending, and credit risk management occupies an important place in the capital market.
The credit risk assessment in the prior art is mainly based on modeling of enterprise operation indexes, and pays more attention to enterprises, but actually, risk conduction of events outside the enterprises to the enterprises also has influence on the enterprises, but the credit risk assessment in the aspect is not performed in the prior art.
The Graph rules engine is a rules engine based on Graph Data (Graph Data). The graph data includes vertices and their attribute data, and edges and their attribute data, which form a graph, where the edges may be directional and may define weights. Therefore, the graph rule engine can be designed, events with certain risk values are used as a class of vertexes, in the graph rule engine, the risk conduction coefficients are defined by edges between external events and enterprises, and meanwhile, the risk calculation mode is defined based on understanding of the events, so that the risk event conduction early warning function is realized in the enterprise credit application evaluation and post-loan management.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the credit risk early warning method based on the graph rule engine can realize a risk event conduction early warning function in enterprise credit application evaluation and post-loan management, and further enables credit risk evaluation to be more accurate and complete.
The technical scheme adopted by the invention is as follows: a credit risk early warning method based on a graph rule engine comprises the following steps:
s1, establishing a graph database containing information of a plurality of enterprises, natural persons and risk events, wherein the graph database comprises vertexes and edges, the enterprises, the natural persons and the risk events are vertexes, the correlation types among the enterprises, the natural persons and the risk events are edges, and the risk values of different risk events, the conduction coefficients of different correlation types, the calculation rules and the total risk threshold are set;
s2, carrying out breadth-first search aiming at an enterprise needing to be evaluated, and completely extracting enterprise, natural people and risk event information related to the enterprise to form a sub data map, wherein the sub data map comprises a vertex and edges, the enterprise, the natural people and the risk event are all vertexes, and the correlation types of the vertexes, the natural people and the risk event are edges;
s3, judging whether the risk event exists in the subdata map, if not, ending; if the risk event exists, jumping to the next step;
s4, calculating the total risk of the enterprise to be evaluated in the sub data map according to the risk value, the conduction coefficient and the calculation rule defined in the step S1, then comparing the total risk with the total risk threshold set in the step S1, and if the obtained total risk does not exceed the set total risk threshold, ending the process; and if the obtained total risk exceeds a set total risk threshold value, judging that the enterprise has risks, and performing risk early warning.
Preferably, the total risk is an internal risk plus an external risk, the internal risk is an enterprise risk required to be evaluated, and the external risk is a risk of an enterprise or a natural person associated with the enterprise required to be evaluated.
Preferably, the calculation rule is: when the risk event is judged to be an internal risk, the calculation rule is accumulation, and when the risk event is judged to be an external risk, the calculation rule is a highest value or an average value.
Preferably, in step S1, a data volume threshold of the sub-data map needs to be set, the data volume of the sub-data map needs to be counted after the sub-data map is formed in step S2, and then the data volume obtained in step S2 needs to be compared with the data volume threshold, if the data volume of the sub-data map is greater than the data volume threshold, the risk coefficient obtained in step S4 needs to be corrected, and if the data volume of the sub-data map is less than the data volume threshold, the risk coefficient obtained in step S4 does not need to be corrected.
Preferably, the database data needs to be updated periodically in step S1.
Preferably, the search frequency of the breadth-first search in step S2 needs to be set by the user in advance.
In order to solve the technical problem of the application, the invention also discloses a credit risk early warning system based on the graph rule engine, which comprises the following components:
the system comprises a graph database creating module, a graph database creating module and a graph database creating module, wherein the graph database is used for creating a graph database according to the existing information of a plurality of enterprises, natural persons and risk events, the graph database comprises vertexes and edges, the enterprises, the natural persons and the risk events are all vertexes, and the correlation types of the enterprises, the natural persons and the risk events are edges;
the subdata map creation module is used for searching enterprises needing evaluation, and completely extracting enterprise, natural people and risk event information related to the enterprises to form a subdata map, wherein the subdata map comprises vertexes and edges, the enterprises, the natural people and the risk events are vertexes, and the correlation types of the vertexes, the natural people and the risk events are edges;
the total risk calculation module is used for calculating the total risk of the enterprise needing to be evaluated according to the formed subdata graph;
and the risk judgment module is used for judging whether the enterprise needing to be evaluated has risk or not according to the calculated total risk.
Preferably, it further comprises an updating module for periodically updating the map database created by the map database creating module.
Preferably, the system further comprises a correction module for correcting the total risk calculated by the total risk calculation module according to the data volume of the sub-data map created by the sub-data map creation module.
In order to solve the technical problem of the present application, the present invention also discloses a computer-readable storage medium having stored thereon a computer program which, when executed, implements a credit risk early warning method based on a graph rule engine.
Compared with the prior art, the method has the following advantages that: through the graph rule engine, a graph database comprising information of a plurality of enterprises, natural persons and risk events can be formed, a sub-data graph is extracted from the graph database as required, the total risk of the enterprises to be evaluated is obtained according to the set risk value, the conduction coefficient and the calculation rule, and then the risk condition of the enterprises to be evaluated can be judged by comparing the total risk with the set threshold value, so that the current conduction risk of the enterprises can be used as the supplement of credit wind control indexes for pre-loan audit and post-loan management links, the wind control level of financial institutions is improved, and the credit risk evaluation is more accurate and complete.
Drawings
FIG. 1 is a flow chart of a credit risk early warning method based on a graph rules engine of the present invention.
Fig. 2 is a schematic diagram of a sub-data map according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
The first embodiment is as follows:
a credit risk early warning method based on a graph rule engine, as shown in fig. 1, comprising the following steps:
s1, establishing a graph database containing information of a plurality of enterprises, natural persons and risk events, wherein the graph database comprises vertexes and edges, the enterprises, the natural persons and the risk events are vertexes, the correlation types among the enterprises, the natural persons and the risk events are edges, and the risk values of different risk events, the conduction coefficients of different correlation types, the calculation rules and the total risk threshold are set; wherein:
because the graph database comprises a plurality of enterprises, natural persons and risk event information, the graph database is huge and cannot be shown in the drawing of the embodiment;
risk events, which are important events that can define a risk value and occur to a certain enterprise or a natural person, such as a certain enterprise loan overdue or a certain natural person being restricted to high consumption, and each risk event has a respective risk value, for example, in this embodiment, the risk value of the loan overdue is 80, and the risk value of the restriction to high consumption is 100;
the association includes association between enterprises, such as enterprise a investing enterprise B, or enterprise a signing a cooperative agreement with enterprise B, and also includes association between enterprises and natural persons, such as someone is a legal person or a stockholder of an enterprise; and representing that the associated edge is directional, representing the direction to which the risk is passed;
the conductivity coefficient refers to the risk conductivity coefficient in different correlations, and if controlled, the conductivity coefficient is 1; investment, the conductivity coefficient is 0.5; in cooperation, the conductivity is 0.8;
the calculation rule is that internal risks are added to external risks, and the internal risks are risks of real control people, stockholders, enterprises and the like; the external risks are risks of cooperative enterprises, investment enterprises and invested enterprises;
the total risk threshold, set to 100 in this embodiment;
s2, carrying out breadth-first search aiming at an enterprise needing to be evaluated, and completely extracting enterprise, natural people and risk event information related to the enterprise to form a sub data map, wherein the sub data map comprises a vertex and edges, the enterprise, the natural people and the risk event are all vertexes, and the correlation types of the vertexes, the natural people and the risk event are edges;
the breadth-first search is a relatively conventional search method in the prior art, so the detailed description is omitted here, but a user can set the search degree of the breadth-first search as required, and can search according to a fixed search degree;
FIG. 2 is a subdata map in this embodiment, which includes 8 vertices, two height limits, one overdue loan, Enterprise A, Enterprise B, Enterprise C, Zhang and Listing, wherein Zhang is associated with a height limit risk event, and Listing is also associated with a height limit risk event, Enterprise A is associated with an overdue loan risk event, Listing is associated with Enterprise A, Enterprise A and Enterprise B are associated with investment, Enterprise C and Enterprise B are associated with collaboration, and Zhang is associated with Enterprise C for control; the enterprise to be evaluated is enterprise C;
s3, judging whether the risk event exists in the subdata map, if not, ending; if the risk event exists, jumping to the next step;
because the sub-data map has risk events, the process goes to step S4 to continue;
s4, calculating the total risk of the enterprise to be evaluated in the sub data map according to the risk value, the conduction coefficient and the calculation rule defined in the step S1, then comparing the total risk with the total risk threshold set in the step S1, and if the obtained total risk does not exceed the set total risk threshold, ending the process; and if the obtained total risk exceeds a set total risk threshold value, judging that the enterprise has risks, and performing risk early warning.
In this embodiment, the total risk of the enterprise C is solved, including an internal risk and an external risk, where the internal risk is a risk event that actually controls the zhangwei of the person, i.e., 100 × 1; the external risk includes the limit risk of lymin, 100 × 0.5 × 0.8, and the loan overdue risk of enterprise a, 80 × 0.5 × 0.8, in this embodiment the external risk is highest, so 80 × 0.5 × 0.8 is taken, so the total risk of enterprise C is 100+32 × 132, which is greater than the set total risk threshold of 100, so enterprise C is risky, and an early warning is given.
The credit risk early warning method is realized by adopting a credit risk early warning system based on a graph rule engine, and the system comprises a graph database creating module, a sub-data graph creating module, a total risk calculating module and a risk judging module, wherein:
the system comprises a graph database creating module, a graph database creating module and a graph database creating module, wherein the graph database is used for creating a graph database according to the existing information of a plurality of enterprises, natural persons and risk events, the graph database comprises vertexes and edges, the enterprises, the natural persons and the risk events are all vertexes, and the correlation types of the enterprises, the natural persons and the risk events are edges;
the subdata map creation module is used for searching enterprises needing evaluation, and completely extracting enterprise, natural people and risk event information related to the enterprises to form a subdata map, wherein the subdata map comprises vertexes and edges, the enterprises, the natural people and the risk events are vertexes, and the correlation types of the vertexes, the natural people and the risk events are edges;
the total risk calculation module is used for calculating the total risk of the enterprise needing to be evaluated according to the formed subdata graph;
and the risk judgment module is used for judging whether the enterprise needing to be evaluated has risk or not according to the calculated total risk.
Example two:
the difference from the first embodiment is that the external risk in the second embodiment is averaged, so that the external risk is 26, the total risk is 126, and the total risk is greater than the threshold value, so that the enterprise C is also risky and needs to be warned.
Example three:
the difference from the first embodiment is that the early warning system also includes a correction module, and the data amount of the sub-data map needs to be calculated in step S2, which may be the number of vertices and edges, and a data amount threshold needs to be set at the same time, this embodiment is set to 20, as shown in fig. 2, there are eight vertices and seven edges, which are fifteen data amounts in total, and are smaller than the threshold, so that no correction is needed, and if the data amount is greater than the threshold, a correction is needed, the correction coefficient of the present application is set to 0.95, that is, when the data amount is greater than the threshold, the obtained total risk needs to be multiplied by the correction coefficient to obtain a final total risk, and then the obtained final total risk is compared with the set total risk threshold.
Example four:
the difference from the first embodiment is that the warning system includes an updating module, and after the step S1 completes creating the database, the warning system needs to perform periodic updating, where the updating includes adding some new information and modifying some old information, if the enterprise has no risk event but finds a risk event, the risk event needs to be added to the database, or if the enterprise has a risk event but the risk event has been cancelled, the risk event needs to be removed from the database, and the data required for updating is obtained from a public network or other open data source, so as to ensure the information accuracy of the database, and further ensure the information accuracy of the sub-data map extracted from the database.
Example five:
the difference from the fourth embodiment is that after each update, a sub data map needs to be re-formed, then a new total risk of the enterprise needing to be evaluated is calculated according to the new sub data map, if the total risk exceeds a set total risk threshold, an early warning is directly performed, if the total risk does not exceed the set total risk threshold, a change trend of the total risk needs to be calculated compared with the previously calculated total risk, and then compared with the set change trend threshold, if the change trend of the total risk is faster, the enterprise needs to be warned even if the total risk does not exceed the set total risk threshold.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Various alterations and modifications will no doubt become apparent to those skilled in the art after having read the above description. Therefore, the appended claims should be construed to cover all such variations and modifications as fall within the true spirit and scope of the invention. Any and all equivalent ranges and contents within the scope of the claims should be considered to be within the intent and scope of the present invention.
Claims (10)
1. A credit risk early warning method based on a graph rule engine is characterized by comprising the following steps:
s1, establishing a graph database containing information of a plurality of enterprises, natural persons and risk events, wherein the graph database comprises vertexes and edges, the enterprises, the natural persons and the risk events are vertexes, the correlation types among the enterprises, the natural persons and the risk events are edges, and the risk values of different risk events, the conduction coefficients of different correlation types, the calculation rules and the total risk threshold are set;
s2, carrying out breadth-first search aiming at an enterprise needing to be evaluated, and completely extracting enterprise, natural people and risk event information related to the enterprise to form a sub data map, wherein the sub data map comprises a vertex and edges, the enterprise, the natural people and the risk event are all vertexes, and the correlation types of the vertexes, the natural people and the risk event are edges;
s3, judging whether the risk event exists in the subdata map, if not, ending; if the risk event exists, jumping to the next step;
s4, calculating the total risk of the enterprise to be evaluated in the sub data map according to the risk value, the conduction coefficient and the calculation rule defined in the step S1, then comparing the total risk with the total risk threshold set in the step S1, and if the obtained total risk does not exceed the set total risk threshold, ending the process; and if the obtained total risk exceeds a set total risk threshold value, judging that the enterprise has risks, and performing risk early warning.
2. The credit risk early warning method based on graph rule engine according to claim 1, characterized in that: the total risk is the internal risk plus the external risk, the internal risk is the risk of the enterprise needing to be evaluated, and the external risk is the risk of the enterprise or natural people associated with the enterprise needing to be evaluated.
3. The credit risk early warning method based on the graph rule engine as claimed in claim 2, wherein: the calculation rule is as follows: when the risk event is judged to be an internal risk, the calculation rule is accumulation, and when the risk event is judged to be an external risk, the calculation rule is a highest value or an average value.
4. The credit risk early warning method based on graph rule engine according to claim 1, characterized in that: in step S1, a data volume threshold of the sub-data map needs to be set, the data volume of the sub-data map needs to be counted after the sub-data map is formed in step S2, and then the data volume obtained in step S2 needs to be compared with the data volume threshold, if the data volume of the sub-data map is greater than the data volume threshold, the risk coefficient obtained in step S4 needs to be corrected, and if the data volume of the sub-data map is less than the data volume threshold, the risk coefficient obtained in step S4 does not need to be corrected.
5. The credit risk early warning method based on graph rule engine according to claim 1, characterized in that: in step S1, the database data needs to be updated periodically.
6. The credit risk early warning method based on graph rule engine according to claim 1, characterized in that: the search frequency of the breadth-first search in step S2 needs to be set by the user in advance.
7. A credit risk early warning system based on a graph rule engine is characterized in that: it includes:
the system comprises a graph database creating module, a graph database creating module and a graph database creating module, wherein the graph database is used for creating a graph database according to the existing information of a plurality of enterprises, natural persons and risk events, the graph database comprises vertexes and edges, the enterprises, the natural persons and the risk events are all vertexes, and the correlation types of the enterprises, the natural persons and the risk events are edges;
the subdata map creation module is used for searching enterprises needing evaluation, and completely extracting enterprise, natural people and risk event information related to the enterprises to form a subdata map, wherein the subdata map comprises vertexes and edges, the enterprises, the natural people and the risk events are vertexes, and the correlation types of the vertexes, the natural people and the risk events are edges;
the total risk calculation module is used for calculating the total risk of the enterprise needing to be evaluated according to the formed subdata graph;
and the risk judgment module is used for judging whether the enterprise needing to be evaluated has risk or not according to the calculated total risk.
8. The credit risk warning system based on graph rules engine as claimed in claim 7 wherein: it also includes an updating module for periodically updating the map database created by the map database creating module.
9. The credit risk warning system based on graph rules engine as claimed in claim 7 wherein: the system also comprises a correction module for correcting the total risk calculated by the total risk calculation module according to the data volume of the sub data diagram created by the sub data diagram creation module.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the program when executed implements the graph rules engine-based credit risk early warning method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110924127.2A CN113657991A (en) | 2021-08-12 | 2021-08-12 | Credit risk early warning method, system and storage medium based on graph rule engine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110924127.2A CN113657991A (en) | 2021-08-12 | 2021-08-12 | Credit risk early warning method, system and storage medium based on graph rule engine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113657991A true CN113657991A (en) | 2021-11-16 |
Family
ID=78479555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110924127.2A Pending CN113657991A (en) | 2021-08-12 | 2021-08-12 | Credit risk early warning method, system and storage medium based on graph rule engine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657991A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160012235A1 (en) * | 2014-02-10 | 2016-01-14 | Vivo Security Inc. | Analysis and display of cybersecurity risks for enterprise data |
| CN110363449A (en) * | 2019-07-25 | 2019-10-22 | 中国工商银行股份有限公司 | A kind of Risk Identification Method, apparatus and system |
| CN111402064A (en) * | 2020-06-03 | 2020-07-10 | 天云融创数据科技（北京）有限公司 | Risk value evaluation method and device |
| CN112184012A (en) * | 2020-09-27 | 2021-01-05 | 平安资产管理有限责任公司 | Enterprise risk early warning method, device, equipment and readable storage medium |
| CN112488843A (en) * | 2020-10-29 | 2021-03-12 | 中国农业银行股份有限公司福建省分行 | Enterprise risk early warning method, device, equipment and medium based on social network |
-
2021
- 2021-08-12 CN CN202110924127.2A patent/CN113657991A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160012235A1 (en) * | 2014-02-10 | 2016-01-14 | Vivo Security Inc. | Analysis and display of cybersecurity risks for enterprise data |
| CN110363449A (en) * | 2019-07-25 | 2019-10-22 | 中国工商银行股份有限公司 | A kind of Risk Identification Method, apparatus and system |
| CN111402064A (en) * | 2020-06-03 | 2020-07-10 | 天云融创数据科技（北京）有限公司 | Risk value evaluation method and device |
| CN112184012A (en) * | 2020-09-27 | 2021-01-05 | 平安资产管理有限责任公司 | Enterprise risk early warning method, device, equipment and readable storage medium |
| CN112488843A (en) * | 2020-10-29 | 2021-03-12 | 中国农业银行股份有限公司福建省分行 | Enterprise risk early warning method, device, equipment and medium based on social network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Predicting future earnings changes using machine learning and detailed financial data | |
| EP1565856A2 (en) | Portfolio rebalancing by means of resampled efficient frontiers | |
| US8694427B2 (en) | Time-efficient and deterministic adaptive score calibration techniques for maintaining a predefined score distribution | |
| CN106156151A (en) | The Risk Identification Method of internetwork operation event and device | |
| CN109272362A (en) | A kind of method for pushing, device and the electronic equipment of risk guarantee product | |
| Nordås et al. | Quantifying regulatory barriers to services trade | |
| CN110782349A (en) | Model training method and system | |
| CN113657990A (en) | Ant-lion algorithm optimized NARX neural network risk prediction system and method | |
| CN115203496A (en) | Project intelligent prediction and evaluation method and system based on big data and readable storage medium | |
| Obweger et al. | Similarity searching in sequences of complex events | |
| CN110516713A (en) | A kind of target group's recognition methods, device and equipment | |
| Filiz et al. | Graphical models for correlated defaults | |
| KR102249028B1 (en) | System for Debt Repayment Capability Evaluation Of Corporation | |
| Kim et al. | Volume‐based ranking method for a ranked voting system | |
| CN113657991A (en) | Credit risk early warning method, system and storage medium based on graph rule engine | |
| US20150348201A1 (en) | Automated tool for investment technologies | |
| CN111784495B (en) | Guarantee ring identification method and device, computer equipment and storage medium | |
| CN115330510A (en) | Cross-platform credit management method based on block chain intelligent contract | |
| CN112632197A (en) | Service relation processing method and device based on knowledge graph | |
| Krusinskas et al. | THE RESEARCH OF RELIABILITY OF BANKRUPTCY PREDICTION MODELS IN LITHUANIAN COMPANIES. | |
| Othman et al. | Impact of external and domestic shocks on Malaysia’s electronic and electrical (E&E) export demand | |
| Vnukova et al. | Identifying changes in insurance companies’ competitiveness on the travel services market | |
| CN112348220A (en) | Credit risk assessment prediction method and system based on enterprise behavior pattern | |
| Ewertzh | Bankruptcy Distributions and Modelling for Swedish Companies Using Logistic Regression | |
| Tangsawasdirat et al. | Credit Risk Database: Credit Scoring Models for Thai SMEs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211116 |