CN112633709A - Enterprise credit investigation evaluation method and device - Google Patents
Enterprise credit investigation evaluation method and device Download PDFInfo
- Publication number
- CN112633709A CN112633709A CN202011569137.0A CN202011569137A CN112633709A CN 112633709 A CN112633709 A CN 112633709A CN 202011569137 A CN202011569137 A CN 202011569137A CN 112633709 A CN112633709 A CN 112633709A
- Authority
- CN
- China
- Prior art keywords
- credit investigation
- credit
- enterprise
- evaluation
- data
- 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
- 238000011835 investigation Methods 0.000 title claims abstract description 373
- 238000011156 evaluation Methods 0.000 title claims abstract description 201
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000013210 evaluation model Methods 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 10
- 238000011161 development Methods 0.000 description 14
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a method and a device for enterprise credit investigation evaluation. The method comprises the steps of obtaining credit investigation indexes of the enterprises according to credit investigation reports; judging whether credit investigation indexes of the enterprises meet preset quantity conditions and preset effectiveness conditions at the same time, if so, obtaining credit investigation scores of the enterprises according to the credit investigation indexes of the enterprises, and evaluating the credit investigation of the enterprises according to the credit investigation scores of the enterprises; if not, acquiring multi-channel data of the enterprise, and performing credit investigation evaluation on the enterprise according to the multi-channel data. Confirming whether credit investigation indexes of the enterprises are sufficient and perfect according to a preset quantity condition and a preset validity condition, and evaluating the enterprises with sufficient and perfect credit investigation indexes according to credit investigation scores of the enterprises; and for enterprises with insufficient and/or incomplete credit investigation indexes, the source channels of credit investigation data of the enterprises are widened, and credit investigation evaluation is realized by data of multiple channels. The problem that the enterprise credit investigation evaluation is too low due to the fact that the credit investigation indexes analyzed in the credit investigation report are missing is solved, and the accuracy of the enterprise credit investigation evaluation is improved.
Description
Technical Field
The application relates to the technical field of data processing, in particular to an enterprise credit investigation evaluation method and device.
Background
The credit investigation is the activity of collecting, sorting, storing and processing credit information of natural people, legal people and other organizations according to law, providing services such as credit reports, credit assessment, credit consultation and the like for the outside, helping clients judge and control credit risks and performing credit management. The credit investigation plays an important basic role in promoting the development of credit economy and the construction of a social credit system: first, credit risk prevention; secondly, credit transaction is expanded; thirdly, the economic operation efficiency is improved; and fourthly, construction of a push social credit system.
The existing enterprise credit investigation evaluation system relies on credit investigation index data analyzed from a people bank credit investigation report, and machine learning models are used for evaluating and judging credit investigation conditions. However, compared with large enterprises in the industry, small and medium-sized enterprises have smaller personnel scale, asset scale and operation scale, and credit investigation index data of the small and medium-sized enterprises analyzed from credit investigation reports of people's banks may not be comprehensive, so that the evaluation result of the credit investigation evaluation system for the small and medium-sized enterprises is poor, and the small and medium-sized enterprises are difficult to evaluate through credit investigation. Thus, the credit business transaction for small and medium enterprises is hindered. For example, financial data of small and medium-sized enterprises often have loss and cannot guarantee authenticity of the data, and sufficient mortgages are lacking. If the medium and small enterprises are assessed before credit according to the credit assessment scheme of the large enterprise, the medium and small enterprises can hardly obtain financing, which is contrary to the strategy of emphasizing the development of the medium and small enterprises.
Therefore, how to perfect a credit investigation evaluation system not only meets the credit evaluation requirement of large enterprises, but also makes up for short boards missing credit investigation data of small and medium-sized enterprises to accurately evaluate the credit, which is a problem to be solved urgently at present.
Disclosure of Invention
Based on the above problems, the application provides an enterprise credit investigation assessment method and device to improve the accuracy of the credit investigation assessment of small and medium enterprises.
The embodiment of the application discloses the following technical scheme:
the first aspect of the present application provides an enterprise credit investigation assessment method, including:
acquiring credit investigation indexes of the enterprises according to the credit investigation reports;
judging whether credit investigation indexes of the enterprises meet preset quantity conditions and preset effectiveness conditions at the same time, if so, obtaining credit investigation scores of the enterprises according to the credit investigation indexes of the enterprises, and evaluating the credit investigation of the enterprises according to the credit investigation scores of the enterprises; if not, acquiring multi-channel data of the enterprise, and performing credit investigation evaluation on the enterprise according to the multi-channel data; the multi-channel data and the credit report come from different channels.
Optionally, obtaining credit investigation scores of the enterprises according to the credit investigation indexes of the enterprises includes:
obtaining the score value of each credit investigation index according to the score rule corresponding to each credit investigation index in all credit investigation indexes of the enterprise;
and obtaining the credit investigation score of the enterprise according to the credit assessment value of each credit investigation index and the credit investigation score weight of each credit investigation index.
Optionally, credit assessment is performed on the enterprise according to credit assessment scores of the enterprise, including:
when the credit investigation score of the enterprise exceeds a preset first threshold value, inputting the credit investigation index of the enterprise into a first credit investigation evaluation model to obtain a credit investigation evaluation result output by the first credit investigation evaluation model; the credit assessment result comprises the following steps: the credit investigation evaluation is qualified or the credit investigation evaluation is unqualified;
and when the credit investigation score of the enterprise does not exceed the preset first threshold value, determining that the credit investigation evaluation of the enterprise is unqualified.
Optionally, performing credit investigation evaluation on the enterprise according to the multi-channel data, including:
obtaining industry region scores of enterprises according to the multi-channel data;
and performing credit investigation evaluation on the enterprise according to the industry regional score of the enterprise.
Optionally, credit investigation and evaluation are performed on the enterprise according to the industry regional score of the enterprise, including:
obtaining the evaluation weight of each credit investigation evaluation submodel according to the mapping relation between the industry regional score and the evaluation weight of the credit investigation evaluation submodels and the industry regional score of the enterprise; the multiple credit investigation evaluation submodels respectively correspond to one different data dimension;
inputting credit data of an enterprise into corresponding credit investigation evaluation submodels according to data dimensions respectively to obtain evaluation results output by the credit investigation evaluation submodels respectively; the credit data of the enterprise comprises multi-channel data of the enterprise and credit investigation indexes of the enterprise;
obtaining credit investigation evaluation results of the enterprise according to the evaluation results output by the credit investigation evaluation submodels and the evaluation weights of the credit investigation evaluation submodels; the credit assessment result comprises the following steps: and the credit assessment is qualified or the credit assessment is not qualified.
Optionally, the plurality of credit assessment submodels includes at least two of:
credit investigation evaluation submodel corresponding to business class data, credit investigation evaluation submodel corresponding to performance record class data, credit investigation evaluation submodel corresponding to enterprise management class data, credit investigation evaluation submodel corresponding to potential growth class data or credit investigation evaluation submodel corresponding to enterprise associated credit class data
Optionally, the preset number condition includes: the credit investigation index total number of the enterprise exceeds a preset second threshold; the preset validity indexes include: the key indexes of the enterprise are complete and effective.
Optionally, the multi-channel data comprises data of at least two of the following channels:
data from the administration of the industry and commerce, data from the tax administration, data from the customs administration, data from the statistics bureau, data from the court of law, data from the commission of state, data from the ministry of commerce, data from the post office, or public opinion data.
A second aspect of the present application provides an enterprise credit investigation apparatus, including:
the credit investigation index acquisition module is used for acquiring the credit investigation index of the enterprise according to the credit investigation report;
the first judgment module is used for judging whether credit investigation indexes of enterprises meet a preset quantity condition and a preset validity condition at the same time;
the first evaluation module is used for obtaining credit investigation scores of the enterprises according to the credit investigation indexes of the enterprises and evaluating the credit investigation of the enterprises according to the credit investigation scores of the enterprises when the first judgment module judges that the credit investigation indexes of the enterprises are positive;
the second evaluation module is used for acquiring the multi-channel data of the enterprise and performing credit investigation evaluation on the enterprise according to the multi-channel data when the first judgment module judges that the result is negative; the multi-channel data and the credit report come from different channels.
Optionally, the second evaluation module comprises:
the industry region scoring unit is used for obtaining the industry region scoring of the enterprise according to the multi-channel data;
and the first evaluation unit is used for carrying out credit investigation evaluation on the enterprise according to the industry regional score of the enterprise.
Compared with the prior art, the method has the following beneficial effects:
the enterprise credit investigation evaluation method provided by the application comprises the following steps: acquiring credit investigation indexes of the enterprises according to the credit investigation reports; judging whether credit investigation indexes of the enterprises meet preset quantity conditions and preset effectiveness conditions at the same time, if so, obtaining credit investigation scores of the enterprises according to the credit investigation indexes of the enterprises, and evaluating the credit investigation of the enterprises according to the credit investigation scores of the enterprises; if not, acquiring multi-channel data of the enterprise, and performing credit investigation evaluation on the enterprise according to the multi-channel data; the multi-channel data and the credit report come from different channels. In the technical scheme, whether credit investigation indexes of enterprises are sufficient and complete is confirmed according to a preset quantity condition and a preset validity condition, and for the enterprises with sufficient and complete credit investigation indexes, credit investigation scores of the enterprises are used for evaluation; for enterprises with insufficient and/or imperfect credit investigation indexes, the source channels of credit investigation data are widened, and credit investigation evaluation is realized by data of multiple channels. The scheme avoids the problem of excessively low enterprise credit investigation evaluation caused by the lack of the analyzed credit investigation indexes in the credit investigation report, and improves the accuracy of the enterprise credit investigation evaluation.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a flowchart of an enterprise credit investigation assessment method according to an embodiment of the present application;
fig. 2 is a flowchart of another method for assessing credit investigation of an enterprise according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an enterprise credit assessment apparatus according to an embodiment of the present application.
Detailed Description
As described above, the existing credit assessment technical solutions are only suitable for the assessment of the enterprises with sufficient credit assessment indexes. And when some enterprises with insufficient credit investigation indexes evaluate the credit investigation indexes, the disadvantages are obvious and the evaluation is difficult to pass, so that the business handling is influenced.
Aiming at the problems, the inventor provides a more complete enterprise credit investigation and evaluation method and a more complete enterprise credit investigation and evaluation device through research. Whether credit investigation indexes of enterprises are sufficient and perfect is confirmed through a preset quantity condition and a preset effectiveness condition, credit investigation data channels of the enterprises with insufficient and/or imperfect credit investigation indexes are widened, and credit investigation evaluation is carried out on the enterprises with data of multiple channels. Therefore, the accuracy of enterprise credit investigation evaluation is improved.
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Method embodiment
Referring to fig. 1, the figure is a flowchart of an enterprise credit assessment method according to an embodiment of the present application. As shown in fig. 1, the method for evaluating enterprise credit provided by the embodiment of the present application includes:
s101: and obtaining the credit investigation indexes of the enterprises according to the credit investigation reports.
After the enterprise and the bank generate credit activities, the enterprise credit investigation management system of the people bank can have related credit investigation data, and the related credit investigation data can be obtained from the people bank through inquiring the credit investigation report. The credit investigation report of the enterprise user can generally contain information such as enterprise basic information, enterprise loan transaction, mortgage, enterprise guarantee, inter-enterprise incidence relation, enterprise high management, enterprise tax, public service payment, enterprise rating, enterprise financial report, credit report query history and the like.
When a business user needs to transact business related to credit activities from a certain bank (e.g., bank a), bank a may send a report inquiry request to the people's bank according to the business request of the business user to obtain a credit report of the business from the people's bank. After the credit investigation report is obtained, the information in the credit investigation report can be analyzed into various credit investigation indexes through a preset service rule, and the credit investigation indexes are stored in an index table with a structure shown in the following table 1.
TABLE 1 index Table
The structure of the index table shown in table 1 is merely an example, and in other implementation scenarios, the index table may further include other fields. The structure and content of the index table are not limited herein. The index states include: valid, invalid, or otherwise. The other means that the state in which the index is not specified is valid or invalid. Thus, the status of the indicator is invalid or otherwise, and is not considered valid.
In addition, it is a relatively mature technology to analyze the index data of the enterprise from the enterprise credit report provided by the people's bank in this field, and therefore, the detailed description thereof is omitted here.
S102: judging whether credit investigation indexes of the enterprise simultaneously meet a preset quantity condition and a preset validity condition, if so, executing S103; if not, S104 is executed.
In the step, the completeness of the index is checked from the aspect of the number and the effectiveness of the credit indicators. When the credit investigation indexes of the enterprise are verified to be complete from the aspects of quantity and effectiveness, a credit investigation evaluation scheme is adopted, and the step S103 is as follows; on the contrary, if the credit investigation index of the enterprise is not complete according to the quantity and/or effectiveness of the index, another credit investigation scheme is adopted, as the following step S104.
In one possible implementation, the preset number condition includes: and the total credit investigation index number of the enterprise exceeds a preset second threshold value. As an example, the preset second threshold is 10.
The credit investigation indicators of the enterprise can comprise: key indicators and auxiliary indicators. The key indexes are credit investigation indexes with higher weight when credit investigation is carried out on the enterprise; the auxiliary index is a credit investigation index with lower occupation weight when the credit investigation evaluation is carried out on the enterprise. For example, the credit indicator whose weight exceeds the preset weight threshold is used as the key indicator, and vice versa, the key indicator is used as the auxiliary indicator.
As an example, key metrics may include: the system comprises basic information of an enterprise, debt or overdue information represented by a legal person, credit granting and lending conditions of the legal person, owed tax of the enterprise, administrative penalty information of the enterprise, external financing information of the enterprise, external guarantee information of the enterprise, bad loan of the enterprise and the like. The auxiliary index may include a guarantee amount or the like. In specific implementation, the key indicators and the auxiliary indicators of the credit investigation indicators can be divided according to actual requirements, and are not limited herein.
In a possible implementation manner, the preset validity index includes: the key indexes of the enterprise are complete and effective. That is, all the key indexes are required to be absent and the index states are all effective.
S103: and when the credit investigation indexes of the enterprises meet the preset quantity condition and the preset effectiveness condition, acquiring credit investigation scores of the enterprises according to the credit investigation indexes of the enterprises, and performing credit investigation evaluation on the enterprises according to the credit investigation scores of the enterprises.
The scoring rule corresponding to each credit investigation index is set in advance, and can be set according to actual conditions, and the embodiment of the application is not limited. And calculating the score value of each credit investigation index according to the score rule corresponding to each credit investigation index. In addition, each credit indicator also individually takes a specific weight of credit score. And obtaining credit assessment scores of the enterprises according to the credit assessment values and the credit assessment score weights of the credit assessment indexes. For example, the credit score value of each credit indicator is weighted and summed, and the result is used as the credit score of the enterprise. And then, evaluating the credit investigation condition of the enterprise by using the credit investigation score of the enterprise obtained previously to confirm whether the credit investigation is passed (credit investigation is qualified).
S104: and when the credit investigation indexes of the enterprise can not meet the preset quantity condition and the preset effectiveness condition at the same time, acquiring multi-channel data of the enterprise, and performing credit investigation evaluation on the enterprise according to the multi-channel data.
In the embodiment of the application, the multi-channel data and the credit investigation report come from different channels. The credit investigation report comes from the people's bank, and the people's bank provides credit investigation data through the credit investigation report. The multi-channel data refers to data obtained through channels such as a business administration, a tax administration, a customs administration, a statistical bureau, a court, a state commission, a business department, a post office or the internet. The data obtained from the internet channel may also be called public opinion data. The multi-channel data of the enterprise described in this step S104 includes data of at least two of the above channels.
For the enterprises with incomplete credit investigation indexes verified by the preset quantity conditions and the preset effectiveness conditions, more and richer credit data are collected by acquiring multi-channel data of the enterprises. Therefore, the problem that the enterprise credit investigation index is lost in the credit investigation report is solved. The multi-channel data are integrated, and the effective credit investigation indexes analyzed in the steps are combined, so that more accurate credit investigation evaluation can be realized for enterprises.
The method for evaluating enterprise credit investigation provided by the embodiment of the application is described above. The method comprises the steps of obtaining credit investigation indexes of enterprises according to credit investigation reports; judging whether credit investigation indexes of the enterprises meet preset quantity conditions and preset effectiveness conditions at the same time, if so, obtaining credit investigation scores of the enterprises according to the credit investigation indexes of the enterprises, and evaluating the credit investigation of the enterprises according to the credit investigation scores of the enterprises; if not, acquiring multi-channel data of the enterprise, and performing credit investigation evaluation on the enterprise according to the multi-channel data; the multi-channel data and the credit report come from different channels. In the method, whether credit investigation indexes of an enterprise are sufficient and complete is confirmed according to a preset quantity condition and a preset validity condition, and for the enterprise with sufficient and complete credit investigation indexes, evaluation is carried out according to credit investigation scores of the enterprise; for enterprises with insufficient and/or imperfect credit investigation indexes, the source channels of credit investigation data are widened, and credit investigation evaluation is realized by data of multiple channels. The scheme avoids the problem of excessively low enterprise credit investigation evaluation caused by the lack of the analyzed credit investigation indexes in the credit investigation report, and improves the accuracy of the enterprise credit investigation evaluation.
Therefore, the technical scheme of the application not only meets the credit assessment requirement of large enterprises, but also makes up for short boards missing in credit investigation data of small and medium-sized enterprises, and accurately performs credit assessment on the short boards. And the credit investigation evaluation system is perfected.
On the basis of the technical scheme of the embodiment, the application further provides another enterprise credit investigation evaluation method. Referring to fig. 2, a flow chart of this method is shown. As shown in fig. 2, another enterprise credit assessment method provided in the embodiment of the present application includes:
s201: and obtaining the credit investigation indexes of the enterprises according to the credit investigation reports.
S202: judging whether credit investigation indexes of the enterprise simultaneously meet a preset quantity condition and a preset validity condition, if so, executing S203; if not, S208 is performed.
S203: and obtaining the score value of each credit investigation index according to the scoring rule corresponding to each credit investigation index in all credit investigation indexes of the enterprise, and entering S204.
S204: and obtaining credit assessment scores of the enterprises according to the credit assessment values of the credit assessment indexes and the credit assessment score weights of the credit assessment indexes, and entering S205.
In the embodiment of the present application, the descriptions of S201 to S204 have been already provided in the foregoing embodiments, and are not repeated herein.
S205: judging whether the credit investigation score of the enterprise exceeds a preset first threshold value, if so, executing S206; if not, S207 is performed.
When the credit investigation score of the enterprise is higher than the preset first threshold, step S206 may be executed to input a plurality of credit investigation indicators into the credit investigation evaluation model to obtain a credit investigation evaluation result. If the credit investigation score of the enterprise is lower than the preset first threshold value, S207 is directly executed to judge that the credit investigation evaluation is unqualified, and a bank applying business transaction by the enterprise user refuses to provide corresponding credit service for the enterprise user. It should be noted that the preset first threshold may be set according to actual experience and actual requirements, and the numerical value in the embodiment of the present application is not specifically limited.
In the above S202-S205, the data quality inspection of the index is performed through S202, and the credit assessment scoring of S203-S204 can be performed only after the index reaches the standard. According to S205, if the credit investigation score obtained according to the credit investigation indicator is smaller than the preset first threshold, the enterprise with poor credit investigation condition can be screened as soon as possible (see S207), and the subsequent credit investigation model evaluation is not required (see S206). Therefore, the flow can be shortened, and the credit investigation evaluation efficiency is improved.
S206: when the credit investigation score of the enterprise exceeds a preset first threshold value, inputting the credit investigation index of the enterprise into the first credit investigation evaluation model to obtain a credit investigation evaluation result output by the first credit investigation evaluation model.
The credit assessment result comprises the following steps: and the credit assessment is qualified or the credit assessment is not qualified.
In a possible implementation manner, the first credit investigation evaluation model is obtained by training a data sample of the credit investigation indicator by using a machine learning method. The credit indicator data sample comprises a plurality of credit indicator data and a sample label. For example, if a bad credit record exists in the credit investigation index, marking the sample as unqualified; if no bad credit investigation record exists in the credit investigation index, the service personnel or experts in related fields are requested to carry out subjective judgment, and the sample is marked to be qualified or unqualified.
The credit assessment results contained 1 (for pass) and 0 (for fail). If the credit investigation result is 1, the subsequent due diligence can be continued, and whether the bank has credit business with the enterprise is further judged. If the credit investigation evaluation result is 0, stopping the subsequent process and directly refusing the credit business with the enterprise.
The number of samples in the first credit assessment model is set according to actual conditions, and the training process of the first credit assessment model belongs to the prior art and is not described herein.
As a possible implementation, the training of the first credit evaluation model may select a Gradient Boosting Decision Tree (gradientboosting Tree) algorithm. Since the algorithm and the specific modeling process are relatively mature technologies in the field, they are not described herein again. In addition, other algorithms can be selected according to actual conditions, such as random forests, logistic regression, decision trees and the like, to train the first credit assessment model.
S207: and when the credit investigation score of the enterprise does not exceed the preset first threshold value, determining that the credit investigation evaluation of the enterprise is unqualified.
For enterprises with unqualified credit investigation index data quality in the credit investigation report, credit investigation scoring is not needed according to the credit investigation index, rejection by banks due to too low scoring is avoided, the credit investigation condition of the enterprises is judged by observing data of other channels, and the accuracy of credit investigation evaluation is improved. This is described in particular in connection with S208-S212.
S208: and acquiring multi-channel data of the enterprise, and entering S209.
S209: and obtaining the industry region score of the enterprise according to the multi-channel data, and entering S210.
In the embodiment of the application, basic information of an enterprise can be obtained by combining data obtained through channels such as a business administration, a tax administration, a customs administration, a statistical bureau, a court, a state commission, a business department, a post office or the internet. For example, industry policies (government support attitude and power for industry, whether the industry belongs to the national encouragement development industry, the preferential development industry, the non-restrictive development industry and the non-prohibited development industry or not and development prospects of the industry) of an enterprise are obtained, a regional policy (corresponding encouragement support strength and policy of a local government, whether the industry is limited or not, the encouragement development industry and the economic environment and development trend of an enterprise business district) of an enterprise registry is obtained, and an industry regional score is comprehensively evaluated.
In specific implementation, the industry policy and the region policy can be respectively matched with weights. As an example, the industry policy weighs 0.6; the region policy is weighted 0.4. If the country encourages development, preferentially develops the industry, non-restrictive development, non-prohibited development industry, the corresponding industry policy scores are 100, 90, 70 and 60 in turn. The regional policy scores are similar. And is not particularly limited herein.
The industry regional score is equivalent to the regional development situation of the enterprise industry and is evaluated. And after the industry region score is obtained, credit investigation and evaluation can be carried out on the enterprise according to the industry region score of the enterprise. This process is described below primarily in connection with S210-S212.
S210: and obtaining the evaluation weights of the credit investigation evaluation submodels according to the mapping relation between the industry region score and the evaluation weights of the credit investigation evaluation submodels and the industry region score of the enterprise, and entering S211.
The obtained multi-channel data can be classified according to data dimensions. For example, data of industry and commerce, tax, public opinion, judicial law, customs and the like of an enterprise can be divided into five dimensions of an operation type, a performance record type, an enterprise management type, a potential growth type and an enterprise associated credit type, and characteristic data of the enterprise at least needs to comprise data of two dimensions of the operation type and the performance record type.
The partitioning of the data dimension is illustrated below by way of example.
The business data of the enterprise reflects the business conditions of the enterprise, including the business range, the business scale, the facility equipment, the product popularity, the marketing ability, the business advantages, the business stability, the research and development strength of the enterprise, and the like.
The performance record class data of the enterprise reflects the credit condition of the enterprise, including the information of qualification credit, illegal behaviors, business performance, fee payment, tendering and bidding credit and the like of the enterprise.
The enterprise management data reflects the management level of the enterprise and the high management condition of the enterprise, including the human resource composition, the stock right condition, the high management quality, the organization structure, the management system construction and implementation condition of the enterprise, whether the high management has the information of default illegal behaviors and the like, and whether the high management changes.
The growth potential data reflects the development potential of the enterprise, and comprises data such as employee quality, innovation capability, enterprise honor, patent condition, financing capability, copyright and the like of the enterprise. The enterprise associated credit data reflects the operation conditions of enterprises which have close relationship with the enterprises, including credit condition information of high-management and concurrent enterprises, enterprises which have close capital exchange with the enterprises and enterprises which are externally guaranteed by the enterprises.
Considering that most of enterprises have certain business transaction, bond, stockholder or direct investment relationship, one enterprise is exposed to risks, and the related enterprises are also affected, so that the risks of the related enterprises need to be evaluated, and the risks are embodied in the credit data dimension of the related enterprises of the enterprises.
The credit investigation evaluation sub-model can be established in advance by a machine learning method and a data sample respectively aiming at five dimensions of an operation class, a performance record class, an enterprise management class, a potential growth class and an enterprise association class. After collecting the relevant data of the enterprise to be evaluated, inputting the relevant data into the evaluation submodel with the corresponding dimension to obtain the evaluation result of the submodel (see S211 for details). The establishment process of the credit assessment submodel can adopt methods such as logistic regression, neural network, random forest, decision tree and the like, belongs to mature technologies in the field, and is not described in detail.
In the embodiment of the application, the plurality of credit assessment submodels respectively correspond to different data dimensions. In practical application, the credit investigation evaluation submodel can be respectively established based on the dimension of data. For example, the data dimensions include: business class data, fulfillment record class data, enterprise management class data, potential growth class data, and enterprise associated credit class data. Then, the above-mentioned each data dimension credit assessment submodel can be trained respectively: the credit investigation evaluation submodel corresponding to the business class data, the credit investigation evaluation submodel corresponding to the performance record class data, the credit investigation evaluation submodel corresponding to the enterprise management class data, the credit investigation evaluation submodel corresponding to the potential growth class data and the credit investigation evaluation submodel corresponding to the enterprise associated credit class data.
It should be noted that the above division of the data dimension is only an example. In practical application, the data may be further divided according to other dimensions according to actual requirements or data contents, which is not limited herein.
Before the implementation of S210, a mapping relationship between the industry region score of each interval and the weight of the credit investigation evaluation submodel of each dimension may be set in advance. For example, if the industry region score belongs to a first interval, the evaluation weights of the credit investigation evaluation submodels of the corresponding dimensions are w 11-w 15 in sequence; and if the industry region score belongs to a second interval, the evaluation weights of the credit investigation evaluation submodels of the corresponding dimensions are w 21-w 25 in sequence. The higher the evaluation weight of the credit investigation evaluation submodel is, the more important the data dimension corresponding to the credit investigation evaluation submodel is to the credit investigation evaluation of the enterprise.
And obtaining the evaluation weights of the credit investigation evaluation submodels according to the mapping relation between the industry region score and the evaluation weights of the credit investigation evaluation submodels and the industry region score of the enterprise.
S211: and respectively inputting the credit data of the enterprise into the corresponding credit investigation assessment submodels according to the data dimension, obtaining the assessment results output by the credit investigation assessment submodels respectively, and entering S212.
Note that the data input to the credit investigation sub-model is credit data of the enterprise, and includes both the multi-channel data of the enterprise and the credit investigation indicators of the enterprise obtained from the credit investigation report. And inputting the credit data of the corresponding dimensionality into the credit investigation evaluation submodel to obtain the evaluation result output by each credit investigation evaluation submodel.
However, the evaluation result output by each sub-model only represents the evaluation result of the credit investigation situation of the enterprise by its dimension, and the subordinate step S212 is further required to be executed in order to more fully balance the credit investigation situation of the enterprise.
Fig. 2 only shows the implementation flow of executing S211 after executing S210. In practical applications, the execution order of these two steps is not limited. For example, S211 may be performed first and then S210 or both S210 and S211 may be performed.
S212: and obtaining the credit investigation evaluation result of the enterprise according to the evaluation result output by each of the credit investigation evaluation submodels and the evaluation weight of each of the credit investigation evaluation submodels.
The evaluation weight of each credit assessment submodel matching the industry regional score of the enterprise is obtained in S210, and the evaluation result (e.g., in the form of score) output by each credit assessment submodel is obtained in S211. In step S212, the final evaluation can be performed by combining the evaluation weights and the evaluation results.
The specific implementation mode can be as follows: and obtaining the evaluation weight of each credit investigation submodel according to the industry regional score, and carrying out weighted calculation on the evaluation result of each credit investigation submodel. The following formula:
wherein S is a summation result, Yi is an output result of the credit assessment submodel of the ith dimension, and Xi is an assessment weight of the credit assessment submodel of the ith dimension read from the remapping relation table according to the industry region score of the enterprise. n represents the total number of dimensions of the credit assessment submodel. As an example n-5.
And obtaining a final credit assessment result according to the summation result S. As an example, if the summation result S exceeds a preset third threshold, the final credit assessment result is that the credit assessment is qualified; otherwise, the credit investigation evaluation result is unqualified.
In the enterprise credit investigation evaluation method introduced in the above embodiment, obtaining multi-channel data enriches the evaluation dimension and evaluation perspective of credit investigation conditions. After multi-channel data are obtained, industry region scores of enterprises are calculated, a weight mapping relation table between the industry region scores and corresponding dimension credit assessment submodels is set, and different submodel weight mappings are read according to different scores. The credit investigation condition of the enterprise can be judged more flexibly and more accurately.
Based on the enterprise credit investigation evaluation method provided by the foregoing embodiment, correspondingly, the application further provides an enterprise credit investigation evaluation device. Specific implementations of this apparatus are described below with reference to the accompanying drawings and examples.
Device embodiment
Referring to fig. 3, the figure is a schematic structural diagram of an enterprise credit assessment apparatus according to an embodiment of the present application. As shown in fig. 3, an enterprise credit assessment apparatus 300 provided in the embodiment of the present application includes:
the credit investigation index acquisition module 301 is configured to acquire a credit investigation index of an enterprise according to a credit investigation report;
a first judging module 302, configured to judge whether the credit investigation indicator of the enterprise meets a preset quantity condition and a preset validity condition at the same time;
a first evaluation module 303, configured to, when the first determination module 302 determines that the result is yes, obtain a credit investigation score of the enterprise according to the credit investigation indicator of the enterprise, and perform credit investigation evaluation on the enterprise according to the credit investigation score of the enterprise;
a second evaluation module 304, configured to, when the first determination module 302 determines that the result is negative, obtain multi-channel data of the enterprise, and perform credit investigation and evaluation on the enterprise according to the multi-channel data; the multi-channel data and the credit report come from different channels.
In the technical scheme, whether credit investigation indexes of enterprises are sufficient and complete is confirmed according to a preset quantity condition and a preset validity condition, and for the enterprises with sufficient and complete credit investigation indexes, credit investigation scores of the enterprises are used for evaluation; for enterprises with insufficient and/or imperfect credit investigation indexes, the source channels of credit investigation data are widened, and credit investigation evaluation is realized by data of multiple channels. The scheme avoids the problem of excessively low enterprise credit investigation evaluation caused by the lack of the analyzed credit investigation indexes in the credit investigation report, and improves the accuracy of the enterprise credit investigation evaluation.
Optionally, the first evaluation module 303 includes:
the index credit rating value acquisition unit is used for acquiring the credit rating value of each credit investigation index according to the rating rule corresponding to each credit investigation index in all credit investigation indexes of the enterprise;
and the credit investigation score obtaining unit is used for obtaining the credit investigation score of the enterprise according to the credit investigation value of each credit investigation index and the credit investigation score weight of each credit investigation index.
Optionally, the first evaluation module 303 further comprises:
the second evaluation unit is used for inputting the credit investigation indexes of the enterprise into the first credit investigation evaluation model when the credit investigation score of the enterprise exceeds a preset first threshold value, and obtaining a credit investigation evaluation result output by the first credit investigation evaluation model; the credit assessment result comprises: the credit investigation evaluation is qualified or the credit investigation evaluation is unqualified;
and the third evaluation unit is used for determining that the credit investigation evaluation of the enterprise is unqualified when the credit investigation score of the enterprise does not exceed the preset first threshold.
Optionally, the second evaluation module 304 includes:
the industry region scoring unit is used for obtaining the industry region scoring of the enterprise according to the multi-channel data;
and the first evaluation unit is used for carrying out credit investigation evaluation on the enterprise according to the industry region score of the enterprise.
Optionally, the first evaluation unit specifically includes:
the evaluation weight obtaining subunit is used for obtaining the evaluation weights of the credit investigation evaluation submodels according to the mapping relation between the industry region scores and the evaluation weights of the credit investigation evaluation submodels and the industry region scores of the enterprises; the plurality of credit investigation evaluation submodels respectively correspond to different data dimensions;
the evaluation result preliminary obtaining subunit is used for respectively inputting the credit data of the enterprise into corresponding credit investigation evaluation submodels according to data dimensions, and obtaining the evaluation results output by the credit investigation evaluation submodels; the credit data of the enterprise comprises multi-channel data of the enterprise and credit investigation indexes of the enterprise;
the evaluation result final obtaining subunit is used for obtaining credit investigation evaluation results of the enterprise according to the evaluation results output by the credit investigation evaluation submodels and the evaluation weights of the credit investigation evaluation submodels; the credit assessment result comprises: and the credit assessment is qualified or the credit assessment is not qualified.
In the enterprise credit investigation evaluation device introduced in the above embodiment, obtaining multi-channel data enriches the evaluation dimension and evaluation perspective of credit investigation conditions. After multi-channel data are obtained, industry region scores of enterprises are calculated, a weight mapping relation table between the industry region scores and corresponding dimension credit assessment submodels is set, and different submodel weight mappings are read according to different scores. Therefore, the credit investigation condition of the enterprise can be judged more flexibly and more accurately.
Optionally, the plurality of credit assessment submodels comprises at least two of:
credit investigation evaluation submodel corresponding to business class data, credit investigation evaluation submodel corresponding to performance record class data, credit investigation evaluation submodel corresponding to enterprise management class data, credit investigation evaluation submodel corresponding to potential growth class data or credit investigation evaluation submodel corresponding to enterprise associated credit class data
Optionally, the preset number condition includes: the total credit investigation index number of the enterprise exceeds a preset second threshold; the preset validity index includes: the key indexes of the enterprise are complete and effective.
Optionally, the multi-channel data comprises data of at least two of the following channels:
data from the administration of the industry and commerce, data from the tax administration, data from the customs administration, data from the statistics bureau, data from the court of law, data from the commission of state, data from the ministry of commerce, data from the post office, or public opinion data.
The above description is only one specific embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An enterprise credit investigation assessment method is characterized by comprising the following steps:
acquiring credit investigation indexes of the enterprises according to the credit investigation reports;
judging whether the credit investigation indexes of the enterprises meet a preset quantity condition and a preset effectiveness condition at the same time, if so, obtaining credit investigation scores of the enterprises according to the credit investigation indexes of the enterprises, and evaluating the credit investigation of the enterprises according to the credit investigation scores of the enterprises; if not, acquiring multi-channel data of the enterprise, and performing credit investigation evaluation on the enterprise according to the multi-channel data; the multi-channel data and the credit report come from different channels.
2. The method of claim 1, wherein obtaining credit investigation scores for the business based on credit investigation metrics for the business comprises:
obtaining the score value of each credit investigation index according to the scoring rule corresponding to each credit investigation index in all credit investigation indexes of the enterprise;
and obtaining credit assessment scores of the enterprises according to the credit assessment values of the credit assessment indexes and the credit assessment score weights of the credit assessment indexes.
3. The method of claim 1 or 2, wherein the credit assessment of the business according to the credit assessment score of the business comprises:
when the credit investigation score of the enterprise exceeds a preset first threshold, inputting the credit investigation index of the enterprise into a first credit investigation evaluation model to obtain a credit investigation evaluation result output by the first credit investigation evaluation model; the credit assessment result comprises: the credit investigation evaluation is qualified or the credit investigation evaluation is unqualified;
and when the credit investigation score of the enterprise does not exceed the preset first threshold value, determining that the credit investigation evaluation of the enterprise is unqualified.
4. The method of claim 1, wherein said assessing credit for said business based on said multi-channel data comprises:
obtaining an industry region score of the enterprise according to the multi-channel data;
and performing credit investigation evaluation on the enterprise according to the industry regional score of the enterprise.
5. The method of claim 4, wherein the credit assessment of the enterprise based on the enterprise geographic score comprises:
obtaining the evaluation weight of each credit investigation evaluation submodel according to the mapping relation between the industry regional score and the evaluation weight of each credit investigation evaluation submodel and the industry regional score of the enterprise; the plurality of credit investigation evaluation submodels respectively correspond to different data dimensions;
inputting the credit data of the enterprise into corresponding credit investigation evaluation submodels according to data dimensions respectively to obtain evaluation results output by the credit investigation evaluation submodels respectively; the credit data of the enterprise comprises multi-channel data of the enterprise and credit investigation indexes of the enterprise;
obtaining credit investigation evaluation results of the enterprise according to the evaluation results output by the credit investigation evaluation submodels and the evaluation weights of the credit investigation evaluation submodels; the credit assessment result comprises: and the credit assessment is qualified or the credit assessment is not qualified.
6. The method of claim 1, wherein the plurality of credit evaluation submodels comprises at least two of:
the credit investigation evaluation submodel corresponding to the business class data, the credit investigation evaluation submodel corresponding to the performance record class data, the credit investigation evaluation submodel corresponding to the enterprise management class data, the credit investigation evaluation submodel corresponding to the potential growth class data or the credit investigation evaluation submodel corresponding to the enterprise associated credit class data.
7. The method of claim 1, wherein the preset number condition comprises: the total credit investigation index number of the enterprise exceeds a preset second threshold; the preset validity index includes: the key indexes of the enterprise are complete and effective.
8. The method of claim 1, wherein the multi-channel data comprises data for at least two of the following channels:
data from the administration of the industry and commerce, data from the tax administration, data from the customs administration, data from the statistics bureau, data from the court of law, data from the commission of state, data from the ministry of commerce, data from the post office, or public opinion data.
9. An enterprise credit assessment device, comprising:
the credit investigation index acquisition module is used for acquiring the credit investigation index of the enterprise according to the credit investigation report;
the first judgment module is used for judging whether the credit investigation indexes of the enterprises meet a preset quantity condition and a preset validity condition at the same time;
the first evaluation module is used for obtaining credit investigation scores of the enterprises according to the credit investigation indexes of the enterprises and evaluating the credit investigation of the enterprises according to the credit investigation scores of the enterprises when the first judgment module judges that the business investigation results are yes;
the second evaluation module is used for acquiring the multi-channel data of the enterprise and performing credit investigation evaluation on the enterprise according to the multi-channel data when the first judgment module judges that the result is negative; the multi-channel data and the credit report come from different channels.
10. The apparatus of claim 9, wherein the second evaluation module comprises:
the industry region scoring unit is used for obtaining the industry region scoring of the enterprise according to the multi-channel data;
and the first evaluation unit is used for carrying out credit investigation evaluation on the enterprise according to the industry region score of the enterprise.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011569137.0A CN112633709A (en) | 2020-12-26 | 2020-12-26 | Enterprise credit investigation evaluation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011569137.0A CN112633709A (en) | 2020-12-26 | 2020-12-26 | Enterprise credit investigation evaluation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112633709A true CN112633709A (en) | 2021-04-09 |
Family
ID=75325207
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011569137.0A Pending CN112633709A (en) | 2020-12-26 | 2020-12-26 | Enterprise credit investigation evaluation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112633709A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115456753A (en) * | 2022-09-07 | 2022-12-09 | 安徽省优质采科技发展有限责任公司 | Enterprise credit information analysis method and system for bidding platform |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101118613A (en) * | 2006-08-03 | 2008-02-06 | 上海现代物流投资发展有限公司 | Dangerous chemicals electric commerce credit assessment method |
CN107993143A (en) * | 2017-11-23 | 2018-05-04 | 深圳大管加软件与技术服务有限公司 | A kind of Credit Risk Assessment method and system |
CN108416664A (en) * | 2018-01-29 | 2018-08-17 | 广州越秀金融科技有限公司 | Methods of risk assessment and system based on consumptive credit scene are realized |
CN109409677A (en) * | 2018-09-27 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium |
CN109492945A (en) * | 2018-12-14 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Business risk identifies monitoring method, device, equipment and storage medium |
CN110400215A (en) * | 2019-07-31 | 2019-11-01 | 浪潮软件集团有限公司 | Small micro- Enterprise Credit Rating Model construction method and system towards family, enterprise |
CN110443698A (en) * | 2019-08-13 | 2019-11-12 | 爱信诺征信有限公司 | Credit evaluation device and credit evaluation system |
CN110796539A (en) * | 2019-10-31 | 2020-02-14 | 中国工商银行股份有限公司 | Credit investigation evaluation method and device |
CN111598682A (en) * | 2020-05-11 | 2020-08-28 | 上海企腾投资咨询有限公司 | Credit risk assessment method and system for enterprise |
-
2020
- 2020-12-26 CN CN202011569137.0A patent/CN112633709A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101118613A (en) * | 2006-08-03 | 2008-02-06 | 上海现代物流投资发展有限公司 | Dangerous chemicals electric commerce credit assessment method |
CN107993143A (en) * | 2017-11-23 | 2018-05-04 | 深圳大管加软件与技术服务有限公司 | A kind of Credit Risk Assessment method and system |
CN108416664A (en) * | 2018-01-29 | 2018-08-17 | 广州越秀金融科技有限公司 | Methods of risk assessment and system based on consumptive credit scene are realized |
CN109409677A (en) * | 2018-09-27 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium |
CN109492945A (en) * | 2018-12-14 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Business risk identifies monitoring method, device, equipment and storage medium |
CN110400215A (en) * | 2019-07-31 | 2019-11-01 | 浪潮软件集团有限公司 | Small micro- Enterprise Credit Rating Model construction method and system towards family, enterprise |
CN110443698A (en) * | 2019-08-13 | 2019-11-12 | 爱信诺征信有限公司 | Credit evaluation device and credit evaluation system |
CN110796539A (en) * | 2019-10-31 | 2020-02-14 | 中国工商银行股份有限公司 | Credit investigation evaluation method and device |
CN111598682A (en) * | 2020-05-11 | 2020-08-28 | 上海企腾投资咨询有限公司 | Credit risk assessment method and system for enterprise |
Non-Patent Citations (1)
Title |
---|
易纲 等: ""中国人民银行营业管理部2006年调研报告选编"", 31 August 2007, 北京:中国经济出版社, pages: 199 - 201 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115456753A (en) * | 2022-09-07 | 2022-12-09 | 安徽省优质采科技发展有限责任公司 | Enterprise credit information analysis method and system for bidding platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Caramanis et al. | Auditee and audit firm characteristics as determinants of audit qualifications: Evidence from the Athens stock exchange | |
CN108665159A (en) | A kind of methods of risk assessment, device, terminal device and storage medium | |
Chen et al. | A first econometric analysis of the CRIX family | |
CN106651570A (en) | System and method for real-time loan approval | |
JP4710011B2 (en) | Company value analysis apparatus and company value analysis method | |
CN110796539A (en) | Credit investigation evaluation method and device | |
CN112613977A (en) | Personal credit loan admission credit granting method and system based on government affair data | |
CN112541817A (en) | Marketing response processing method and system for potential customers of personal consumption loan | |
Buriak et al. | Reputation risk in banking: application for Ukraine | |
Bilbao-Terol et al. | Hedonic evaluation of the SRI label of mutual funds using matching methodology | |
CN113989019A (en) | Method, device, equipment and storage medium for identifying risks | |
CN112163944B (en) | Loan qualification scoring method and device for clients, computer equipment and storage medium | |
CN111882140A (en) | Risk evaluation method, model training method, device, equipment and storage medium | |
CN111090833A (en) | Data processing method, system and related equipment | |
Chi et al. | Debt rating model based on default identification: Empirical evidence from Chinese small industrial enterprises | |
CN115082225A (en) | Enterprise financing risk assessment method and device | |
CN113159796A (en) | Trade contract verification method and device | |
Shygun et al. | The influence of the classification of non-current assets as holding for sales on the liquidity of the company’s balance sheet | |
Cumming et al. | Misconduct risks, legal enforcement and venture capital networks | |
CN112633709A (en) | Enterprise credit investigation evaluation method and device | |
Agbiogwu et al. | Effects of human resource cost on profitability of banks in Nigeria | |
Dimitras et al. | Multi‐criteria evaluation of loan applications in shipping | |
Cucaro | Measuring the" health" of Italian SMEs with insolvency prediction models Z'-ScoreM and D-Score: Measuring default index of Italian SMEs | |
CN115564591A (en) | Financing product determination method and related equipment | |
CN114971241A (en) | Credit evaluation method and system for engineering construction subject |
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 |