CN112037007A - Credit approval method for small and micro enterprises and electronic equipment - Google Patents
Credit approval method for small and micro enterprises and electronic equipment Download PDFInfo
- Publication number
- CN112037007A CN112037007A CN202010767315.4A CN202010767315A CN112037007A CN 112037007 A CN112037007 A CN 112037007A CN 202010767315 A CN202010767315 A CN 202010767315A CN 112037007 A CN112037007 A CN 112037007A
- Authority
- CN
- China
- Prior art keywords
- model
- credit
- risk
- client
- evaluation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000011156 evaluation Methods 0.000 claims abstract description 105
- 238000004422 calculation algorithm Methods 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 12
- 238000012502 risk assessment Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000007477 logistic regression Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 238000003860 storage Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000699670 Mus sp. Species 0.000 description 1
- 108010063499 Sigma Factor Proteins 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 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
- 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
- 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
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a credit approval method for a small and micro enterprise and electronic equipment, wherein the method comprises the following steps: performing risk evaluation on data of a plurality of clients through a first model to obtain first evaluation results corresponding to the client data one by one, and generating a risk factor combination of a client group according to all the client data; fitting to obtain a second model based on the risk factor combination and all the first evaluation results, and adjusting the second model according to the actual business; and performing risk evaluation on the data of the client by using the second model to obtain a second evaluation result, and judging the credit approval result of the client based on the loan amount of the client and the second evaluation result. The credit company which newly develops the mini-micro credit business can quickly start the new credit business of the mini-micro enterprise, develop a more accurate self-owned model, provide reference basis for the credit company to carry out credit approval on the mini-micro enterprise, and make a more appropriate credit approval result so as to reduce the risk of the credit company.
Description
Technical Field
The invention relates to the technical field of internet financial wind control, in particular to a method and electronic equipment for credit approval of small and micro enterprises.
Background
The number of small micro-enterprises is large, and according to the data of the national statistical bureau, about 7000 thousands of small micro-enterprises are currently active in China. Meanwhile, due to the continuous development of big data related technologies, the credit of the small and micro enterprises is gradually on-line and scaled, and emerging credit companies increasingly adopt an on-line credit mode to carry out business. For an emerging credit company, developing an online credit business for a small and micro enterprise requires a corresponding small and micro enterprise risk assessment model, but when the business is not developed or is developed for a short period of time, enough customer samples cannot be accumulated, especially default customer samples which can be accumulated for a long time are accumulated, so that the emerging credit company actually has few samples for model development.
Credit companies often require cold start development models in the event that they do not have enough customer sample data in the early days. For example, a first version of the model is developed according to experience of other services, and then the model is slowly adjusted according to actual conditions; or directly adopting a model provided by an external third party to carry out the business. However, due to the lack of client sample data, the model results based on other previous business experiences are mostly not satisfactory, and in the selection of variables and the setting of parameters, important risk factors are ignored, or the result of the model is poorly adapted to the business due to the too tight or too loose parameter setting, so that unnecessary loss of the actual business is caused. On the other hand, if the model provided by the third-party organization is adopted, the model owned by the third-party organization is deviated from the actual target passenger group of the credit company in most cases, the business requirements of the third-party organization are not necessarily met, and the credit company cannot master the rules and logic contained in the model because the purchased model is a black box, so that the risk of the assets is not easy to analyze and control.
Therefore, when the credit company lacks the client sample data of the small and micro enterprises in the initial stage of the business, how to develop a relatively accurate self model becomes a problem that the credit company needs to solve for risk assessment of the small and micro enterprises, and is also an important basis for credit approval of the small and micro enterprises.
Disclosure of Invention
The invention aims to provide a method and electronic equipment for credit approval of a small and micro enterprise, and solves the problem of how to develop a relatively accurate self-owned model and provide a reference basis for a credit company to reduce the risk of the credit company when the credit company approves the small and micro enterprise.
In order to achieve the above purpose, the invention provides the following technical scheme:
a method for credit approval for a small business, comprising:
performing risk evaluation on data of a plurality of clients through a first model to obtain first evaluation results corresponding to the client data one by one, and generating a risk factor combination of a client group according to all the client data;
fitting to obtain a second model based on the risk factor combination and all the first evaluation results, and adjusting the second model according to the actual business;
and performing risk evaluation on the data of the client by using the second model to obtain a second evaluation result, and judging the credit approval result of the client based on the loan amount of the client and the second evaluation result.
Preferably, the method for performing risk evaluation on data of a plurality of customers through the first model to obtain first evaluation results corresponding to the customer data one by one, and generating the risk factor combination of the customer population includes:
processing the customer data according to the input requirements of the first model;
inputting the processed customer data into a first model to obtain a corresponding first evaluation result, and storing the first evaluation result and the customer data into a first database in a one-to-one correspondence manner;
all combinations of the digitized risk factors associated with the business credit risk are extracted from the customer data.
Specifically, the customer data includes: the system comprises client basic information, tax information, financial information, person credit information and enterprise owner credit information.
Preferably, the method for fitting to obtain the second model based on the risk factor combination and all the first evaluation results comprises:
directly fitting all the first evaluation results and all the risk factors in the risk factor combination by using a fitting algorithm to obtain a second model; or
And fitting any type of risk factors in all the first evaluation results and risk factor combinations by using a fitting algorithm to obtain sub models corresponding to the risk factors one by one, and integrating all the sub models to obtain a second model.
Specifically, the fitting algorithm includes a linear regression algorithm, a logistic regression algorithm, a random forest algorithm, or a neural network.
Further, the method for fitting to obtain the second model based on the risk factor combination and all the first evaluation results further includes:
and obtaining fitting statistic of the second model, comparing the fitting statistic serving as an identifier of the fitting degree of the second model with a preset statistic qualified standard, judging whether the second model is qualified, and if the second model is not qualified, re-fitting by using any fitting algorithm except the currently adopted fitting algorithm to obtain a new second model.
Preferably, the method for adjusting the second model according to the actual service includes:
judging whether any risk factor used when the second model is generated by fitting is suitable for a customer group, and removing the risk factor which is not suitable for the customer group from the second model;
adjusting the weight of any risk factor adopted by the second model according to the actual service;
introducing new customer data sources suitable for customer groups or deleting customer data sources not suitable for customer groups.
Preferably, the method for evaluating the risk of the customer by using the second model to obtain a second evaluation result, selecting a corresponding examination and approval mode based on the loan amount of the customer and the second evaluation result, and judging the credit result comprises the following steps:
cleaning the client data of the client data source, and converting the client data into a format identified by the second model;
accessing the converted customer data to a second model, and performing risk evaluation on the customer by using the second model to obtain a second evaluation result;
comparing the loan amount of the client and the second evaluation result with a preset amount grade and a preset evaluation grade respectively;
automatically determining the credit approval or the non-approval of the credit based on the comparison, or
And judging that manual intervention is needed in the credit approval process according to the comparison result so as to judge the credit approval result.
Preferably, the first evaluation result and the second evaluation result are risk scores and/or default probabilities of customers;
the first model is a client risk assessment model which is designed by a third party introduced by a credit company aiming at the credit approval business of the small and micro enterprise, or the client risk assessment model which is designed by the credit company aiming at the credit approval business of other enterprises except the small and micro enterprise.
An electronic device, the electronic device comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the above-described method for mini-enterprise credit approval.
Compared with the prior art, the method and the electronic equipment for credit approval of the small and micro enterprises provided by the invention have the following beneficial effects:
the invention provides a method for examining and approving the credit of a small and micro enterprise, which is mainly aimed at a credit company which newly develops the credit examination and approval business of the small and micro enterprise (hereinafter, the small and micro credit business for short), firstly carries out risk evaluation on data of a plurality of customers through a first model to obtain first evaluation results which are in one-to-one correspondence with the customer data, utilizes the existing relatively mature first model on the market to cold start the small and micro credit business, and generates a risk factor combination of a customer group according to all the customer data, then, fitting based on the risk factor combination and all the first evaluation results to obtain a second model, reducing the dependence of the wind control of the second model on the first model, and then adjusting the second model according to the actual business based on experience, the characteristics of business customer groups and the problems of the actual business, so that the wind control model which has a good effect and is suitable for the customer groups of the second model, namely the adjusted second model, is quickly built; and finally, performing risk evaluation on the data of the client by using a second model to obtain a second evaluation result, and judging the credit approval result of the client based on the loan amount of the client and the second evaluation result.
The electronic equipment provided by the invention can execute the method for the credit approval of the small and micro enterprises, so that a credit company which newly develops the small and micro credit business can quickly start the new credit business of the small and micro enterprises, develop a relatively accurate self-owned model, provide a reference basis for the credit company to carry out the credit approval on the small and micro enterprises, and make a relatively proper credit approval result so as to reduce the risk of the credit company.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart illustrating a method for credit approval for a small business enterprise according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating a relationship between customer data and risk factor combinations according to an embodiment of the present invention;
fig. 3 is a schematic block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. 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 invention.
Example one
Referring to fig. 1, the method for credit approval of a small enterprise provided by the embodiment includes:
performing risk evaluation on data of a plurality of clients through a first model to obtain first evaluation results corresponding to the client data one by one, and generating a risk factor combination of a client group according to all the client data;
fitting to obtain a second model based on the risk factor combination and all the first evaluation results, and adjusting the second model according to the actual business;
and performing risk evaluation on the data of the client by using the second model to obtain a second evaluation result, and judging the credit approval result of the client based on the loan amount of the client and the second evaluation result.
The first model is a client risk assessment model which is designed by a third party introduced by a credit company aiming at the credit approval business of the small and micro enterprise, or the client risk assessment model which is designed by the credit company aiming at the credit approval business of other enterprises except the small and micro enterprise; the first evaluation result and the second evaluation result are risk scores and/or default probabilities of the customers.
The method for examining and approving the credit of the small and micro enterprise provided by the embodiment of the invention is mainly used for a credit company which newly develops the credit examination and approval business of the small and micro enterprise (hereinafter referred to as the small and micro credit business), firstly, the small and micro credit business is cold started by utilizing a first relatively mature model existing in the market, performing risk evaluation on data of a plurality of clients to obtain first evaluation results corresponding to the client data one by one, generating risk factor combinations of client groups according to all the client data, then, fitting based on the risk factor combination and all the first evaluation results to obtain a second model, reducing the dependence of the wind control of the second model on the first model, and then adjusting the second model according to the actual business based on experience, the characteristics of business customer groups and the problems of the actual business, so that the wind control model which has a good effect and is suitable for the customer groups of the second model, namely the adjusted second model, is quickly built; and finally, performing risk evaluation on the data of the client by using a second model to obtain a second evaluation result, and judging the credit approval result of the client based on the credit limit of the client and the second evaluation result, so that a credit company which newly develops the small and micro credit business can quickly start the small and micro enterprise credit new business, develop a more accurate self-owned model, provide a reference basis for the credit company to perform credit approval on the small and micro enterprise, and make a more appropriate credit approval result so as to reduce the risk of the credit company.
In the method for credit approval of the small and micro enterprises provided by the embodiment of the invention, risk evaluation is carried out on data of a plurality of customers through a first model to obtain first evaluation results corresponding to the customer data one by one, and the method for generating the risk factor combination of the customer group comprises the following steps:
processing the customer data according to the input requirements of the first model;
inputting the processed customer data into a first model to obtain a corresponding first evaluation result, and storing the first evaluation result and the customer data into a first database in a one-to-one correspondence manner;
all combinations of the digitized risk factors associated with the business credit risk are extracted from the customer data.
For a credit company which newly develops a credit approval business of a small and micro enterprise (hereinafter referred to as a small and micro credit business), because the same kind of business is not developed before and the data base of customers of the small and micro enterprise is not provided, a relatively mature first model can be accessed to start a new business for insurance, namely, the customer data is accessed to the first model according to the data format requirement of the first model. The first model is selected from a mature model that has passed market examination in the market. Because the mature first model is actually tested, the problem of large risk can not occur, and the risk is convenient to control. Corresponding business processes, policies and databases can be built while the business is developed, and preparation is made for the development of the credit business with larger scale and higher efficiency.
In one embodiment, referring to FIG. 2, the customer data sources include data collected by the credit company itself or accumulated by other businesses, data purchased from outside, data collected by people, and data that the customer needs to provide. The client data content includes: client basic information, tax information, financial information, person credit information, enterprise owner credit information and the like. The method has the advantages that the problems encountered in actual business or embodied risk characteristics need to be collected while customer data are collected, the risk characteristics can generally reflect business characteristics of a company aiming at customer groups, and later-stage adjustment of a second model is facilitated, so that the model can grasp the risk characteristics of the customer groups more easily and is closer to the customers. Meanwhile, by combining experience and problems found in actual business, corresponding risk factor combinations, namely all combinations of the digitalized risk factors related to the enterprise credit risk, are designed aiming at the risk of the small and micro enterprises according to the customer data. These risk factors are all embodied in finance, credit investigation, credit history, tax, business owners, etc.
Further, in the method for credit approval of a small enterprise provided by the embodiment of the present invention, the method for obtaining the second model based on the risk factor combination and all the first evaluation results includes:
directly fitting all the first evaluation results and all the risk factors in the risk factor combination by using a fitting algorithm to obtain a second model; or fitting any risk factor in all the first evaluation results and risk factor combinations by using a fitting algorithm to obtain sub-models corresponding to the risk factors one by one, and integrating all the sub-models to obtain a second model. The fitting algorithm comprises a linear regression algorithm, a logistic regression algorithm, a random forest algorithm or a neural network.
Taking linear regression as an example, it is specifically shown how to use the risk factor combination designed in the previous step to perform fitting for the first evaluation result, and one is to use a fitting algorithm to directly fit all the first evaluation results and all the risk factors in the risk factor combination to obtain a second model. Alternatively, risk factor combinations for the small micro enterprise credit business are classified, and block fitting is performed for each type of risk factor, such as: fitting a sub-model for the financial risk factors, fitting a sub-model for the credit risk factors, fitting a sub-model for the enterprise owner personal information risk factors, and integrating the sub-models together to form the whole second model.
And after the second model is obtained through fitting, obtaining fitting statistic of the second model, comparing the fitting statistic serving as an identifier of the fitting degree of the second model with a preset statistic qualified standard, judging whether the second model is qualified, and if the second model is not qualified, re-fitting by using any fitting algorithm except the currently adopted fitting algorithm to obtain a new second model.
The magnitude of the second model fit is represented by the statistics of the model fit, which may determine coefficients for R2. R2 determines the coefficient to measure the fitting degree of the regression equation as a whole, expresses the overall relation between the dependent variable and all independent variables (namely the overall relation between the evaluation result and the risk factor combination), has the value equal to the ratio of the regression square sum in the total square sum, and has the value between 0 and 1, and the closer the value is to 1, the better the fitting result is. The associated formula is as follows:
where y represents the actual value of the sample (i.e. the first model evaluation),
representing the predicted value of the sample (i.e. the second model evaluation),
the average of the samples is indicated.
Meanwhile, the influence of each risk factor on the third-party model can be analyzed through the P value of the variable coefficient significance test in variable fitting, and the higher the P value is, the higher the significance of the variable is, and the larger the influence on the third-party model is. The significance test is a method for detecting whether a difference exists between an experimental group (evaluated by using a second model) and a control group (evaluated by using a first model) in a scientific experiment and whether the difference is significant. For a specific risk factor, it is verified by the t-statistic whether the risk factor has a significant relationship with the observed actual result, which is the output result of the first model. For the risk factor and the first model result, constructing a corresponding statistic t:
where α is the coefficient of the regression result of the risk factor, n is the number of samples of the risk factor, i is the counting variable of the samples of the risk factor, Σ ei2 is the sum of the squares of the residuals of the predicted value and the actual value, Σ xi 2Is the sum of the squares of the risk factor sample values. The P value is the value corresponding to the t statistic under the t distribution in n-2 degrees of freedom.
It can be set that the second model is approved to be qualified when R2 is greater than 0.7 and P is greater than 2.9, if not, any fitting algorithm except the currently adopted fitting algorithm is used for re-fitting to obtain a new second model, whether the second model is qualified or not is evaluated again, or several fitting algorithms are combined for re-fitting to obtain a new second model, or parameters of the second model are fine-tuned based on the evaluation result of the second model until the obtained second model is qualified, namely the obtained second model is as close to the first model as possible.
In the method for credit approval of a small and micro enterprise provided by the embodiment of the invention, after the second model is obtained, the method for adjusting the second model according to actual business comprises the following steps:
judging whether any risk factor used when the second model is generated by fitting is suitable for a customer group, and removing the risk factor which is not suitable for the customer group from the second model;
adjusting the weight of any risk factor adopted by the second model according to the actual service;
introducing new customer data sources suitable for customer groups or deleting customer data sources not suitable for customer groups.
Since the first model is a model developed by a third party based on its available customer data and services, or a model developed by a credit company based on its original services and customer base, such a model is not necessarily suitable for the credit company's own small micro-enterprise customer base. Therefore, it is necessary to analyze the risk factors used in performing the second model fitting, and to analyze whether these risk factors are suitable for the credit company's own passenger group from data or experience.
First, it is determined from the data whether any risk factor is retained by correlating the risk factor with the third-party model results (KS value/AR value of univariate). For example: whether the variables correspond to KS greater than 0.05 or the corresponding AR value greater than 0.05. If the KS value is less than 0.05 or the AR value is less than 0.05, such variables are discarded. It should be clear to those skilled in the art that KS and AR values are common statistics in statistics and are not described here.
The risk factors selected by the second model can also be adjusted empirically, and if the corresponding risk factors are judged from actual business experience to be obviously unsuitable for the credit company passenger groups, the indexes have certain fitting effect but should be abandoned. If it is empirically determined that a risk factor is an important parameter for its own customer group, the effect of the risk factor fitting may not be good, and should be preserved. The experience here can be judged by combining multiple experts in the credit company, and a few principles subject to the majority are selected.
After the risk factors of the unsuitable second model are adjusted, the second model needs to be adjusted according to experience of the small micro enterprise credit business. The method mainly comprises the following steps: A. whether risk factors targeted to the credit company's own guest group are taken into consideration or not; B. whether the risk factor weight taken into account is too large or too small; C. whether there is a new data source on the market that is helpful for credit company's own crowd risk judgment.
Firstly, after the preliminary fitting is finished to obtain a second model, the risk factors selected by the second model need to be examined, and whether the risk factors with the targeted characteristics of the credit company passenger groups are considered or not is checked. Risk factors for targeted features of a guest group include: regional risk factors (such as a certain province city), scale risk factors (such as annual sales of more than 100 ten thousand), industrial risk factors (such as manufacturing industry and wholesale retail industry), and risk factors related to profitability (such as whether the profit exceeds a certain threshold), and whether the risk factors with targeted characteristics are adopted in the second model is checked. The second model is then adapted to the risk factors of the target features not taken into account in a manner such that the risk factors of the target features are effective in the second model.
The weights assigned to the risk factors selected for use in the second model also need to be adjusted. Because the second model is obtained by fitting based on the risk factors embodied by the client group in the past period of the credit company and the first evaluation result, the weight given to the selected risk factor can be judged whether the weight is too large or too small based on expert experience, and the expert can be an expert of the micro-credit in the credit company. If the weight is found to be too large, the adjustment is made downward, and if the weight is too small, the adjustment is made upward.
In addition, whether a new data source which is helpful for the risk judgment of the passenger group is available on the market is detected. If there is a new data source on the market and the small micro business credit judgment is critical, then the second model needs to be purchased and adjusted using that data source. Based on the data of the new data source, the criteria for rejecting the customer are reset, and the original credit policy is adjusted to allow the new data source to be taken into account.
After the second model is adjusted, the second model is used for carrying out risk evaluation on the client to obtain a second evaluation result, and a corresponding examination and approval mode is selected based on the loan amount of the client and the second evaluation result so as to judge the credit result, wherein the method comprises the following steps:
cleaning the client data of the client data source, and converting the client data into a format identified by the second model;
accessing the converted customer data to a second model, and performing risk evaluation on the customer by using the second model to obtain a second evaluation result;
comparing the loan amount of the client and the second evaluation result with a preset amount grade and a preset evaluation grade respectively;
and automatically judging whether the credit examination and approval is passed or not according to the comparison result, or judging that the credit examination and approval process needs manual intervention according to the comparison result so as to judge the credit examination and approval result.
Before a credit company develops a mini credit business, a corresponding business process needs to be set for a target customer group of the credit company. The small and micro products are mainly online credit business, and the approval standard is set based on the loan amount of the online business and the second evaluation result, and the approval standard comprises the following steps: the credit business automatically approves the upper limit of the limit, the lower limit of the automatically rejected limit, the limit interval needing manual approval, the evaluation threshold value passing the automatic approval during the automatic approval, the evaluation threshold value automatically rejected and the evaluation threshold interval needing manual approval, and the credit approval result is judged by referring to a second evaluation result in the manual approval process. For example:
setting the upper limit of the automatically approved limit of the credit business to be 30 ten thousand, the lower limit of the automatically rejected limit to be 100 ten thousand, and the limit interval needing manual approval to be 30-100 ten thousand, firstly entering a corresponding approval process according to the loan limit of a client; taking the second evaluation result as an example of violation, the upper evaluation threshold passed by automatic approval in the automatic approval process can be set to be 2%, the lower evaluation threshold rejected automatically can be set to be 5%, and the interval of the evaluation threshold needing to be manually approved is 2% -5%. In the specific implementation process, the client can be prompted to apply again after adding the mortgage information besides automatically rejecting the credit loan application with the predicted default probability of more than 5%.
Before the business is developed, a second model developer accesses a related customer data source into the second model in advance, and configures an approval system according to approval standards to complete a corresponding requirement document. In addition, when the mini-mini credit business is developed by using the first model or the second model, the data generated in the mini-mini credit business, including the original data, the intermediate data and the result data, are stored in the tribal library to prepare for the fitting of a new model later, so that the obtained risk assessment model is more suitable for the passenger groups and businesses of credit companies.
In the specific implementation process, after the mini credit business is carried out by using the second model, various problems may also occur in the actual operation of the business and need to be correspondingly adjusted, for example, an adjustment method for a problem occurring in customer data introduced from the outside: if the data content and format of the client data introduced from the outside are changed, the format is adjusted according to the risk factor with changed format to ensure that the data format is consistent, and the corresponding coefficient is adjusted according to the risk factor with changed content. If the format change is too large, the operation of early warning and credit level adjustment is required to be performed for the client, and the operation of tightening the model or suspending the credit approval business of the client is also required to be comprehensively checked. The adjusting method aiming at the problem of the accuracy of the client data comprises the following steps: the accuracy threshold of the customer data can be set to 25%, and if the data is wrong and exceeds 25%, the credit level of the customer is adjusted downwards or an early warning is given. Aiming at the problem of data defect, the method comprises the following steps: the threshold value of the missing degree of the customer data can be set to be 25%, and when the customer data is more than 25% missing, an early warning signal is provided or the credit level of the customer is adjusted downwards. The adjustment method of the data authenticity problem is that: if the data authenticity is in problem, checking whether a risk factor of which the authenticity is in problem is a key variable, and if the risk factor is a non-key variable, adjusting the credit level of the client down or adjusting the coefficient of the risk factor tightly; if the variable is a key variable, immediately giving an early warning and stopping the examination and approval business of the client to carry out comprehensive inspection. Adjustment methods for problems with new bad (overdue) customer characteristics: if most newly-occurring bad (overdue) customers have a certain common characteristic, adjusting the second model according to the common characteristic, for example, if most newly-occurring bad (overdue) customers come from the same province or county, adjusting the credit rating of all the customers in the province or county as a whole, or stopping the tiny credit approval business in the region; if most newly-occurring bad (overdue) customers occur in a particular industry, the credit levels of all the customers in the industry are adjusted downwards or the minor credit approval business of the industry is stopped; if most newly occurring bad (overdue) customers occur in a particular channel, then the credit levels of all customers entering the system from that channel are adjusted downward or the mini-mini credit approval business of that channel is stopped; if a financial index of most newly occurring bad (overdue) customers is problematic, the coefficients of risk factors associated with the financial index are tightened.
The method for the credit approval of the small and micro enterprise provided by the embodiment of the invention enables a credit company which newly develops the small and micro credit business to quickly start the new credit business of the small and micro enterprise, develops a relatively accurate self-owned model, provides a reference basis for the credit company to carry out the credit approval on the small and micro enterprise, makes a relatively proper credit approval result, and can adjust the wind control model in time according to problems occurring in the actual business so as to reduce the risk of the credit company.
Example two
An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for mini-enterprise credit approval of the first embodiment.
Referring now to FIG. 3, shown is a schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 3, the electronic device may include a processing apparatus (e.g., a central processing unit, a graphic processor, etc.) that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) or a program loaded from a storage apparatus into a Random Access Memory (RAM). In the RAM, various programs and data necessary for the operation of the electronic apparatus are also stored. The processing device, the ROM, and the RAM are connected to each other by a bus. An input/output (I/O) interface is also connected to the bus.
Generally, the following systems may be connected to the I/O interface: input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, and the like; output devices including, for example, Liquid Crystal Displays (LCDs), speakers, vibrators, and the like; storage devices including, for example, magnetic tape, hard disk, etc.; and a communication device. The communication means may allow the electronic device to communicate wirelessly or by wire with other devices to exchange data. While the figures illustrate an electronic device with various systems, it is to be understood that not all illustrated systems are required to be implemented or provided. More or fewer systems may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means, or installed from a storage means, or installed from a ROM. The computer program, when executed by a processing device, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
By executing the method for credit approval of the small and micro enterprise in the first embodiment, the electronic device provided by the invention enables a credit company newly developing the small and micro credit business to quickly start the new credit business of the small and micro enterprise, develops a relatively accurate self-owned model, provides a reference basis for the credit company to carry out credit approval on the small and micro enterprise, makes a relatively proper credit approval result, and can timely adjust the wind control model according to problems occurring in actual business so as to reduce the risk of the credit company. Compared with the prior art, the electronic device provided by the embodiment of the invention has the same beneficial effect as the method for credit approval of the small and micro enterprise provided by the first embodiment, and other technical features of the electronic device are the same as those disclosed in the method of the previous embodiment, which are not repeated herein.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring at least two internet protocol addresses; sending a node evaluation request comprising the at least two internet protocol addresses to node evaluation equipment, wherein the node evaluation equipment selects the internet protocol addresses from the at least two internet protocol addresses and returns the internet protocol addresses; receiving an internet protocol address returned by the node evaluation equipment; wherein the obtained internet protocol address indicates an edge node in the content distribution network.
Alternatively, the computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: receiving a node evaluation request comprising at least two internet protocol addresses; selecting an internet protocol address from the at least two internet protocol addresses; returning the selected internet protocol address; wherein the received internet protocol address indicates an edge node in the content distribution network.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Wherein the name of a module in some cases does not constitute a limitation on the module itself.
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the foregoing description of embodiments, the particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A method for credit approval for a small business, comprising:
performing risk evaluation on data of a plurality of clients through a first model to obtain first evaluation results corresponding to the client data one by one, and generating a risk factor combination of a client group according to all the client data;
fitting to obtain a second model based on the risk factor combination and all the first evaluation results, and adjusting the second model according to the actual business;
and performing risk evaluation on the data of the client by using the second model to obtain a second evaluation result, and judging the credit approval result of the client based on the loan amount of the client and the second evaluation result.
2. The method for credit approval of a small business enterprise according to claim 1, wherein the risk evaluation of the data of a plurality of customers is performed through the first model, a first evaluation result corresponding to the customer data in a one-to-one manner is obtained, and the method for generating the risk factor combination of the customer group comprises the following steps:
processing the customer data according to the input requirements of the first model;
inputting the processed customer data into a first model to obtain a corresponding first evaluation result, and storing the first evaluation result and the customer data into a first database in a one-to-one correspondence manner;
all combinations of the digitized risk factors associated with the business credit risk are extracted from the customer data.
3. The method for mini-enterprise credit approval of claim 1 or 2, wherein the customer data comprises: the system comprises client basic information, tax information, financial information, person credit information and enterprise owner credit information.
4. The method for credit approval of a small business as claimed in claim 1 or 2 wherein the method of fitting to derive the second model based on the combination of risk factors and all of the first evaluation results comprises:
directly fitting all the first evaluation results and all the risk factors in the risk factor combination by using a fitting algorithm to obtain a second model; or
And fitting any type of risk factors in all the first evaluation results and risk factor combinations by using a fitting algorithm to obtain sub models corresponding to the risk factors one by one, and integrating all the sub models to obtain a second model.
5. The method for mini-micro enterprise credit approval of claim 4, wherein the fitting algorithm comprises a linear regression algorithm, a logistic regression algorithm, a random forest algorithm, or a neural network.
6. The method for mini-enterprise credit approval of claim 5, wherein the method of fitting a second model based on the combination of risk factors and all first evaluation results further comprises:
and obtaining fitting statistic of the second model, comparing the fitting statistic serving as an identifier of the fitting degree of the second model with a preset statistic qualified standard, judging whether the second model is qualified, and if the second model is not qualified, re-fitting by using any fitting algorithm except the currently adopted fitting algorithm to obtain a new second model.
7. The method for mini-enterprise credit approval of claim 5 or 6, wherein the method of adjusting the second model as a function of actual business comprises:
judging whether any risk factor used when the second model is generated by fitting is suitable for a customer group, and removing the risk factor which is not suitable for the customer group from the second model;
adjusting the weight of any risk factor adopted by the second model according to the actual service;
introducing new customer data sources suitable for customer groups or deleting customer data sources not suitable for customer groups.
8. The method for credit approval of a small business enterprise of claim 7, wherein the risk evaluation of the client using the second model is performed to obtain a second evaluation result, and the method for determining the credit result by selecting the corresponding approval mode based on the loan line of the client and the second evaluation result comprises:
cleaning the client data of the client data source, and converting the client data into a format identified by the second model;
accessing the converted customer data to a second model, and performing risk evaluation on the customer by using the second model to obtain a second evaluation result;
comparing the loan amount of the client and the second evaluation result with a preset amount grade and a preset evaluation grade respectively;
automatically determining the credit approval or the non-approval of the credit based on the comparison, or
And judging that manual intervention is needed in the credit approval process according to the comparison result so as to judge the credit approval result.
9. The method for mini-enterprise credit approval of claim 8, wherein the first and second evaluations are a risk score and/or a probability of breach of the customer;
the first model is a client risk assessment model which is designed by a third party introduced by a credit company aiming at the credit approval business of the small and micro enterprise, or the client risk assessment model which is designed by the credit company aiming at the credit approval business of other enterprises except the small and micro enterprise.
10. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for mini-enterprise credit approval of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010767315.4A CN112037007A (en) | 2020-08-03 | 2020-08-03 | Credit approval method for small and micro enterprises and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010767315.4A CN112037007A (en) | 2020-08-03 | 2020-08-03 | Credit approval method for small and micro enterprises and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112037007A true CN112037007A (en) | 2020-12-04 |
Family
ID=73583769
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010767315.4A Pending CN112037007A (en) | 2020-08-03 | 2020-08-03 | Credit approval method for small and micro enterprises and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112037007A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112634023A (en) * | 2020-12-28 | 2021-04-09 | 四川新网银行股份有限公司 | Early warning system and method for group risk monitoring |
| CN112862594A (en) * | 2021-02-01 | 2021-05-28 | 深圳无域科技技术有限公司 | Financial risk control method, system, device and computer readable medium |
| CN112990311A (en) * | 2021-03-15 | 2021-06-18 | 中国建设银行股份有限公司 | Method and device for identifying admitted client |
| CN116416054A (en) * | 2023-04-03 | 2023-07-11 | 东方微银科技股份有限公司 | Small micro credit business admittance optimization method and system based on risk management |
| CN116823163A (en) * | 2023-06-28 | 2023-09-29 | 北银消费金融有限公司 | Flow approval method, device, computer equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109727120A (en) * | 2018-12-14 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Test method and device, storage medium, the computer equipment of risk evaluation model |
| CN110335143A (en) * | 2019-07-02 | 2019-10-15 | 上海淇毓信息科技有限公司 | Financial Risk Analysis method, apparatus and electronic equipment based on multiple temporal verifying |
-
2020
- 2020-08-03 CN CN202010767315.4A patent/CN112037007A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109727120A (en) * | 2018-12-14 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Test method and device, storage medium, the computer equipment of risk evaluation model |
| CN110335143A (en) * | 2019-07-02 | 2019-10-15 | 上海淇毓信息科技有限公司 | Financial Risk Analysis method, apparatus and electronic equipment based on multiple temporal verifying |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112634023A (en) * | 2020-12-28 | 2021-04-09 | 四川新网银行股份有限公司 | Early warning system and method for group risk monitoring |
| CN112862594A (en) * | 2021-02-01 | 2021-05-28 | 深圳无域科技技术有限公司 | Financial risk control method, system, device and computer readable medium |
| CN112990311A (en) * | 2021-03-15 | 2021-06-18 | 中国建设银行股份有限公司 | Method and device for identifying admitted client |
| CN116416054A (en) * | 2023-04-03 | 2023-07-11 | 东方微银科技股份有限公司 | Small micro credit business admittance optimization method and system based on risk management |
| CN116823163A (en) * | 2023-06-28 | 2023-09-29 | 北银消费金融有限公司 | Flow approval method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112037007A (en) | Credit approval method for small and micro enterprises and electronic equipment | |
| CN108876188B (en) | Inter-connected service provider risk assessment method and device | |
| CN110738527A (en) | feature importance ranking method, device, equipment and storage medium | |
| CN113837596B (en) | Fault determination method and device, electronic equipment and storage medium | |
| CN110929799A (en) | Method, electronic device, and computer-readable medium for detecting abnormal user | |
| CN110688536A (en) | Label prediction method, device, equipment and storage medium | |
| CN114004700A (en) | Service data processing method and device, electronic equipment and storage medium | |
| CN111966915A (en) | Information inspection method, computer equipment and storage medium | |
| CN111563673A (en) | Computer technology digitization degree evaluation method and device | |
| CN111626855A (en) | Bond credit interest difference prediction method and system | |
| CN111210332A (en) | Method and device for generating post-loan management strategy and electronic equipment | |
| CN112950359A (en) | User identification method and device | |
| CN116416052A (en) | Trusted method and device for specific user, electronic equipment and storage medium | |
| US20230130550A1 (en) | Methods and systems for providing automated predictive analysis | |
| CN111815435A (en) | Visualization method, device, equipment and storage medium for group risk characteristics | |
| CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
| CN115994819A (en) | Risk customer identification method, apparatus, device and medium | |
| WO2022022572A1 (en) | Calculating developer time during development process | |
| CN114782170A (en) | Method, apparatus, device and medium for evaluating model risk level | |
| CN115204733A (en) | Data auditing method and device, electronic equipment and storage medium | |
| CN115048561A (en) | Recommendation information determination method and device, electronic equipment and readable storage medium | |
| CN113129127A (en) | Early warning method and device | |
| CN110163706B (en) | Method and device for generating information | |
| CN112732272A (en) | Application program publishing method and device | |
| CN115409636A (en) | Product risk prediction method, device, equipment and medium |
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: 20201204 |