CN112053231A - Loan application processing method and device - Google Patents
Loan application processing method and device Download PDFInfo
- Publication number
- CN112053231A CN112053231A CN202010915724.4A CN202010915724A CN112053231A CN 112053231 A CN112053231 A CN 112053231A CN 202010915724 A CN202010915724 A CN 202010915724A CN 112053231 A CN112053231 A CN 112053231A
- Authority
- CN
- China
- Prior art keywords
- loan
- auditing
- loan application
- data
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a processing method and a device of loan application, wherein the method comprises the following steps: when a loan application is received, obtaining multi-dimensional information of a loan application party; inputting the multi-dimensional information into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant; and the loan auditing model is generated by pre-training according to historical multi-dimensional information samples of a plurality of loan application parties. The invention can ensure the accuracy of loan application processing when an emergency abnormal event occurs.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a loan application processing method and device.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
Currently, bank loan such as credit auditing is mainly based on the profit capacity of enterprises, however, the mode is not applicable when the whole social economy is affected due to sudden abnormal events such as social encounters with sudden public crisis. When the social economy is affected as a whole due to sudden public crisis, the overall operation activities of the enterprise can be seriously affected, and at the moment, the enterprise often urgently needs external financing to get through the crisis. However, the crisis causes the data reflecting the operational capacity to have a great influence, which leads to low accuracy of credit review processing under the conventional loan review scheme, and the enterprises cannot obtain the loan, thereby possibly causing a great social problem.
Disclosure of Invention
The embodiment of the invention provides a processing method of loan application, which is used for ensuring the processing accuracy of the loan application when an emergency abnormal event occurs, and comprises the following steps:
when a loan application is received, obtaining multi-dimensional information of a loan application party;
inputting the multi-dimensional information into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant; and the loan auditing model is generated by pre-training according to historical multi-dimensional information samples of a plurality of loan application parties.
The embodiment of the invention also provides a processing device for loan application, which is used for ensuring the processing accuracy of the loan application when an emergency abnormal event occurs, and the device comprises:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring multi-dimensional information of a loan application party when receiving a loan application;
the auditing unit is used for inputting the multi-dimensional information into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant; and the loan auditing model is generated by pre-training according to historical multi-dimensional information samples of a plurality of loan application parties.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the processing method of the loan application when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program for executing the processing method of the loan application is stored in the computer-readable storage medium.
In the embodiment of the invention, compared with the technical scheme that loan application processing is carried out only by depending on the profitability of enterprises in the prior art, and when the society is influenced by sudden public crisis, the processing accuracy of loan application is low, the processing scheme of loan application in the embodiment of the invention comprises the following steps: when a loan application is received, obtaining multi-dimensional information of a loan application party; inputting the multi-dimensional information into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant; the loan auditing model is generated by pre-training according to historical multi-dimensional information samples of a plurality of loan application parties, and can ensure the accuracy of loan application processing when an emergency abnormal event occurs.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
FIG. 1 is a flow chart illustrating a method for processing a loan application according to an embodiment of the invention;
FIG. 2 is a schematic diagram illustrating the processing of a loan application in an embodiment of the invention;
FIG. 3 is a flow chart illustrating a method for processing a loan application according to another embodiment of the invention;
FIG. 4 is a schematic diagram of the processing apparatus for loan application according to the embodiment of the invention;
fig. 5 is a schematic structural diagram of a processing device for loan application according to another embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
The inventor finds that the technical problems of the existing loan application processing scheme are as follows:
1) existing solutions focus primarily on profitability data of the enterprise, such as cash flow, equity, profits, pipelining, etc. information. However, under the influence of a serious crisis, the normal production operation of an enterprise has been greatly influenced, and the profitability has also been greatly influenced. The original loan audit scheme can not help the bank accurately complete the loan audit, which leads to the accumulation of funds in the bank system and difficult to flow into the physical economy.
2) The influence of crisis on the macroscopic economy and the industry where enterprises are located is not considered in the existing scheme.
3) The existing loan scheme does not fully consider the influence of an enterprise manager on loan audit, and may ignore the influence of the operation management capability and social relationship of the enterprise manager on the profit capability of the enterprise.
4) The existing scheme has less limitation to the situation that the low interest loan is not used.
In view of the technical problems, the invention provides a processing scheme of loan application, which is a loan auditing scheme under crisis, the scheme utilizes multi-dimensional information such as macroscopic economic data, industrial data, enterprise manager data and the like under crisis to automatically complete loan auditing, and the whole process comprehensively considers various factors, so that the loan auditing result in crisis is more accurate. Specifically, the method comprises the following steps:
1) according to the scheme, data reflecting the social value of the enterprise is added in loan audit, the social value and the future expected profitability of the enterprise are comprehensively considered, the influence of the profitability on the loan audit result is properly weakened, and finally a loan audit conclusion is comprehensively made by combining the social value and the profitability of the enterprise.
2) According to the scheme, macroscopic economic information and industry information of enterprises are added in loan auditing, and the influence degree of crisis on the society and the whole industry is measured by using the macroscopic economic information and the industry information.
3) The scheme adds data such as enterprise manager assets, stream, social relations and the like to measure the influence of the management ability of the enterprise manager on the profitability of the enterprise.
4) According to the scheme, credit information of enterprise managers, enterprise tax payment and the like is added to measure the risk of appropriating the loan.
The processing scheme of the loan application is described in detail below.
Fig. 1 is a schematic flow chart of a processing method of a loan application in an embodiment of the invention, as shown in fig. 1, the method includes the following steps:
step 101: when a loan application is received, obtaining multi-dimensional information of a loan application party;
step 103: inputting the multi-dimensional information into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant; and the loan auditing model is generated by pre-training according to historical multi-dimensional information samples of a plurality of loan application parties.
The processing method of the loan application provided by the embodiment of the invention can ensure the accuracy of loan application processing when an emergency abnormal event occurs.
The following describes in detail the steps involved in the method for processing a loan application according to an embodiment of the present invention.
Firstly, a step of generating a loan auditing model by pre-training is introduced.
In one embodiment, the processing method of the loan application may further include: obtaining a loan auditing model generated by pre-training according to the following method:
obtaining historical multi-dimensional information sample data of a plurality of loan application parties; the sample data comprises positive sample data and negative sample data, wherein the positive sample data is data which meets the loan auditing requirement, and the negative sample data is data which does not meet the loan auditing requirement;
dividing the sample data into a training set and a test set;
training a deep neural network model by using the training set;
testing the trained deep neural network model by using the test set;
and obtaining the loan auditing model generated by the pre-training according to the test result.
In specific implementation, the loan audit model with accurate audit result is obtained through the steps of obtaining the loan audit model generated by pre-training, and the accuracy of loan application processing is further ensured when the model is subsequently used for loan audit.
In particular, the loan audit model may be a deep learning neural network model, where the input is multidimensional information of a loan applicant (e.g., a business), and the output is a result of the loan audit, such as approval or non-approval.
The embodiment of the invention provides a loan auditing scheme under crisis, which mainly utilizes multi-dimensional information such as macroscopic economic data, industrial data, enterprise manager data and the like under crisis and utilizes a data analysis model (loan auditing model) to research an enterprise loan auditing mechanism under crisis, such as epidemic situations, and can automatically complete accurate auditing of loan objects. As shown in fig. 2, the step of pre-training the generated loan audit model (i.e. the data analysis model in fig. 2) in the embodiment of the present invention mainly includes:
1. and (6) data acquisition and labeling.
In one embodiment, the multi-dimensional information may include: macro economic data, industry data, enterprise data, and enterprise manager data.
In specific implementation, the multidimensional information may include: the macroscopic economic data, the industrial data, the enterprise data and the enterprise manager data further ensure the accuracy of loan application processing.
The embodiment of the invention collects macroscopic economic data, industrial data, enterprise data and enterprise manager data to construct a basic data set.
1) And macroscopic economic data comprises data such as resident consumption information, resident deposit information, market information based on stocks and debts and the like.
Constructing new characteristics according to the resident consumption information to reflect the change conditions of consumption intentions, such as the change quantity, the change proportion and the change direction of the consumption amount; according to the deposit information construction characteristics of residents, the future economic expectation of the residents is reflected, such as the increase of the total sum of deposit, the acceleration and the like; and constructing new characteristics such as equity-based redemption rate, yield rate, total market value, market value change rate and the like according to equity-based market information. The influence degree of the crisis on the macroscopic economy, the influence degree of the crisis on the confidence of residents and the influence degree of the crisis on the market liquidity are reflected through the characteristics.
2) The industry data comprises the industry to which the enterprise belongs, the total number of the industry enterprises, industry market value information, policy support information, industry upstream and downstream industry market value information and the like.
And constructing new characteristics according to data such as the industry to which the enterprise belongs, the total number of industry and enterprises, industry market value information, policy support information, industry upstream and downstream industry market value information and the like, and reflecting the integral influence of the crisis on the industry to which the enterprise belongs and the importance of the industry to economy.
3) Enterprise data, wherein the enterprise data characteristic engineering is divided into 2 parts, and the first part reflects the social value and the industrial value of an enterprise according to the upstream and downstream supply chain information of the enterprise, the market value information of the enterprise, the employee information of the enterprise, the tax payment information of the enterprise and the payment information of five risks and one fund of the enterprise; and the second part performs characteristic engineering on enterprise product production region information, enterprise product sales region information, enterprise product consumption scene information, enterprise product consumption group information, past enterprise production sales information, enterprise flow information, enterprise cash flow information, past enterprise profit and loan repayment information and reflects future expected profit capacity and continuous profit capacity of the enterprise.
4) The enterprise manager data is divided into 3 parts, including credit information of enterprise managers, asset information of enterprise managers and basic information of enterprise managers.
The first part is to carry out characteristic engineering on data such as credit information of an enterprise manager, consumption record information of the enterprise manager, loan and loan information of the enterprise manager, loan use information of the enterprise manager and the like, reflect credit information of the enterprise manager, and measure the possibility of using funds by enterprise legal persons by using the information; the second part is that characteristic engineering is carried out on data such as asset liability information, capital flow information, investment information and the like of an enterprise manager to reflect the management capability of the enterprise manager, such as new characteristics of construction of annual capital value-added rate, investment return rate, annual asset allocation proportion and the like, and the data is utilized to measure the operation management capability of enterprise legal persons, so as to be used for evaluating the influence on the future profitability of the enterprise; and the third part is to perform characteristic engineering on data of the enterprise manager academic calendar, the graduate colleges and households, reflect the social relationship information of the enterprise manager and evaluate the influence of the social relationship on enterprise operation.
The invention integrates the social value of the enterprise, the future profitability of the enterprise, the influence degree of the enterprise, the urgency of the loan demand of the enterprise, the management ability of the corporate legal person and the credit information of the corporate legal person, and finally gives a loan auditing result.
2. And (4) data association division. And (3) integrating the data obtained in the step (1), and associating the data according to the target requirements and the main keys provided by different data sources. The current association key is an enterprise ID and an enterprise manager ID.
3. And (4) preprocessing data. And (3) performing abnormal value cleaning, vacancy value filling, data vectorization and other work on the well-correlated data in the step (2), and improving the data quality.
4. And (5) model feature engineering and training. Respectively carrying out feature engineering operation on macroscopic economic data, industrial data, enterprise data and enterprise supervisor data to generate derivative features, and further mining implicit information in the data:
1) macroscopic economic data, new characteristics are constructed according to resident consumption information to reflect consumption intention change conditions, such as consumption amount change quantity, change proportion and change direction; according to the deposit information construction characteristics of residents, the future economic expectation of the residents is reflected, such as the increase of the total sum of deposit, the acceleration and the like; and constructing new characteristics such as equity-based redemption rate, yield rate, total market value, market value change rate and the like according to equity-based market information. The influence degree of the crisis on the macroscopic economy, the influence degree of the crisis on the confidence of residents and the influence degree of the crisis on the market liquidity are reflected through the characteristics.
2) And the industry data constructs new characteristics according to the data such as the industry to which the enterprise belongs, the total number of the industry and the enterprise, the market value information of the industry, the policy support information, the industry upstream and downstream industry market value information of the industry and the like, and reflects the integral influence of the crisis on the industry to which the enterprise belongs and the importance of the industry to the economy.
3) Enterprise data, wherein the enterprise data characteristic engineering is divided into 2 parts, and the first part reflects the social value and the industrial value of an enterprise according to the upstream and downstream supply chain information of the enterprise, the market value information of the enterprise, the employee information of the enterprise, the tax payment information of the enterprise and the payment information of five risks and one fund of the enterprise; and the second part performs characteristic engineering on enterprise product production region information, enterprise product sales region information, enterprise product consumption scene information, enterprise product consumption group information, past enterprise production sales information, enterprise flow information, enterprise cash flow information, past enterprise profit and loan repayment information and reflects future expected profit capacity and continuous profit capacity of the enterprise.
4) The first part of the enterprise manager data is characterized engineering on data such as credit information of an enterprise manager, consumption record information of the enterprise manager, loan and repayment information of the enterprise manager, loan use information of the enterprise manager and the like, credit information of the enterprise manager is reflected, and the possibility that an enterprise legal person uses funds is measured by using the credit information; the second part is that characteristic engineering is carried out on data such as asset liability information, capital flow information, investment information and the like of an enterprise manager to reflect the management capability of the enterprise manager, such as new characteristics of construction of annual capital value-added rate, investment return rate, annual asset allocation proportion and the like, and the data is utilized to measure the operation management capability of enterprise legal persons, so as to be used for evaluating the influence on the future profitability of the enterprise; and the third part is to perform characteristic engineering on data of the enterprise manager academic calendar, the graduate colleges and households, reflect the social relationship information of the enterprise manager and evaluate the influence of the social relationship on enterprise operation.
And training the data analysis model by using the sorted data until the model converges.
The operation activities of the enterprises under the crisis are seriously affected, and the influence of the crisis on the macro economy, the influence on the industry and the influence on the enterprises also include the influence on the normal operation activities of the enterprises. Considering the continuous influence of crisis on society, industry and enterprises, the auditing scheme mainly based on the current profitability of the enterprises is easy to deviate, so that the enterprises needing and actually having repayment ability cannot be credited.
Aiming at the extreme scene of loan auditing under crisis, the invention comprehensively considers the overall influence of the crisis on social economy and industry, the influence on normal operation activities of enterprises, the social value and the industrial value of the enterprises, and the urgency of not hitting the loan demand of the enterprises and the future repayment capacity of the enterprises by combining the expected operation capacity of the enterprises and the operation and management capacity of enterprise legal persons; adding corporate legal credit measures the risk of the loan being stolen. And making loan decisions by comprehensively considering the industry, enterprise requirements, enterprise social values, enterprise profitability and stolen risks. Therefore, the method is more suitable for processing the loan audit of enterprises under crisis.
5. And calling the model to check the loan object. And (4) invoking a data preprocessing and data analysis model (loan audit model) trained in the step (4), processing the test data to obtain an output test result, and adjusting the loan audit model according to the test result to obtain a final pre-trained loan audit model.
Next, the procedure of loan application processing using the previously trained loan approval model is described.
In one embodiment, as shown in fig. 3, upon receiving a loan application, multi-dimensional information of the loan application party is obtained, which may be followed by step 102: preprocessing the multi-dimensional information of the loan applicant to obtain preprocessed multi-dimensional information of the loan applicant;
inputting the preprocessed multidimensional information of the loan application party into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan application party, wherein the loan application auditing result comprises the following steps: and inputting the preprocessed multi-dimensional information of the loan applicant into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant.
In specific implementation, before loan application is performed by using the multidimensional information, the multidimensional information of the loan application party is preprocessed (see the preprocessing step in the training model in detail) to obtain the preprocessed multidimensional information of the loan application party, and the preprocessed multidimensional information of the loan application party is input into the loan auditing analysis model, so that a more accurate auditing result can be obtained, and the accuracy of subsequent loan application processing is further ensured.
In summary, the processing method of the loan application provided by the embodiment of the invention has the advantages that:
1) the embodiment of the invention considers the integral influence of the crisis on the macroscopic economy and the industry of the enterprise, and further can measure the integral influence of the crisis on the enterprise.
2) The embodiment of the invention considers the social value and the industrial value of the enterprise and the future expected profitability and the continuous profitability of the enterprise, and the auditing result is more reliable.
3) The embodiment of the invention considers the influence of the management capability of the enterprise manager and the social relationship on the future profitability of the enterprise, and the auditing result is more accurate.
4) The embodiment of the invention considers the credit information of the enterprise manager, measures the possibility of fund usage of enterprise legal persons, and reduces the risk of fund usage by the manager.
The embodiment of the invention also provides a processing device for loan application, which is described in the following embodiment. Since the principle of the device for solving the problems is similar to the processing method of the loan application, the implementation of the device can be referred to the implementation of the processing method of the loan application, and repeated details are not repeated.
Fig. 4 is a schematic structural diagram of a processing apparatus for loan application according to an embodiment of the present invention, as shown in fig. 4, the apparatus includes:
the obtaining unit 01 is used for obtaining the multi-dimensional information of a loan application party when receiving a loan application;
the auditing unit 03 is used for inputting the multi-dimensional information into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant; and the loan auditing model is generated by pre-training according to historical multi-dimensional information samples of a plurality of loan application parties.
In one embodiment, the multi-dimensional information may include: macro economic data, industry data, enterprise data, and enterprise manager data.
In one embodiment, as shown in fig. 5, the processing device for loan application may further include: the preprocessing unit 02 is used for preprocessing the multidimensional information of the loan applicant to obtain the preprocessed multidimensional information of the loan applicant;
the auditing unit may specifically be configured to: and inputting the preprocessed multi-dimensional information of the loan applicant into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant.
In one embodiment, the processing device of the loan application may further include: the model generation unit is used for obtaining a loan auditing model generated by pre-training according to the following method:
obtaining historical multi-dimensional information sample data of a plurality of loan application parties; the sample data comprises positive sample data and negative sample data, wherein the positive sample data is data which meets the loan auditing requirement, and the negative sample data is data which does not meet the loan auditing requirement;
dividing the sample data into a training set and a test set;
training a deep neural network model by using the training set;
testing the trained deep neural network model by using the test set;
and obtaining the loan auditing model generated by the pre-training according to the test result.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the processing method of the loan application when executing the computer program.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program for executing the processing method of the loan application is stored in the computer-readable storage medium.
In the embodiment of the invention, compared with the technical scheme that loan application processing is carried out only by depending on the profitability of enterprises in the prior art, and when the society is influenced by sudden public crisis, the processing accuracy of loan application is low, the processing scheme of loan application in the embodiment of the invention comprises the following steps: when a loan application is received, obtaining multi-dimensional information of a loan application party; inputting the multi-dimensional information into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant; the loan auditing model is generated by pre-training according to historical multi-dimensional information samples of a plurality of loan application parties, and can ensure the accuracy of loan application processing when an emergency abnormal event occurs.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for processing a loan application, comprising:
when a loan application is received, obtaining multi-dimensional information of a loan application party;
inputting the multi-dimensional information into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant; and the loan auditing model is generated by pre-training according to historical multi-dimensional information samples of a plurality of loan application parties.
2. The method of processing a loan application of claim 1, wherein the multi-dimensional information comprises: macro economic data, industry data, enterprise data, and enterprise manager data.
3. The method of processing a loan application according to claim 1, wherein, upon receiving the loan application, obtaining the multidimensional information of the loan application party, then comprises: preprocessing the multi-dimensional information of the loan applicant to obtain preprocessed multi-dimensional information of the loan applicant;
inputting the multi-dimensional information into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant, wherein the loan application auditing result comprises the following steps: and inputting the preprocessed multi-dimensional information of the loan applicant into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant.
4. The method of processing a loan application of claim 1, further comprising: obtaining a loan auditing model generated by pre-training according to the following method:
obtaining historical multi-dimensional information sample data of a plurality of loan application parties; the sample data comprises positive sample data and negative sample data, wherein the positive sample data is data which meets the loan auditing requirement, and the negative sample data is data which does not meet the loan auditing requirement;
dividing the sample data into a training set and a test set;
training a deep neural network model by using the training set;
testing the trained deep neural network model by using the test set;
and obtaining the loan auditing model generated by the pre-training according to the test result.
5. A loan application processing apparatus, comprising:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring multi-dimensional information of a loan application party when receiving a loan application;
the auditing unit is used for inputting the multi-dimensional information into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant; and the loan auditing model is generated by pre-training according to historical multi-dimensional information samples of a plurality of loan application parties.
6. The loan application processing apparatus of claim 5, wherein the multi-dimensional information comprises: macro economic data, industry data, enterprise data, and enterprise manager data.
7. The loan application processing apparatus of claim 5, further comprising: the preprocessing unit is used for preprocessing the multidimensional information of the loan applicant to obtain the preprocessed multidimensional information of the loan applicant;
the auditing unit is specifically configured to: and inputting the preprocessed multi-dimensional information of the loan applicant into a loan auditing model generated by pre-training to obtain a loan application auditing result of the loan applicant.
8. The loan application processing apparatus of claim 5, further comprising: the model generation unit is used for obtaining a loan auditing model generated by pre-training according to the following method:
obtaining historical multi-dimensional information sample data of a plurality of loan application parties; the sample data comprises positive sample data and negative sample data, wherein the positive sample data is data which meets the loan auditing requirement, and the negative sample data is data which does not meet the loan auditing requirement;
dividing the sample data into a training set and a test set;
training a deep neural network model by using the training set;
testing the trained deep neural network model by using the test set;
and obtaining the loan auditing model generated by the pre-training according to the test result.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010915724.4A CN112053231A (en) | 2020-09-03 | 2020-09-03 | Loan application processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010915724.4A CN112053231A (en) | 2020-09-03 | 2020-09-03 | Loan application processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112053231A true CN112053231A (en) | 2020-12-08 |
Family
ID=73607785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010915724.4A Pending CN112053231A (en) | 2020-09-03 | 2020-09-03 | Loan application processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112053231A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112419048A (en) * | 2020-12-10 | 2021-02-26 | 中国农业银行股份有限公司南海分行 | Credit customer intelligent analysis method |
| CN113283979A (en) * | 2021-05-12 | 2021-08-20 | 广州市全民钱包科技有限公司 | Loan credit evaluation method and device for loan applicant and storage medium |
| CN114971879A (en) * | 2022-06-17 | 2022-08-30 | 北京极致车网科技有限公司 | Information processing system and information processing method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110322089A (en) * | 2018-03-30 | 2019-10-11 | 宗略投资(上海)有限公司 | Enterprise Credit Risk Evaluation method and its system |
| CN110348981A (en) * | 2019-05-21 | 2019-10-18 | 平安科技（深圳）有限公司 | Loan air control method and device, electronic equipment and computer readable storage medium |
-
2020
- 2020-09-03 CN CN202010915724.4A patent/CN112053231A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110322089A (en) * | 2018-03-30 | 2019-10-11 | 宗略投资(上海)有限公司 | Enterprise Credit Risk Evaluation method and its system |
| CN110348981A (en) * | 2019-05-21 | 2019-10-18 | 平安科技（深圳）有限公司 | Loan air control method and device, electronic equipment and computer readable storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112419048A (en) * | 2020-12-10 | 2021-02-26 | 中国农业银行股份有限公司南海分行 | Credit customer intelligent analysis method |
| CN113283979A (en) * | 2021-05-12 | 2021-08-20 | 广州市全民钱包科技有限公司 | Loan credit evaluation method and device for loan applicant and storage medium |
| CN114971879A (en) * | 2022-06-17 | 2022-08-30 | 北京极致车网科技有限公司 | Information processing system and information processing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230009149A1 (en) | System, method and computer program for underwriting and processing of loans using machine learning | |
| Amani et al. | Data mining applications in accounting: A review of the literature and organizing framework | |
| Blalock et al. | Financial constraints on investment in an emerging market crisis | |
| US8065214B2 (en) | Methods and system for assessing loss severity for commercial loans | |
| KR102009309B1 (en) | Management automation system for financial products and management automation method using the same | |
| US20040015376A1 (en) | Method and system to value projects taking into account political risks | |
| US20050080821A1 (en) | System and method for managing collections accounts | |
| CN112053231A (en) | Loan application processing method and device | |
| Bakhach et al. | TSFDC: A trading strategy based on forecasting directional change | |
| Legowo | Monitoring and Evaluation Information System Modeling for Banking Credits | |
| Kothandapani | Applications of Robotic Process Automation in Quantitative Risk Assessment in Financial Institutions | |
| CN112766814A (en) | Training method, device and equipment for credit risk pressure test model | |
| KR102249028B1 (en) | System for Debt Repayment Capability Evaluation Of Corporation | |
| Biswas et al. | Automated credit assessment framework using ETL process and machine learning | |
| Quaranta et al. | Impairment of intangible assets and disclosure by Italian banks | |
| García–Gallego et al. | Forecasting statistical methods in business: a comparative study of discriminant and logit analysis in predicting business failure | |
| Roberts et al. | Risk Modeling: Practical Applications of Artificial Intelligence, Machine Learning, and Deep Learning | |
| Parnes | A spline hazard model for current expected credit losses | |
| Emeke et al. | Revenue Leakages and Economic Growth in Nigeria: The Place of Forensic Accounting | |
| KR102334923B1 (en) | Loan expansion hypothesis testing system using artificial intelligence and method using the same | |
| Paolone et al. | Concluding Remarks: The Importance of Cash Flow Statement | |
| Subramanian R et al. | ERRM Gap Analysis & Identification | |
| Qin et al. | Are there digital tech bubbles in China? | |
| Locatelli et al. | AI Tools in Credit Risk | |
| Motale | Predicting business failure in a South African business bank |
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 |