CN113781198A - Enterprise loan application evaluation system - Google Patents
Enterprise loan application evaluation system Download PDFInfo
- Publication number
- CN113781198A CN113781198A CN202010691410.0A CN202010691410A CN113781198A CN 113781198 A CN113781198 A CN 113781198A CN 202010691410 A CN202010691410 A CN 202010691410A CN 113781198 A CN113781198 A CN 113781198A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- variable
- data
- credit
- revenue
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 55
- 238000004364 calculation method Methods 0.000 claims abstract description 25
- 238000010801 machine learning Methods 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims description 34
- 238000011835 investigation Methods 0.000 claims description 18
- 238000012797 qualification Methods 0.000 claims description 8
- 238000012552 review Methods 0.000 claims description 8
- 230000007774 longterm Effects 0.000 claims description 6
- 238000004064 recycling Methods 0.000 claims description 6
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 230000036651 mood Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000007306 turnover Effects 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
An enterprise loan application evaluation system comprises a bank computer system, wherein the bank computer system comprises a limit calculation and check module and a database. When the bank computer system receives an application document image from a first mobile device and related to an enterprise, the application document image is firstly subjected to image recognition to generate application document data containing contents of a plurality of paper application documents. The limit calculation and check module obtains the joint check data and the client data related to the enterprise from the joint check central computer system and the database respectively according to the application file data, and generates input data to be input into the machine learning model for calculation so as to generate a creditable limit. The bank computer system transmits the lendable amount to the first mobile device to notify the enterprise in real time.
Description
Technical Field
The invention relates to a financial system, in particular to an enterprise loan application evaluation system for remote credit investigation and fast credit check.
Background
With the prosperous entrepreneurity of entrepreneurial business, a plurality of small and medium-sized or micro-sized enterprises gradually appear in the society, but the fund turnover problem caused by the enterprise operation is always tired of a plurality of enterprise owners. The fund is the key for maintaining the operation of the company, and compared with the personal credit loan, the enterprise loan has more documents which need to be represented due to the existing regulatory requirements, so that a common bank is used to passively wait for the client to consult and replenish the paper document before beginning to check and transact the loan application. Therefore, the loan application time of the enterprise is long, the final credit limit condition and the client expectation are always different, the scheduling arrangement and the operation development of the enterprise operation fund are inconvenient, and the willingness of the enterprise to apply the loan to the bank is influenced, so that the problem to be solved is solved.
Disclosure of Invention
The invention aims to provide an enterprise loan application evaluation system for remote credit investigation and quick loan checking.
Therefore, the invention provides an enterprise loan application evaluation system, which is suitable for a first mobile device and a joint credit central computer system and comprises a bank computer system. The bank computer system belongs to a bank, can establish a connection with the first mobile device, and comprises a limit calculation and check module and a database, wherein the database stores a machine learning model and client data related to enterprises.
When the bank computer system receives the application document image from the first mobile device, the application document image is subjected to image recognition to generate application document data of the content of a plurality of paper application documents contained in the application document image, wherein the paper application documents are related to loan applications proposed by the enterprise.
The line calculation and check module obtains the joint check data related to the enterprise from the joint credit investigation central computer system according to the application file data, obtains the client data related to the enterprise from the database, obtains input data according to the joint check data and the client data, inputs the input data into the machine learning model, calculates to generate a credit line, and transmits the credit line to the first mobile device through the bank computer system so as to inform the enterprise in real time.
In some implementations, wherein the machine learning model is a Gradient Boosting Decision Tree (GBDT) model.
In other embodiments, the credit calculation review module obtains, as the input data, industry variable data of an industry class to which the enterprise belongs, evaluation variable data of a bank class, revenue variable data related to revenue of the enterprise, asset variable data related to assets of the enterprise, liability variable data related to liability of the enterprise, and corporate seniority variable data according to the affiliation data or the client data.
In some embodiments, the evaluation variable data comprises one of a plurality of different values corresponding to a plurality of different evaluations. The industry level variable data includes one of a plurality of different values corresponding to a plurality of different industry levels.
The revenue variable data comprises at least one of a 1 st variable of the last 12 months revenue of the enterprise, a 2 nd variable of the average monthly amount of the actual revenue of the enterprise in the last three months, a 3 rd variable of the average monthly amount of the actual revenue of the enterprise in the last half year, a 4 th variable of the average monthly amount of the revenue of the enterprise divided by the average monthly amount of the actual revenue of the enterprise in the last three months, a 5 th variable of the last 12 months revenue of the enterprise divided by the storage performance of the responsible person and spouse of the enterprise in the last three months, and a 6 th variable of the last 12 months revenue of the enterprise minus the annual revenue.
The asset variable data includes at least one of a 7 th variable of whether the business's responsible person and spouse and children have real estate, and an 8 th variable of the business's responsible person and spouse's performance in the last three months.
The liability variable data comprises a 9 th variable of the recent total credit balance of the enterprise, a 10 th variable of the total credit balance of the couple of the person in charge of the enterprise, an 11 th variable of the monthly intrinsic expenditure of the person in charge of the enterprise and the couple of the enterprise, and a 12 th variable of the recent total credit balance of the enterprise divided by the latest 12 months income, and the sum of the recent total credit balance of the enterprise and the total credit balance of the couple of the responsible person of the enterprise is divided by 13 th variable collected in the last 12 months of the enterprise, the 14 th variable of the monthly intrinsic expenditure of the responsible person and the spouse of the enterprise and the enterprise divided by the three-month inventory performance of the responsible person and the spouse of the enterprise and the recent total credit balance of the responsible person and the spouse of the enterprise are divided by 15 th variable of the same year-round total credit balance of the responsible person and the spouse of the enterprise and the enterprise.
The company qualification variable data comprises at least one of a 16 th variable of whether the enterprise has come and go with a leasing company, a 17 th variable of how many banks the enterprise has been inquired in association with in three months, an 18 th variable of how many banks the enterprise has come and go with the banks, a 19 th variable of how many banks the enterprise has come and go without the banks, a 20 th variable of how many months the enterprise has been operated continuously, and a landscape index. The mood indicator includes one of a plurality of different values corresponding to a plurality of different mood levels.
In other embodiments, the machine learning model is trained (Training) with Training input data and Training target data, wherein the Training input data includes the industry variable data, the evaluation variable data, the revenue variable data, the asset variable data, the liability variable data, and the corporate seniority variable data of a plurality of business clients belonging to the bank and in a Training time interval and between a first proportion and a second proportion related to revenue and credit ratios, and the Training target data is a plurality of actual loan amounts of the business clients respectively corresponding to the Training input data.
In other embodiments, one of the revenue variable data is revenue interval revenue of the enterprise in a predetermined time interval, and the amount calculation and review module determines at least one corresponding one of an industry note, a comment note and a revenue interval note according to at least one of the industry variable data, the evaluation variable data and the revenue interval revenue, so as to use at least the corresponding one of the industry note, the comment note and the revenue interval note as a part of the input data.
In some embodiments, each of the industry note, the assessment note, and the revenue interval note comprises two values. The amount calculation and check module determines that the industry notes are respectively equal to a first numerical value and a second numerical value when the industry grade of the enterprise is judged to be respectively equal to or not equal to a set industry according to the industry grade variable data, determines that the evaluation notes are respectively equal to a third numerical value and a fourth numerical value when the bank grade of the enterprise is judged to be respectively higher than or lower than a set evaluation according to the evaluation variable data, and determines that the operation section notes are respectively equal to a fifth numerical value and a sixth numerical value when the income of the enterprise in the operation section in the preset time section is respectively greater than or equal to or less than a set amount.
In other embodiments, the machine learning model is trained (Training) with Training input data and Training target data, wherein the Training input data includes the industry variable data, the evaluation variable data, the revenue variable data, the asset variable data, the liability variable data, the company qualification variable data, the industry remarks, the evaluation remarks, and the revenue interval remarks of a plurality of enterprise clients belonging to the bank and in a Training time interval and between a first proportion and a second proportion related to revenue and credit proportions, and the Training target data is a plurality of actual credit amounts of the enterprise clients respectively corresponding to the Training input data.
In other embodiments, the earning and credit proportion is (financial liability of the enterprise-long guarantee and long loan of the enterprise + financial liability of the responsible person of the enterprise-long guarantee and long loan of the responsible person of the enterprise + recycling card fee of credit card of the responsible person of the enterprise + cash balance of cash card of the responsible person of the enterprise + financial liability of the spouse of the responsible person of the enterprise-long guarantee and long loan of the spouse of the responsible person of the enterprise + recycling card fee of credit card of the spouse of the responsible person of the enterprise + debit balance of cash card of the spouse of the responsible person of the enterprise)/earning of the 401 table of the enterprise for approximately 12 months.
In other embodiments, the enterprise loan application evaluation system is further adapted to a credit collector and a second mobile device, after the first mobile device notifies the enterprise of the loanable amount and transmits a confirmation loan application instruction to the bank computer system, wherein the bank computer system generates a credit report set corresponding to the industry to which the enterprise belongs and transmits the credit report set to the second mobile device, the second mobile device obtains a credit report corresponding to the credit report set through the credit collector, completes writing of the credit report and transmits the written credit report to the bank computer system, and the bank computer system determines whether to approve the loan application corresponding to the loanable amount according to the credit report.
The invention has the beneficial effects that: the bank computer system receives the application file image of the first mobile device, obtains the application file data according to the application file image, and then obtains the joint sign data and the customer data through the joint credit investigation central computer system and the database respectively. The credit line calculation and check module obtains the input data according to the joint check data and the client data to input the machine learning model, and further calculates the creditable credit line which can be immediately transmitted to the first mobile device to inform the enterprise, so that the problems encountered in the prior credit application can be effectively solved.
Drawings
FIG. 1 is a block diagram illustrating one embodiment of an enterprise loan application evaluation system of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and examples.
Before the present invention is described in detail, it should be noted that in the following description, like elements are represented by like reference numerals.
Referring to fig. 1, an embodiment of the enterprise loan application evaluation system of the present invention is suitable for a business person, a credit investigation person, a first mobile device 2, a second mobile device 3, and a joint credit investigation center computer system 4, and comprises a bank computer system 1. Any one of the first mobile device 2 and the second mobile device 3 is, for example, a smart phone, a tablet computer, or other similar portable electronic devices with networking functions. The bank computer system 1, the service personnel and the credit investigation personnel all belong to the same bank. The joint credit bureau computer system 4 is, for example, one or more computer hosts or servers to provide credit bureau service.
The first mobile device 2 is pre-installed with an application program (APP) provided by the bank and includes an image capturing module 21. The image capturing module 21 is, for example, a camera lens and a related sensor. The first mobile device 2 selects to execute the application program through the business personnel after the business personnel visits a client, such as a responsible person of an enterprise, and confirms the intention of the enterprise to provide a loan application to the bank, so as to use the image acquisition module 21 to acquire an application document image containing a plurality of paper application documents, and establish a connection with the bank computer system 1, so as to transmit the application document image to the bank computer system 1. The paper application document relates to the loan application made by the business (i.e., the principal). For example, the paper document includes personal data protection agreement of related people, company registration data, various financial statements, insurance document data and financial data, etc.
The bank computer system 1 is, for example, one or more computer hosts or servers of the bank, and includes a credit calculation and verification module 11 and a database 12. The credit calculation verification module 11 is, for example, a single computer host or a server, but not limited thereto. The database 12 stores a machine learning model and a customer data associated with the enterprise. In the embodiment, the machine learning model belongs to a supervised learning model, and is, for example, a Gradient Boosting Decision Tree (GBDT) model.
When the bank computer system 1 receives the application document image from the first mobile device 2, the application document image is first subjected to image recognition to generate application document data including the content of the paper application document. The quota calculation check module 11 obtains a connection data related to the enterprise from the joint credit central computer system 4 according to the application document data, obtains the client data related to the enterprise from the database 12, and obtains an input data according to the connection data and the client data. The credit calculation and review module 11 inputs the input data into the machine learning model for calculation to generate a credit-able credit, and the bank computer system 1 transmits the credit-able credit to the first mobile device 2 to notify the enterprise in real time.
More specifically, the credit calculation and review module 11 obtains an industry variable data of the industry to which the enterprise belongs, an evaluation variable data of the evaluation at the bank, revenue variable data related to the revenue of the enterprise, asset variable data related to the asset of the enterprise, liability variable data related to the liability of the enterprise, and corporate seniority variable data according to the linkage data or the client data.
In the present embodiment, the evaluation variable data includes one of a plurality of different values corresponding to a plurality of different evaluations, for example, A, B, C, D, E the grades of five evaluations correspond to values of 1-5 respectively. The industry variable data includes one of a plurality of different values corresponding to a plurality of different industries, such as manufacturing industry, wholesale industry, service industry, retail catering industry, construction industry, and other industries, which are respectively 1-6.
The revenue variable data includes a 1 st variable to a 6 th variable. The 1 st variable is the last 12 months of revenue for the business, for example, in millennia. The 2 nd variable is the monthly average amount that the enterprise remits into the bankbook detail for approximately three months to identify as revenue, and the unit is thousand yuan, for example. The 3 rd variable is the monthly average of the actual revenue of the enterprise in the last half year, for example, thousand yuan. The 4 th variable is the monthly average amount of revenue that the enterprise imports into the bankbook detail for nearly three months and can be identified as revenue divided by the monthly average amount of actual revenue of the enterprise nearly half a year. The 5 th variable is the last three months of performance of the business and its responsible and spouse divided by the last 12 months of revenue of the business. The deposit result, i.e., the deposit result number, is an average value calculated from the deposit balances of 5, 10, 15, 20, 25, and 30 days per month of the deposit book. The 6 th variable is the last 12 months of revenue minus the last year of revenue for the business, for example, in millennia.
The asset variable data comprises a 7 th variable through an 8 th variable. The 7 th variable is, for example, equal to 0 or 1, indicating that the responsible person and spouse and children of the enterprise do not hold or hold real property, respectively. The 8 th variable is the performance of the business and its responsible person and spouse for approximately three months, for example, in thousand yuan.
The liability variable data comprises a 9 th variable to a 15 th variable. The 9 th variable is the latest total credit balance of the enterprise, which is the latest total credit balance updated by the contact center, for example, the contact center updates data at 15 days per month, and the unit is thousand yuan. The 10 th variable is the total credit balance of the enterprise's responsible couple, for example, in thousand yuan. The 11 th variable is the monthly rest cost of the business and its responsible persons and spouses, in units such as thousand yuan. The 12 th variable is the enterprise's recent total credit balance divided by the recent 12 months revenue. The 13 th variable is the sum of the recent total credit balance of the enterprise and the total credit balance of the responsible couple of the enterprise divided by the last 12 months revenue of the enterprise. The 14 th variable is the last three months worth of performance of the business and the business's responsible person and spouse divided by the monthly instinct expenditure of the business and the business's responsible person and spouse. The 15 th variable is the most recent total credit balance of the enterprise and its responsible party and spouse minus the same previous year total credit balance of the enterprise and its responsible party and spouse, for example, in thousand yuan.
The company seniority variable data includes a 16 th variable through a 20 th variable and a mood indicator. The 16 th variable is, for example, equal to 0 or 1, indicating that the business has no or no business to or from the rental company, respectively. The 17 th variable is how many bank affiliations the business was queried by in the last three months. The 18 th variable is how many banks the business has come and go with the bank. The 19 th variable is how many banks the business has come and go with which the bank is not included. The 20 th variable is how many months the business was operating continuously. The landscape index is, for example, equal to 1 to 5, which indicates that the landscape is very poor, slightly poor, medium, slightly good, and very good, respectively.
In addition, one of the revenue variable data is a revenue interval revenue of the enterprise for a predetermined time interval, such as annual revenue. The credit calculation and review module 11 determines an industry note, an evaluation note and a revenue interval note according to the industry variable data, the evaluation variable data and the revenue interval income. In this embodiment, each of the industry note, the evaluation note, and the revenue zone note includes two values, the amount calculation and qualification module 11 determines that the industry note is equal to a first value and a second value when determining that the industry to which the enterprise belongs is equal to or not equal to a set industry, respectively, and determines that the evaluation note is equal to a third value and a fourth value when determining that the bank belongs to which the enterprise is higher than or equal to or lower than a set evaluation, respectively, according to the evaluation variable data, and determines that the revenue zone note is equal to a fifth value and a sixth value when the revenue zone income of the enterprise in the predetermined time zone is greater than or equal to or less than a set amount, respectively.
For example, if the industry is the construction industry, the industry index is equal to 0 (i.e., the first value) and, conversely, equal to 1 (i.e., the second value). The rating is set to be a rating of B, and when the rating is a rating of a or B, the rating is equal to 1 (i.e., the third value), and conversely, equal to 0 (i.e., the fourth value). The set amount is 4000 ten thousand yuan, and when the annual revenue is more than or equal to 4000 ten thousand yuan, the revenue interval is marked with a symbol of 1 (i.e., the fifth value), and conversely, is equal to 0 (i.e., the sixth value).
The credit calculation and review module 11 uses the industry variable data, the evaluation variable data, the revenue variable data, the asset variable data, the liability variable data, the company seniority variable data, the industry note, the evaluation note and the revenue interval note as the input data to input the machine learning model, and further calculate to generate the creditable credit. Further, it is to be noted that: in other embodiments, the industry note, the comment note, and the revenue interval note may be omitted from the input data, but the calculated creditable amount may be somewhat less effective.
The machine learning model is trained (Training) in advance with a Training input data and a Training target data, the Training input data including the industry variable data, the evaluation variable data, the revenue variable data, the asset variable data, the liability variable data, the company seniority variable data, the industry remarks, the evaluation interval remarks of a plurality of enterprise clients belonging to the bank and in a Training time interval and between a first proportion and a second proportion related to a revenue and credit ratio. The training target data is a plurality of actual loan amounts of the business clients respectively corresponding to the training input data.
For example, the earnings and credits ratio (financial liability of the enterprise-long term guarantee and long term loan of the enterprise + financial liability of the responsible person of the enterprise-long term guarantee and long term loan of the responsible person of the enterprise + recycling card fee of credit card of the responsible person of the enterprise + debit balance of cash card of the responsible person of the enterprise + financial liability of the spouse of the responsible person of the enterprise-long term guarantee and long term loan of the spouse of the responsible person of the enterprise + recycling card fee of credit card of the spouse of the responsible person of the enterprise + debit balance of cash card of the spouse of the responsible person of the enterprise)/earnings of the nearly 12 months 401 tables of the enterprise, the first proportion is 6.3%, the second proportion is 92.5%, the training time interval is the first 11 months out of the first 12 months of the current month, and the corresponding data of the previous month before the current month is taken as test data. During the trained testing process, when each of the lendable limit calculated by the machine learning model is greater than or equal to 80% of the corresponding actual loan limit, it is regarded as hit, i.e., the estimated result is regarded as valid. Further, specifically, the following are: in the present embodiment, the calculation result of the lendable amount is, for example, the amount corresponding to one repayment type loan, but may be converted into the amount of another loan type loan through a predetermined formula.
After the business person transmits the application image to the bank computer system 1 through the first mobile device 2, the bank computer system 1 can immediately transmit the credit limit back to the first mobile device 2, so that the business person can give the customer (i.e. the responsible person) product combination and limit suggestion on site. When the enterprise determines to apply the loan application of the loan amount, the first mobile device 2 transmits a confirmation loan application instruction to the bank computer system 1 through the service personnel, so that the bank computer system 1 generates a credit investigation question set corresponding to the industry of the enterprise, and transmits the credit investigation question set to the second mobile device 3.
Then, the credit investigation personnel carries the second mobile device 3 to go to the enterprise to interview the responsible person, and provides the problem of the credit investigation question set for the responsible person, and inputs and generates a credit investigation report corresponding to the credit investigation question set through the second mobile device 3, namely, the credit investigation report is written and completed. The second mobile device 3 further transmits the credit investigation report to the bank computer system 1, so that the bank computer system 1 determines whether to approve the loan application corresponding to the lendable amount according to the credit investigation report. For example, the credit report is a 5P questionnaire, and includes: peoples, business continents, responsible human home experience, and the like; the rationality of the Purpose of borrowing and the existing debt raising of the Purpose; payment, source of Payment; protection, insurance related seniority; and 5. Perproductive, future development and prospects of the company. In addition, the authorization personnel can confirm the correctness and reasonableness of the related data again or the bank computer system 1 can automatically recognize and interpret the content to decide whether to approve the loan application. Therefore, the credit applicant can complete the visit report at the same time when the visit is finished according to the credit question set of the second mobile device 3, so that the time required for credit check can be greatly reduced.
In summary, when the bank computer system 1 receives the application document image of the first mobile device 2, it first obtains the application document data according to the application document image, and then obtains the affiliation data and the customer data from the joint credit center computer system 4 and the database 12, respectively. The credit calculation and review module 11 obtains the input data according to the connection data and the client data to input the machine learning model, and further calculates the creditable credit, which can be immediately transmitted to the first mobile device 2 to notify the enterprise. Furthermore, the credit-investigation personnel can complete the visit report at the same time when performing the credit investigation by the second mobile device 3, so the problems encountered in the prior loan application can be effectively solved, and the purpose of the invention can be achieved.
It should be understood that the above description is only exemplary of the present invention, and should not be taken as limiting the scope of the invention, i.e., the appended claims and the description should be construed as being limited only by the scope of the invention.
Claims (10)
1. An enterprise loan application evaluation system is suitable for a first mobile device and a joint credit-reporting central computer system, and is characterized in that: the enterprise loan application evaluation system comprises a bank computer system which belongs to a bank and can be connected with the first mobile device, and the bank computer system comprises a credit calculation and check module and a database, wherein the database stores a machine learning model and client data related to an enterprise,
when the bank computer system receives the application document image from the first mobile device, the application document image is subjected to image recognition to generate application document data of the content of a plurality of paper application documents contained in the application document image, wherein the paper application documents are related to loan applications proposed by the enterprise,
the line calculation and check module obtains the joint check data related to the enterprise from the joint credit investigation central computer system according to the application file data, obtains the client data related to the enterprise from the database, obtains input data according to the joint check data and the client data, inputs the input data into the machine learning model, calculates to generate a credit line, and transmits the credit line to the first mobile device through the bank computer system so as to inform the enterprise in real time.
2. The enterprise loan declaration evaluation system of claim 1, wherein: the machine learning model is a gradient boosting decision tree model.
3. The enterprise loan declaration evaluation system of claim 1, wherein: the credit calculation and review module obtains, as the input data, industry grade variable data of an industry grade to which the enterprise belongs, evaluation grade variable data of a bank grade, revenue variable data related to revenue of the enterprise, asset variable data related to assets of the enterprise, liability variable data related to liability of the enterprise, and corporate seniority variable data according to the linkage data or the client data.
4. The enterprise loan declaration evaluation system of claim 3, wherein:
the evaluation variable data includes one of a plurality of different values corresponding to a plurality of different evaluations, the industry category variable data includes one of a plurality of different values corresponding to a plurality of different industry categories,
the revenue variable data comprises at least one of a 1 st variable of the last 12 months revenue of the enterprise, a 2 nd variable of the monthly average amount of the annual actual revenue of the enterprise which is available for identification by the inventory details of the annual revenue of the enterprise, a 3 rd variable of the monthly average amount of the annual actual revenue of the enterprise, a 4 th variable of the monthly average amount of the annual actual revenue of the enterprise which is available for identification by the inventory details of the annual average amount of the annual actual revenue of the enterprise, a 5 th variable of the annual or annual average of the responsible and spouse of the enterprise divided by the annual revenue of the last 12 months of the enterprise, and a 6 th variable of the annual revenue of the last 12 months of the enterprise minus the annual revenue of the last 12 months of the enterprise,
the asset variable data includes at least one of a 7 th variable of whether the business's responsible person and spouse and children have real estate, and an 8 th variable of the business's responsible person and spouse's performance in the last three months,
the liability variable data comprises at least one of a 9 th variable of the recent total credit balance of the enterprise, a 10 th variable of the total credit balance of the couple of the responsible person of the enterprise, a 11 th variable of the monthly current expenditure of the responsible person and the couple of the enterprise and the enterprise, a 12 th variable of the recent total credit balance of the enterprise divided by the last 12 months income, a 13 th variable of the sum of the recent total credit balance of the enterprise and the total credit balance of the responsible person of the enterprise divided by the last 12 months income of the enterprise, a 14 th variable of the recent performance of the responsible person and the couple of the enterprise divided by the monthly current expenditure of the responsible person and the couple of the enterprise and the enterprise, and a 15 th variable of the recent total credit balance of the responsible person and the couple of the enterprise minus the annual current total credit balance of the responsible person and the couple of the enterprise and the enterprise,
the company qualification variable data comprises at least one of a 16 th variable of whether the enterprise has come and go with a leasing company, a 17 th variable of how many banks the enterprise has been in a third month for a joint query, an 18 th variable of how many banks the enterprise has come and go with the banks, a 19 th variable of how many banks the enterprise has come and go without the banks, a 20 th variable of how many months the enterprise has been in continuous business, and a landscape index, wherein the landscape index comprises one of a plurality of different values corresponding to a plurality of different landscape levels.
5. The enterprise loan declaration evaluation system of claim 3, wherein: the machine learning model is trained by training input data and training target data, wherein the training input data comprise industry variable data, evaluation variable data, income variable data, asset variable data, liability variable data and company qualification variable data of a plurality of enterprise clients belonging to the bank and in a training time interval and between a first proportion and a second proportion related to income and credit proportions, and the training target data are a plurality of actual credit loans of the enterprise clients respectively corresponding to the training input data.
6. The enterprise loan declaration evaluation system of claim 3, wherein: one of the revenue variable data is revenue of the enterprise in a predetermined time interval, and the amount calculation and qualification module determines at least one corresponding one of an industry note, a comment note and a revenue interval note according to at least one of the industry variable data, the comment variable data and the revenue interval, so as to use at least the corresponding one of the industry note, the comment note and the revenue interval note as a part of the input data.
7. The enterprise loan declaration evaluation system of claim 6, wherein: each of the industry notes, the evaluation notes and the revenue interval notes comprises two numerical values, the amount calculation and qualification module determines that the industry notes are respectively equal to a first numerical value and a second numerical value when judging that the industry of the enterprise is respectively equal to or not equal to a set industry according to the industry variable data, determines that the evaluation notes are respectively equal to a third numerical value and a fourth numerical value when judging that the bank of the enterprise is higher than or equal to or lower than a set evaluation according to the evaluation variable data, and determines that the revenue interval notes are respectively equal to a fifth numerical value and a sixth numerical value when the revenue interval of the enterprise in the preset time interval is respectively greater than or equal to or less than a set amount.
8. The enterprise loan declaration evaluation system of claim 6, wherein: the machine learning model is trained by training input data and training target data, wherein the training input data comprises industry variable data, evaluation variable data, revenue variable data, asset variable data, liability variable data, company qualification variable data, industry comments, comments and the like of a plurality of enterprise clients belonging to the bank and in a training time interval and between a first proportion and a second proportion related to revenue and credit ratios, and the training target data is a plurality of actual credit limits of the enterprise clients respectively corresponding to the training input data.
9. The enterprise loan declaration evaluation system according to claim 5 or 8, wherein: the earning and credit allocation ratio is (financial liability of the enterprise-long-term guarantee and long-term loan of the enterprise + financial liability of the responsible person of the enterprise-long-term guarantee and long-term loan of the responsible person of the enterprise + recycling card fee of credit card of the responsible person of the enterprise + debit balance of cash card of responsible person of the enterprise + financial liability of spouse of responsible person of the enterprise-long-term guarantee and long-term loan of spouse of responsible person of the enterprise + recycling card fee of credit card of spouse of responsible person of the enterprise + debit of cash card of spouse of responsible person of the enterprise)/earning of 401 table of the enterprise for nearly 12 months.
10. The enterprise loan declaration evaluation system according to claim 5 or 8, wherein: the enterprise loan application evaluation system is also suitable for credit collection personnel and a second mobile device, after the first mobile device informs the enterprise of the loan-available amount, and sends a confirmation loan application instruction to the bank computer system, wherein the bank computer system generates a credit collection set corresponding to the industry of the enterprise and sends the credit collection set to the second mobile device, the second mobile device obtains a credit collection report corresponding to the credit collection set through the credit collection personnel, writes the credit collection report completely and sends the credit collection report to the bank computer system, and the bank computer system determines whether to approve the loan application corresponding to the loan-available amount according to the credit collection report.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW109119311 | 2020-06-09 | ||
| TW109119311A TWI759759B (en) | 2020-06-09 | 2020-06-09 | Enterprise Loan Evaluation System |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113781198A true CN113781198A (en) | 2021-12-10 |
Family
ID=78835171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010691410.0A Pending CN113781198A (en) | 2020-06-09 | 2020-07-17 | Enterprise loan application evaluation system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113781198A (en) |
| TW (1) | TWI759759B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140201061A1 (en) * | 2013-01-14 | 2014-07-17 | Wonga Technology Limited | On-line automated loan system |
| US20150278941A1 (en) * | 2014-03-26 | 2015-10-01 | Wonga Technology Limited | Loan automation system |
| CN107067319A (en) * | 2017-03-13 | 2017-08-18 | 平安科技（深圳）有限公司 | Loan limit measuring method and device |
| TWM549928U (en) * | 2017-06-16 | 2017-10-01 | Ctbc Bank Co Ltd | Online real-time credit analysis and approval server unit |
| CN108648074A (en) * | 2018-05-18 | 2018-10-12 | 深圳壹账通智能科技有限公司 | Loan valuation method, apparatus based on support vector machines and equipment |
| CN108961040A (en) * | 2018-06-29 | 2018-12-07 | 重庆富民银行股份有限公司 | Loan limit assessment system and method for credit extension loan |
| CN109166033A (en) * | 2018-09-03 | 2019-01-08 | 平安国际融资租赁有限公司 | Loan limit calculation method, device, computer equipment and storage medium |
| TWM577559U (en) * | 2018-11-30 | 2019-05-01 | 中國信託商業銀行股份有限公司 | Evaluation system for unsecured relocation loan amount |
| CN109711981A (en) * | 2018-12-28 | 2019-05-03 | 上海点融信息科技有限责任公司 | The method, apparatus and storage medium of the accrediting amount are determined based on artificial intelligence |
| CN110060144A (en) * | 2019-03-18 | 2019-07-26 | 平安科技（深圳）有限公司 | Amount model training method, amount appraisal procedure, device, equipment and medium |
| CN110335141A (en) * | 2019-06-29 | 2019-10-15 | 北京淇瑀信息科技有限公司 | A kind of accrediting amount based on multi-model determines method, apparatus and electronic equipment |
| CN110458693A (en) * | 2019-08-08 | 2019-11-15 | 中国建设银行股份有限公司 | A kind of automatic measures and procedures for the examination and approval of business loan, device, storage medium and electronic equipment |
| CN111210341A (en) * | 2020-01-14 | 2020-05-29 | 中国建设银行股份有限公司 | Method and device for determining service quota |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2018102040A4 (en) * | 2018-12-10 | 2019-01-17 | Chen, Shixuan Mr | The method of an efficient and accurate credit rating system through the gradient boost decision tree |
| CN109767319A (en) * | 2018-12-17 | 2019-05-17 | 平安普惠企业管理有限公司 | The accrediting amount determines method, apparatus, computer equipment and storage medium |
| CN110046984A (en) * | 2019-03-01 | 2019-07-23 | 安徽省优质采科技发展有限责任公司 | Enterprise credit risk system and evaluation method |
-
2020
- 2020-06-09 TW TW109119311A patent/TWI759759B/en active
- 2020-07-17 CN CN202010691410.0A patent/CN113781198A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140201061A1 (en) * | 2013-01-14 | 2014-07-17 | Wonga Technology Limited | On-line automated loan system |
| US20150278941A1 (en) * | 2014-03-26 | 2015-10-01 | Wonga Technology Limited | Loan automation system |
| CN107067319A (en) * | 2017-03-13 | 2017-08-18 | 平安科技（深圳）有限公司 | Loan limit measuring method and device |
| TWM549928U (en) * | 2017-06-16 | 2017-10-01 | Ctbc Bank Co Ltd | Online real-time credit analysis and approval server unit |
| CN108648074A (en) * | 2018-05-18 | 2018-10-12 | 深圳壹账通智能科技有限公司 | Loan valuation method, apparatus based on support vector machines and equipment |
| CN108961040A (en) * | 2018-06-29 | 2018-12-07 | 重庆富民银行股份有限公司 | Loan limit assessment system and method for credit extension loan |
| CN109166033A (en) * | 2018-09-03 | 2019-01-08 | 平安国际融资租赁有限公司 | Loan limit calculation method, device, computer equipment and storage medium |
| TWM577559U (en) * | 2018-11-30 | 2019-05-01 | 中國信託商業銀行股份有限公司 | Evaluation system for unsecured relocation loan amount |
| CN109711981A (en) * | 2018-12-28 | 2019-05-03 | 上海点融信息科技有限责任公司 | The method, apparatus and storage medium of the accrediting amount are determined based on artificial intelligence |
| CN110060144A (en) * | 2019-03-18 | 2019-07-26 | 平安科技（深圳）有限公司 | Amount model training method, amount appraisal procedure, device, equipment and medium |
| CN110335141A (en) * | 2019-06-29 | 2019-10-15 | 北京淇瑀信息科技有限公司 | A kind of accrediting amount based on multi-model determines method, apparatus and electronic equipment |
| CN110458693A (en) * | 2019-08-08 | 2019-11-15 | 中国建设银行股份有限公司 | A kind of automatic measures and procedures for the examination and approval of business loan, device, storage medium and electronic equipment |
| CN111210341A (en) * | 2020-01-14 | 2020-05-29 | 中国建设银行股份有限公司 | Method and device for determining service quota |
Also Published As
| Publication number | Publication date |
|---|---|
| TW202147222A (en) | 2021-12-16 |
| TWI759759B (en) | 2022-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10366394B2 (en) | Service management systems and associated methods | |
| US20110166987A1 (en) | Evaluating Loan Access Using Online Business Transaction Data | |
| US20120330819A1 (en) | System and method for locating and accessing account data | |
| US20120239552A1 (en) | System and method for dynamic working capital | |
| US20140143126A1 (en) | Loan Analysis And Management System | |
| US20120029949A1 (en) | Method And System For Determining Rate Of Insurance | |
| KR20020016769A (en) | Application apparatus and method | |
| US20130275279A1 (en) | Engine, system and method of providing a multi-platform payment and information exchange | |
| US20150379591A1 (en) | Method, System, And Software For Generating Performance Metrics Of Charity Effectiveness | |
| Abrahams et al. | Fair lending compliance: Intelligence and implications for credit risk management | |
| US20140164293A1 (en) | Systems and methods for online securitization of illiquid assets | |
| US20100153262A1 (en) | System and method for administering insurance and loan accounts | |
| Boshoff et al. | Investigating the use of Automated Valuation Models (AVMs) in the South African commercial property market | |
| Maigua | Determinants of Loan Repayment Default in Micro-finance Institutions in Kenya | |
| CN113781198A (en) | Enterprise loan application evaluation system | |
| Mutamimah et al. | Corporate governance innovation framework to reduce credit risk in MSMEs using blockchain technology | |
| ADELEYE | Impact of Cashless Policy on the Performance of Deposit Money Banks in Nigeria | |
| Deltas et al. | Free Riding on the Search of Others: Information Externalities in the Mortgage Industry | |
| JP7231296B1 (en) | Information processing device, information processing method and program | |
| Zhao | Contemporary working capital practices in Australia | |
| Than | Customer perception of home loan in Yoma Bank | |
| Callender | Fundamentals for Factors | |
| Tsai et al. | A General Pricing Model for a Mortgage Insurance Contract Considering the Effects of Multivariate Random Variables on Termination Probabilities and Loss Rate | |
| Win | PERCEPTION OF PENSIONERS ON E-PENSION SERVICE OF MYANMA ECONOMIC BANK | |
| Elliott | Exploring the Economic Potential of a Mobile Financial System in Jamaica |
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 |