CN116843445A - User credit business assessment method based on big data - Google Patents
User credit business assessment method based on big data Download PDFInfo
- Publication number
- CN116843445A CN116843445A CN202310558933.1A CN202310558933A CN116843445A CN 116843445 A CN116843445 A CN 116843445A CN 202310558933 A CN202310558933 A CN 202310558933A CN 116843445 A CN116843445 A CN 116843445A
- Authority
- CN
- China
- Prior art keywords
- credit
- historical
- enterprise
- business
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012502 risk assessment Methods 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 6
- 238000011084 recovery Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000007306 turnover Effects 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 abstract 1
- 238000012550 audit Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a user credit business assessment method based on big data, which relates to the technical field of credit risk assessment, and comprises the following steps: acquiring historical lending records of enterprise users, establishing a scoring card, and further carrying out grade evaluation on the enterprise users and obtaining user credit values; acquiring a historical credit business record of a bank, and further establishing a credit risk assessment model; inputting the credit business selected by the enterprise user into a credit risk assessment model so as to assess the risk level of the credit business selected by the enterprise user; intelligently adjusting the selected credit business according to the risk level thereof; according to the application, the grading evaluation is carried out on the enterprise user by establishing the grading card, and meanwhile, the credit risk evaluation model is established, so that the credit business selected by the enterprise user is intelligently adjusted, the accuracy of the credit risk evaluation is improved to a certain extent, and the credit risk is reduced.
Description
Technical Field
The application relates to the technical field of credit risk assessment, in particular to a user credit business assessment method based on big data.
Background
Banking credit business refers to a form of value movement subject to repayment and payment, and generally includes credit activities such as bank deposit, loan, etc.; because of the industry characteristics of credit business and risk management and control requirements, risk assessment on credit, financial conditions and other aspects is required to be carried out on a user applying for loans, so that repayment risk of the user is judged;
in the prior art, the risk of the credit business is predicted mainly by a logistic regression analysis method, and the risk of the credit business is evaluated by analyzing the correlation degree between each factor and default, but the method cannot extract the characteristics of the information of the user, and further cannot evaluate the risk of the credit business from multiple aspects, and the accuracy and the logic lack confidence, so that the method for evaluating the credit business of the user based on big data is provided.
Disclosure of Invention
In order to solve the technical problems, the application aims to provide a user credit service assessment method based on big data.
In order to achieve the above object, the present application provides the following technical solutions: a user credit business assessment method based on big data comprises the following steps:
acquiring historical borrowing records of enterprise users, establishing a scoring card, performing grade evaluation on the enterprise users to obtain grade scores L, and simultaneously calculating user potential values W according to the historical annual business records of the enterprise users and the enterprise assets, and multiplying the user potential values W with the grade scores L to obtain user credit values of the enterprise users;
acquiring a historical credit business record of a bank, further establishing a credit risk assessment model, and setting a credit risk level;
according to the historical lending record of the enterprise user, the enterprise guarantee condition and the user credit value, calculating the predicted default rate F and the predicted credit asset recovery rate G, inputting the credit business selected by the enterprise user into a credit risk assessment model, and assessing the risk level of the credit business selected by the enterprise user;
and intelligently adjusting the credit business selected by the enterprise user according to the risk level of the credit business, and monitoring and tracking the issued credit business in real time.
Further, the establishment process of the scoring card includes:
acquiring relevant information of the enterprise user according to the identity information of the enterprise user, wherein the relevant information comprises the annual business value of the enterprise, the enterprise asset, the enterprise guarantee condition and the historical loan records of each bank;
setting the initial grade score L of the enterprise user as 0, and intelligently adjusting the initial grade score L of the enterprise user according to the related information of the enterprise user.
Further, the calculation process of the user potential value W includes:
acquiring historical annual business records of enterprise users and historical enterprise asset records, and finding out the maximum historical business amount P from the historical annual business records max Minimum historical sales P min Maximum historic enterprise asset Q max Minimum historic enterprise asset Q min Further normalizing the historical year business balance record and the historical business balance and the historical business assets in the historical business asset record, wherein the normalization formula is as follows:
wherein P is j Operating the normalized turnover value of the jth year for the enterprise user, Q j Normalized enterprise asset value, p, for the j-th year of an enterprise user j 、q j Respectively representing the historical sales and the historical enterprise assets of the j-th year operated by the enterprise user, wherein j is a natural number greater than 0;
calculating a user potential value W of an enterprise user, wherein the calculation formula is as follows:
when n=1, the number of the n-type switches,
where n is the total business year of the enterprise user, α j Is a coefficient set according to the enterprise asset.
Further, the credit risk assessment model building process includes:
acquiring all historical credit business records of a bank, and numbering all the historical credit business records H 1 、H 2 、……、H n Wherein n is a positive integer greater than 3The history credit business record comprises the name of the history credit business, a borrowing limit value A, a history default rate M, a post-default credit asset recovery rate N, a corresponding guarantee value part C and an average repayment period Y;
the borrowing amount A and the corresponding guarantee value part C are values obtained by adopting the same normalization method as that of the historical annual service amount to obtain each historical borrowing amount and each historical guarantee value;
setting a history credit service information set S (H n )＝{A n ，M n ，N n ，C n ，Y n }；
According to historical credit service information set S (H n ) The credit risk value K of the corresponding historical credit business is calculated according to the data of the historical credit business, and the calculation formula is as follows:
wherein K is n The representation number is H n Credit risk values for historical credit transactions of (a).
Further, the setting process of the credit risk level comprises the following steps:
arranging credit risk values of each historical credit business from small to large and setting serial numbers q1, q2, … … and q for the credit risk values n Setting two initial threshold values a and b of 0, starting from a serial number q1, searching a serial number with a first corresponding index number greater than or equal to n/3, assigning a corresponding credit risk value to a, searching a serial number with a first corresponding index number greater than or equal to 2n/3, and assigning a corresponding credit risk value to b; setting a risk assessment threshold interval, and further evaluating the risk level of each historical credit business;
for historical credit transactions with credit risk values in a threshold interval (0, a), rated as low risk credit, a green icon is set;
for historical credit transactions with credit risk values in the threshold interval [ a, b), rating as medium risk credit, setting a yellow icon;
for historical credit transactions with credit risk values in the threshold interval [ b, + ], rated as high risk credit, a red icon is set.
Further, the calculating process of the estimated default rate F and the estimated credit asset recovery rate G comprises the following steps:
according to the credit business selected by the enterprise user, matching historical credit business with the same borrowing line and the same average repayment period from a historical credit business record of a bank, normalizing the borrowing line of the credit business selected by the enterprise user and the enterprise guarantee condition thereof according to the historical borrowing record of the enterprise user to obtain a corresponding borrowing line value and a corresponding guarantee value, and calculating the estimated default rate F and the estimated credit asset recovery G of the credit business selected by the enterprise user according to the historical default rate and the credit asset recovery after default in the matched historical credit business and the historical borrowing record, the corresponding guarantee value and the user credit value of the enterprise user;
wherein the calculation formula of the predicted default rate F and the predicted credit asset recovery rate G is:
wherein Num is the historical violating times of the enterprise users, num is the total historical lending times of the enterprise users, delta epsilon (0, 1), and omega is a coefficient larger than 0.
Further, when the enterprise user performs credit service selection, the historical credit record of the enterprise user is automatically called, the historical credit service which is the same as the current credit limit of the enterprise user is called from the historical credit service record of the bank according to the credit limit and the average repayment limit in the historical credit record of the enterprise user, and the enterprise user can refer to or directly select the recommended historical credit service to select the credit service.
Further, the process of intelligently adjusting the credit business comprises:
if the risk level of the credit business selected by the enterprise user is low-risk credit, not modifying, and sending a prompt for improving the borrowing amount to the enterprise user;
if the risk level of the credit business selected by the enterprise user is the risk credit of the risk, the borrowing amount in the credit business is adjusted downwards, and the adjusted risk level is obtained;
if the risk level of the credit business selected by the enterprise user is high-risk credit, the borrowing amount in the credit business is adjusted downwards, the repayment time is shortened, and the adjusted risk level is obtained.
Compared with the prior art, the application has the beneficial effects that:
1. according to the application, a scoring card is established, historical credit business records of a user in each bank and relevant information of the user are obtained and substituted into the scoring card, so that the grade score of the user is obtained, meanwhile, the potential value of the user is calculated according to the historical annual business records of the user and enterprise assets, and the potential value of the user is multiplied by the grade score of the user, so that the reputation value of the user is obtained, and the user can be accurately and comprehensively evaluated by obtaining a plurality of influencing factors, so that a guarantee is provided for subsequently evaluating the risk grade of the credit business selected by the user;
2. according to the application, a risk assessment model is established through the historical credit business records of the bank, the estimated default probability and the estimated credit asset recovery rate are obtained according to the historical default records and the mortgage asset values of the user, the risk grade of the credit business selected by the user is further assessed, and intelligent adjustment is performed according to the risk assessment result, so that the accuracy and the strong adaptability of risk assessment of the credit business are improved to a certain extent.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.
FIG. 1 is a flow chart of the method of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail below. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, based on the examples herein, which are within the scope of the application as defined by the claims, will be within the scope of the application as defined by the claims.
As shown in fig. 1, the present application provides a user credit service assessment method based on big data, the method comprising the steps of:
step one, acquiring historical lending records of enterprise users and establishing a scoring card, and further performing grade evaluation on the enterprise users and acquiring user credit values;
specifically, the enterprise user sends a credit service one-time application and identity information to the bank, wherein the identity information comprises the name of the enterprise, the location of the enterprise, the legal representative, the operating qualification and the contact mode:
the bank auditor acquires historical credit business records of the enterprise user at each bank according to the identity information of the enterprise user, if the historical credit business records show that the enterprise user has more than three default records, the bank auditor refuses to apply for the credit business of the enterprise user once, and if the default records are less than or equal to three times, the bank auditor applies for the credit business of the enterprise user once through the credit business of the enterprise user;
further, a scoring card is established, relevant information of the enterprise user is obtained according to the identity information of the enterprise user and substituted into the scoring card, and then the grade score of the enterprise user is obtained;
the establishment process of the grading card comprises the following steps:
the relevant information of the enterprise user comprises annual business amount of the enterprise, enterprise assets, enterprise guarantee status and historical loan records at each bank;
setting the initial grade score L of the enterprise user as 0, and intelligently adjusting the initial grade score L of the enterprise user according to the related information of the enterprise user;
the scoring card includes the following rules:
according to the annual business of enterprise users, if the annual business is below 3000000, the grade score L is unchanged, if the annual business is between [3000000,500000 ], the grade score L is added with 1, if the annual business is between [500000,1000000], the grade score L is added with 2, and if the annual business is above 1000000, the grade score L is added with 4;
according to enterprise assets of enterprise users, if the enterprise assets are below 100000, the grade score L is unchanged, if the enterprise assets are above [100000,500000], the grade score L is increased by 1, if the enterprise assets are between (500000, 1000000), the grade score L is increased by 2, if the enterprise assets are between (1000000, 3000000), the grade score L is increased by 3, and if the enterprise assets are above 3000000, the grade score L is increased by 4;
obtaining the total value of the enterprise according to the enterprise guarantee condition of enterprise users, wherein the grade score L is unchanged if the total value of the enterprise is below 500000, the grade score L is added with 1 if the total value of the enterprise is between [500000 and 200000], the grade score L is added with 2 if the total value of the enterprise is between 200000 and 500000, and the grade score L is added with 4 if the total value of the enterprise is above 500000;
obtaining a credit borrowing limit according to historical borrowing records of each bank of an enterprise user, wherein if the credit borrowing limit is below 500000, the grade score L is unchanged, if the credit borrowing limit is between [500000,3000000 ], the grade score L is added with 2, if the credit borrowing limit is between [3000000,10000000), the grade score L is added with 4, if one default record exists in the historical borrowing record, the grade score L is subtracted by 5, if two default records exist in the historical borrowing record, the grade score L is subtracted by 10, and if three default records exist in the historical borrowing record, the grade score is cleared;
acquiring historical annual business records of enterprise users and historical enterprise asset records, and finding out the maximum historical business amount P from the historical annual business records max Minimum historical sales P min Most preferably, theLarge historic Enterprise asset Q max Minimum historic enterprise asset Q min Further normalizing the historical year business balance record and the historical business balance and the historical business assets in the historical business asset record, wherein the normalization formula is as follows:
wherein P is j Operating the normalized turnover value of the jth year for the enterprise user, Q j Normalized enterprise asset value, p, for the j-th year of an enterprise user j 、q j Respectively representing the historical sales and the historical enterprise assets of the j-th year operated by the enterprise user, wherein j is a natural number greater than 0;
further, calculating a user potential value W of the enterprise user, wherein the calculation formula is as follows:
when n=1, the number of the n-type switches,
where n is the total business year of the enterprise user, α j Is a coefficient set according to the enterprise asset;
further multiplying the grade value L of the enterprise user and the user potential value to obtain a user credit value;
it should be noted that, according to the user credit value, the upper limit of the credit line and the loan interest rate of the enterprise user are adjusted, for the enterprise user with the user credit value between [0,5 ], the upper limit of the credit line and the loan interest rate are unchanged, for the enterprise user with the user credit value between [5,15 ], the upper limit of the credit line is increased by 10%, the loan interest rate is reduced by 0.5%, for the enterprise user with the user credit value between [15, infinity), the upper limit of the credit line is increased by 20%, the loan interest rate is reduced by 1%, for example, the original credit line of the enterprise user is 100000, the loan interest rate is 4.35%, and after the user credit value is updated, the upper limit of the credit line of the enterprise user is updated to 110000, and the loan interest rate is updated to 3.85%;
step two, acquiring a historical credit business record of a bank, and further establishing a credit risk assessment model;
specifically, all historical credit business records of the bank are acquired, and all historical credit business records are numbered, for example, H 1 、H 2 、……、H n Wherein N is a positive integer greater than 3, the history credit transaction record includes the name of the history credit transaction, the borrowing amount value A, the history default M, the recovery rate N of the credit asset after default, the corresponding guarantee value component C and the average repayment period Y;
the borrowing amount A and the corresponding guarantee value part C are values obtained by adopting the same normalization method as that of the historical annual service amount to obtain each historical borrowing amount and each historical guarantee value;
a credit risk assessment model is established based on a historical credit business, and the concrete process is as follows:
setting a history credit service information set S (H n )＝{A n ，M n ，N n ，C n ，Y n }；
According to historical credit service information set S (H n ) The credit risk value K of the corresponding historical credit business is calculated according to the data of the historical credit business, and the calculation formula is as follows:
wherein K is n The representation number is H n A credit risk value for a historical credit transaction of (a);
arranging credit risk values of each historical credit business from small to large and setting serial numbers q1, q2, … … and q for the credit risk values n Setting two initial thresholds a and b of 0, and sequentiallyStarting from the column number q1, searching a serial number with a first corresponding index number greater than or equal to n/3, assigning a corresponding credit risk value to a, searching a serial number with a first corresponding index number greater than or equal to 2n/3, and assigning a corresponding credit risk value to b; setting a risk assessment threshold interval, and further evaluating the risk level of each historical credit business;
for historical credit transactions with credit risk values in a threshold interval (0, a), rated as low risk credit, a green icon is set;
for historical credit transactions with credit risk values in the threshold interval [ a, b), rating as medium risk credit, setting a yellow icon;
for historical credit transactions with credit risk values in the threshold interval [ b, + ], rated as high risk credit, a red icon is set.
Inputting the credit business selected by the enterprise user into a credit risk assessment model so as to assess the risk level of the credit business selected by the enterprise user;
specifically, after the first application of the credit business submitted by the enterprise user passes, a bank auditor carries out secondary audit according to the user credit value of the enterprise user, if the user credit value of the enterprise user is smaller than 0, an 'application not passing' prompt is sent to the enterprise user, and if the user credit value of the enterprise user is equal to or larger than 0, an 'application passing' prompt is sent to the enterprise user;
after receiving the prompt of 'pass through application', the enterprise user uploads the selected credit business, wherein the credit business comprises a borrowing amount and an average repayment period;
the bank auditor obtains the credit limit upper limit, the enterprise on-credit condition, the enterprise guarantee condition and the user credit value according to the identity information of the enterprise user;
obtaining the current lendable line of the enterprise user and comparing the current lendable line with the borrowed line in the uploaded credit service according to the upper limit of the credit line of the enterprise user and the lending condition of the enterprise, and sending a prompt of exceeding the upper limit to the enterprise user if the current lendable line is greater than the borrowed line in the credit service;
if the current lendable amount is smaller than or equal to the borrowing amount in the credit business, setting a loan interest rate according to the user credit value of the enterprise user and the selected average repayment deadline;
further, according to the credit business selected by the enterprise user, matching historical credit business with the same borrowing amount and the same average repayment term from the historical credit business record of the bank, normalizing the borrowing amount of the credit business selected by the enterprise user and the enterprise guarantee condition thereof according to the historical borrowing record of the enterprise user to obtain a corresponding borrowing amount value and a corresponding guarantee value part, and calculating the estimated default rate F and the estimated credit asset recovery G of the credit business selected by the enterprise user according to the historical default rate and the credit asset recovery rate after default in the matched historical credit business, the historical borrowing record of the enterprise user, the corresponding guarantee value part and the user credit value;
wherein the calculation formula of the predicted default rate F and the predicted credit asset recovery rate G is:
wherein Num is the historical violating times of the enterprise user, num is the total historical lending times of the enterprise user, delta epsilon (0, 1), and omega is a coefficient larger than 0;
the borrowing limit value, the corresponding guarantee value score, the average repayment limit, the predicted default F and the predicted credit asset recovery G of the credit business selected by the enterprise user are input into a credit risk assessment model, and then the credit risk value of the credit business selected by the enterprise user is calculated;
judging the risk level of the credit risk value according to the threshold value interval of the credit risk value;
it should be noted that, when the enterprise user performs credit service selection, the historical credit record of the enterprise user is automatically called, the historical credit service which is the same as the current lendable line of the enterprise user is called from the historical credit record of the bank according to the credit line and the average repayment limit in the historical credit record of the enterprise user, and the enterprise user can refer to or directly select the recommended historical credit service to select the credit service.
Step four, intelligently adjusting the selected credit business according to the risk level of the credit business, and monitoring and tracking the issued credit business in real time;
specifically, if the risk level of the credit business selected by the enterprise user is low risk credit, the modification is not performed, and a prompt for improving the borrowing amount is sent to the enterprise user;
if the risk level of the credit business selected by the enterprise user is the risk credit of the risk, the borrowing amount in the credit business is adjusted downwards, and the adjusted risk level is obtained;
if the risk level of the credit business selected by the enterprise user is high-risk credit, the borrowing amount in the credit business is adjusted downwards, the repayment time is shortened, and the adjusted risk level is obtained;
transmitting the adjusted credit business and the unadjusted credit business to enterprise users simultaneously, marking the risk levels of the adjusted credit business and the unadjusted credit business, and transmitting a historical credit business with the same risk level as the adjusted credit business to the enterprise users simultaneously for the enterprise users to use as a reference;
after the enterprise user determines the credit business, the bank distributes the borrowing amount according to the credit business selected by the enterprise user, and simultaneously monitors and tracks the operation condition and repayment condition of the enterprise user in real time;
updating corresponding user potential values in real time according to the business conditions of enterprise users, and further updating the upper limit of credit line and loan interest rate;
and sending overdue prompts to the enterprise users according to the repayment conditions of the enterprise users if overdue conditions occur, automatically judging the default of the enterprise users if overdue is performed for more than three times, and adopting forced compensation.
The above embodiments are only for illustrating the technical method of the present application and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present application may be modified or substituted without departing from the spirit and scope of the technical method of the present application.
Claims (8)
1. The user credit service assessment method based on big data is characterized by comprising the following steps:
acquiring historical borrowing records of enterprise users, establishing a scoring card, performing grade evaluation on the enterprise users to obtain grade scores L, and simultaneously calculating user potential values W according to the historical annual business records of the enterprise users and the enterprise assets, and multiplying the user potential values W with the grade scores L to obtain user credit values of the enterprise users;
acquiring a historical credit business record of a bank, further establishing a credit risk assessment model, and setting a credit risk level;
according to the historical lending record of the enterprise user, the enterprise guarantee condition and the user credit value, calculating the predicted default rate F and the predicted credit asset recovery rate G, inputting the credit business selected by the enterprise user into a credit risk assessment model, and assessing the risk level of the credit business selected by the enterprise user;
and intelligently adjusting the credit business selected by the enterprise user according to the risk level of the credit business, and monitoring and tracking the issued credit business in real time.
2. The big data based user credit business assessment method according to claim 1, wherein the process of establishing the scoring card comprises:
acquiring relevant information of the enterprise user according to the identity information of the enterprise user, wherein the relevant information comprises the annual business value of the enterprise, the enterprise asset, the enterprise guarantee condition and the historical loan records of each bank;
setting the initial grade score L of the enterprise user as 0, and intelligently adjusting the initial grade score L of the enterprise user according to the related information of the enterprise user.
3. The big data based user credit business assessment method according to claim 1, wherein the calculation process of the user potential value W comprises:
acquiring historical annual business records of enterprise users and historical enterprise asset records, and finding out the maximum historical business amount P from the historical annual business records max Minimum historical sales P min Maximum historic enterprise asset Q max Minimum historic enterprise asset Q min Further normalizing the historical year business balance record and the historical business balance and the historical business assets in the historical business asset record, wherein the normalization formula is as follows:
wherein P is j Operating the normalized turnover value of the jth year for the enterprise user, Q j Normalized enterprise asset value, p, for the j-th year of an enterprise user j 、q j Respectively representing the historical sales and the historical enterprise assets of the j-th year operated by the enterprise user, wherein j is a natural number greater than 0;
calculating a user potential value W of an enterprise user, wherein the calculation formula is as follows:
when n=1, the number of the n-type switches,
where n is the total business year of the enterprise user, α j Is a coefficient set according to the enterprise asset.
4. The big data based user credit business assessment method according to claim 1, wherein the credit risk assessment model building process comprises:
acquiring all historical credit business records of a bank, and numbering H the historical credit business records 1 、H 2 、……、H n Wherein N is a positive integer greater than 3, the history credit transaction record includes the name of the history credit transaction, the borrowing amount value A, the history default M, the recovery rate N of the credit asset after default, the corresponding guarantee value component C and the average repayment period Y;
the borrowing amount A and the corresponding guarantee value part C are values obtained by adopting the same normalization method as that of the historical annual service amount to obtain each historical borrowing amount and each historical guarantee value;
setting a history credit service information set S (H n )＝{A n ，M n ，N n ，C n ，Y n }；
According to historical credit service information set S (H n ) The credit risk value K of the corresponding historical credit business is calculated according to the data of the historical credit business, and the calculation formula is as follows:
wherein K is n The representation number is H n Credit risk values for historical credit transactions of (a).
5. The big data based user credit business assessment method according to claim 4, wherein the credit risk level setting process comprises:
arranging credit risk values of each historical credit business from small to large and setting serial numbers q1, q2, … … and q for the credit risk values n Setting two initial thresholds a and b of 0, starting from the sequence number q1, searching for the first sequence number with the corresponding index greater than or equal to n/3, and comparing the first sequence number with the second sequence numberAssigning a corresponding credit risk value to a, searching a serial number with a first corresponding index number greater than or equal to 2n/3, and assigning a corresponding credit risk value to b;
setting a risk assessment threshold interval, and further evaluating the risk level of each historical credit business;
for historical credit transactions with credit risk values in a threshold interval (0, a), rated as low risk credit, a green icon is set;
for historical credit transactions with credit risk values in the threshold interval [ a, b), rating as medium risk credit, setting a yellow icon;
for historical credit transactions with credit risk values in the threshold interval [ b, + ], rated as high risk credit, a red icon is set.
6. A method of user credit transaction assessment based on big data according to claim 3, wherein the calculation of the estimated default rate F and estimated credit asset recovery G comprises:
according to the credit business selected by the enterprise user, matching historical credit business with the same borrowing amount and the same average repayment period from historical credit business records of the bank, normalizing the borrowing amount of the credit business selected by the enterprise user and the enterprise guarantee condition thereof according to the historical borrowing records of the enterprise user to obtain corresponding borrowing amount values and corresponding guarantee value fractions, and calculating the expected default rate F and the expected credit asset recovery rate G of the credit business selected by the enterprise user according to the history default rate and the credit asset recovery rate after default in the matched historical credit business and the historical borrowing records, the corresponding guarantee value fractions and the user credit value of the enterprise user;
wherein the calculation formula of the predicted default rate F and the predicted credit asset recovery rate G is:
wherein Num is the historical violating times of the enterprise users, num is the total historical lending times of the enterprise users, delta epsilon (0, 1), and omega is a coefficient larger than 0.
7. The method according to claim 6, wherein when the enterprise user performs credit service selection, the historical credit record of the enterprise user is automatically called, the historical credit service identical to the current credit limit of the enterprise user is called from the historical credit record of the bank according to the credit limit and the average repayment limit of the historical credit record of the enterprise user, and the enterprise user can refer to or directly select the recommended historical credit service to select the credit service.
8. The big data based user credit transaction assessment method according to claim 6, wherein the process of intelligently adjusting the credit transaction comprises:
if the risk level of the credit business selected by the enterprise user is low-risk credit, not modifying, and sending a prompt for improving the borrowing amount to the enterprise user;
if the risk level of the credit business selected by the enterprise user is the risk credit of the risk, the borrowing amount in the credit business is adjusted downwards, and the adjusted risk level is obtained;
if the risk level of the credit business selected by the enterprise user is high-risk credit, the borrowing amount in the credit business is adjusted downwards, the repayment time is shortened, and the adjusted risk level is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310558933.1A CN116843445A (en) | 2023-05-18 | 2023-05-18 | User credit business assessment method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310558933.1A CN116843445A (en) | 2023-05-18 | 2023-05-18 | User credit business assessment method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116843445A true CN116843445A (en) | 2023-10-03 |
Family
ID=88158797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310558933.1A Pending CN116843445A (en) | 2023-05-18 | 2023-05-18 | User credit business assessment method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116843445A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160071113A (en) * | 2014-12-11 | 2016-06-21 | 주식회사 쎄븐 | Obligation management system for evaluating risk of obligation and method thereof |
| CN106779310A (en) * | 2016-11-25 | 2017-05-31 | 太原钢铁(集团)有限公司 | The method that credit sale risk management and control is realized using ERP System |
| CN108921689A (en) * | 2018-06-29 | 2018-11-30 | 重庆富民银行股份有限公司 | Credit risk monitoring system and method |
| CN112926651A (en) * | 2021-02-24 | 2021-06-08 | 苏州黑云智能科技有限公司 | Enterprise credit assessment method and system |
| CN113689289A (en) * | 2021-08-26 | 2021-11-23 | 天元大数据信用管理有限公司 | Method and equipment based on bank risk control |
| CN114971883A (en) * | 2022-06-27 | 2022-08-30 | 贵州省农村信用社联合社 | Small and micro enterprise credit risk assessment analysis system based on big data |
| CN115936841A (en) * | 2022-11-22 | 2023-04-07 | 中电金信软件有限公司 | Method and device for constructing credit risk assessment model |
-
2023
- 2023-05-18 CN CN202310558933.1A patent/CN116843445A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160071113A (en) * | 2014-12-11 | 2016-06-21 | 주식회사 쎄븐 | Obligation management system for evaluating risk of obligation and method thereof |
| CN106779310A (en) * | 2016-11-25 | 2017-05-31 | 太原钢铁(集团)有限公司 | The method that credit sale risk management and control is realized using ERP System |
| CN108921689A (en) * | 2018-06-29 | 2018-11-30 | 重庆富民银行股份有限公司 | Credit risk monitoring system and method |
| CN112926651A (en) * | 2021-02-24 | 2021-06-08 | 苏州黑云智能科技有限公司 | Enterprise credit assessment method and system |
| CN113689289A (en) * | 2021-08-26 | 2021-11-23 | 天元大数据信用管理有限公司 | Method and equipment based on bank risk control |
| CN114971883A (en) * | 2022-06-27 | 2022-08-30 | 贵州省农村信用社联合社 | Small and micro enterprise credit risk assessment analysis system based on big data |
| CN115936841A (en) * | 2022-11-22 | 2023-04-07 | 中电金信软件有限公司 | Method and device for constructing credit risk assessment model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107403326A (en) | A kind of Insurance Fraud recognition methods and device based on teledata | |
| CN106651570A (en) | System and method for real-time loan approval | |
| CN111324862A (en) | Method and system for monitoring behavior in loan | |
| CN108492001A (en) | A method of being used for guaranteed loan network risk management | |
| Chen et al. | Loan default prediction using diversified sensitivity undersampling | |
| CN110610413A (en) | Loan transaction risk control method and system | |
| CN115271912A (en) | Credit business intelligent wind control approval system and method based on big data | |
| CN112232950A (en) | Loan risk assessment method and device, equipment and computer-readable storage medium | |
| CN110728568A (en) | Credit credit line method and system for credit investigation blank client | |
| CN109146667B (en) | Method for constructing external interface comprehensive application model based on quantitative statistics | |
| Zhou | Data mining for individual consumer credit default prediction under e-commence context: a comparative study | |
| US20100042446A1 (en) | Systems and methods for providing core property review | |
| Chen | Prediction and analysis of financial default loan behavior based on machine learning model | |
| CN116342247A (en) | Authorization management and control method, device, equipment and storage medium for credit support | |
| CN116843445A (en) | User credit business assessment method based on big data | |
| Buanaputra | Is there any interaction between real earnings management and accrual-based earnings management? | |
| CN109801162A (en) | A kind of credit rating method that social media data are merged with multi-standard cross-certification | |
| Raei et al. | A hybrid model for estimating the probability of default of corporate customers | |
| Lakshmi et al. | Machine learning approach for taxation analysis using classification techniques | |
| CN111681090A (en) | Account grouping method and device of business system, terminal equipment and storage medium | |
| Lin et al. | Research on Credit Big Data Algorithm Based on Logistic Regression | |
| You et al. | Evaluating reputation of internet financial platform: An improved fuzzy evaluation approach | |
| Suprihanto et al. | Determination of weighting assessment on DREAD model using profile matching | |
| Lei | Financial Technology and China's Inclusive Finance | |
| Kumar et al. | Data Mining in Credit Scoring and Future Application |
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 |