CN115409631A - Financial data analysis and prediction platform based on big data modeling - Google Patents
Financial data analysis and prediction platform based on big data modeling Download PDFInfo
- Publication number
- CN115409631A CN115409631A CN202210921012.2A CN202210921012A CN115409631A CN 115409631 A CN115409631 A CN 115409631A CN 202210921012 A CN202210921012 A CN 202210921012A CN 115409631 A CN115409631 A CN 115409631A
- Authority
- CN
- China
- Prior art keywords
- data
- rate
- asset
- repayment
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Abstract
The invention discloses a financial data analysis and prediction platform based on big data modeling, wherein a data processing unit receives data files and carries out structured association processing on the data files; a model establishing unit for establishing an analysis prediction model and outputting the repayment rate of the tangible assets, the repayment rate of the intangible assets and the repayment rate of the revenues by operating the analysis prediction model; the weight distribution unit is used for calculating the association degree between the management target and the intangible asset and carrying out weight distribution on the repayment rate of the intangible asset and the repayment rate of the tangible asset according to the association degree; and the data analysis and prediction unit is used for outputting the loan risk according to the total amount of the repayment rate and the guarantee rate of the loan money. By adopting the technical scheme, more comprehensive and real financial data and main body information are collected through a network channel and a big data technology, a reasonable evaluation mode for enterprise assets is introduced, the repayment capability of an enterprise for borrowing is judged, and the risk of the borrowing money is more reasonably and accurately predicted.
Description
Technical Field
The invention relates to the technical field of financial big data analysis, in particular to a financial data analysis and prediction platform based on big data modeling.
Background
In the financial industry, risk control is a very important link, especially for banks, because companies applying financing and loan do not have repayment capability, the open accounts and bad accounts of banks are increasing continuously, and banking business is susceptible to very serious influence, so when enterprises apply financing or loan, the enterprises need to evaluate assets and earnings of the enterprises in advance, judge the repayment capability of the enterprises, and determine the risk of loan.
In the prior art, the evaluation of the loan risk is mainly carried out through manual review of bank personnel according to written materials such as audit reports provided by enterprises, the problems existing in the evaluation are very obvious, the written materials such as the audit reports cannot reflect the operating conditions of the enterprises comprehensively and truly, different types of enterprises have different ways of judging the revenue capacities, in addition, the manual review lacks of a unified review standard, and meanwhile, the review result has the influence of subjective factors.
Disclosure of Invention
The purpose of the invention is as follows: the invention provides a financial data analysis and prediction platform based on big data modeling, which collects more comprehensive and real financial data and main information through a network channel and a big data technology on the basis of data files provided by enterprises, determines the value of assets owned by the enterprises according to main profit marks of the enterprises, further judges the repayment capacity of the enterprises for the money, and analyzes and predicts the risk of the loaning more reasonably and accurately.
The technical scheme is as follows: the invention provides a financial data analysis and prediction platform based on big data modeling, which comprises: the system comprises a human-computer interaction interface, a data processing unit, a model establishing unit, a weight distribution unit and a data analysis and prediction unit, wherein: the human-computer interaction interface is used for displaying the data files of the input platform in an icon form, displaying an algorithm for processing the data files and displaying results output by the data analysis and prediction unit; the data processing unit receives the data file and performs structural association processing on the data file; the data file comprises financial data and subject information, the financial data is asset data of a target subject, and the subject information comprises the target subject and an operating target of the target subject; the operation target refers to a product or service for operation of the target main body; the model establishing unit is used for determining a corresponding algorithm according to the type of the operation target, establishing an analysis prediction model, and outputting the repayment rate of the tangible assets, the repayment rate of the intangible assets and the repayment rate of the operation through operating the analysis prediction model; the repayment rate refers to the repayment rate of the subject on the loan; the weight distribution unit is used for calculating the association degree between the management target and the intangible asset and carrying out weight distribution on the repayment rate of the intangible asset and the repayment rate of the tangible asset according to the association degree; and the data analysis and prediction unit is used for outputting the loan risk according to the total amount of the repayment rate and the guarantee rate of the loan money.
Specifically, the structured association processing is performed on the data file, and includes: and establishing a structured association data form according to the investment and invested relation between the main bodies and the intangible assets and tangible assets corresponding to the main bodies, and displaying the structured association data form on a human-computer interaction interface.
Specifically, the performing structural association processing on the data file further includes: retrieving, from a network publishing platform, tangible assets and intangible assets of a target subject; carrying out repeatability check on the asset data obtained by retrieval and the existing asset data, reserving the unrepeated asset data, and bringing the unrepeated asset data into a structured associated data form; mortgage information and judicial action information for the asset is retrieved.
Specifically, retrieving mortgage information and judicial action information for an asset includes: and extracting the amount of the mortgage information and the judicial litigation information on the asset punishment by using semantic identification, and correspondingly deducting the asset data according to the amount.
Specifically, determining a corresponding algorithm according to the type of the business target, and establishing an analysis prediction model, wherein the method comprises the following steps: inquiring the annual patent application number in the technical field of the operation target, if the number exceeds the standard number, determining that the operation target belongs to a technical guide type, otherwise, determining that the operation target belongs to a brand guide type; the service is brand-oriented; the revenue of the technology-oriented operation target exceeds the standard revenue of the target main body, and a random forest algorithm is selected to establish an analysis prediction model; and (4) the revenue of the brand-oriented business target exceeds the revenue of the target main body standard, and a long-term and short-term memory network is selected to establish an analysis and prediction model.
Specifically, the total revenue amount, the historical profit margin, the historical liability data and the research and development investment of a target subject in unit time are input, and the repayment rate of the tangible assets, the repayment rate of the intangible assets and the repayment rate of the revenue are respectively calculated; the historical liability data comprises liability amount and liability frequency; the research and development investment is used as an influence variable of the gross revenue; the value of the intangible asset is calculated according to the following formula:
V＝(S/A)×5PN，
wherein S represents research and development investment, A represents earning total amount, P represents profit margin of the business target, and N represents sales quantity of the business target.
Specifically, pictures of authorized patent documents in the intangible assets are obtained, the similarity between the pictures and products is calculated, and the similarity is used as the association degree between the management target and the intangible assets.
Specifically, the weight is calculated according to the following formula:
Q 1 ＝P×(R+0.5) 2 ；
Q 2 ＝|1-P×(R+0.5) 2 |，
wherein Q 1 Weight of repayment rate for intangible assets, Q 2 R is the degree of association between the subject and the intangible asset.
Specifically, the risk level is calculated based on the total amount of the repayment rate and the profit margin of the loan.
Specifically, the risk level is calculated using the following formula:
R＝Q z +C，
wherein Q is z Denotes the total amount of the repayment rate after the calculation of the weight, C denotes the guarantee rate, R denotes the risk level, and the larger the value of R, the lower the risk.
Has the beneficial effects that: compared with the prior art, the invention has the following remarkable advantages: through a network channel and a big data technology, more comprehensive and real financial data and main body information are collected, a reasonable calculation mode for intangible assets of an enterprise is introduced, the repayment capacity of the enterprise for the money is further judged, and the risk of the loan money is more reasonably and accurately analyzed and predicted.
Drawings
Fig. 1 is a schematic structural diagram of a financial data analysis and prediction platform based on big data modeling according to the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
Referring to fig. 1, a schematic structural diagram of a financial data analysis and prediction platform based on big data modeling according to the present invention is shown.
The invention provides a financial data analysis and prediction platform based on big data modeling, which comprises: the system comprises a human-computer interaction interface, a data processing unit, a model establishing unit, a weight distribution unit and a data analysis prediction unit, wherein: the human-computer interaction interface is used for displaying the data files of the input platform in an icon form, displaying an algorithm for processing the data files and displaying results output by the data analysis and prediction unit; the data processing unit receives the data file and performs structured association processing on the data file; the data file comprises financial data and main body information, the financial data is asset data of a target main body, and the main body information comprises the target main body and a management target of the target main body; the business target refers to a product or service for business of the target main body; the model establishing unit is used for determining a corresponding algorithm according to the type of the operation target, establishing an analysis prediction model, and outputting the repayment rate of the tangible assets, the repayment rate of the intangible assets and the repayment rate of the earnings by operating the analysis prediction model; the repayment rate refers to the repayment rate of the target main body for the loan money; the weight distribution unit is used for calculating the association degree between the management target and the intangible asset and carrying out weight distribution on the repayment rate of the intangible asset and the repayment rate of the tangible asset according to the association degree; and the data analysis and prediction unit is used for outputting the loan risk according to the total amount of the repayment rate and the guarantee rate of the loan money.
In specific implementation, the data file, the algorithm model and the output result can be completely and comprehensively displayed on a human-computer interaction interface, and a user can intuitively observe data information and process conditions. The user can drag the data file to the man-machine interaction interface to input the data file, and the data input operation can be efficiently completed.
In the embodiment of the present invention, performing structured association processing on a data file includes: and establishing a structured association data form according to the investment and invested relation between the main bodies and the intangible assets and tangible assets corresponding to the main bodies, and displaying the structured association data form on a human-computer interaction interface.
In the embodiment of the present invention, performing structured association processing on a data file further includes: retrieving, from a network publishing platform, tangible assets and intangible assets of a target subject; carrying out repeatability inspection on the asset data obtained by retrieval and the existing asset data, reserving the asset data which is not repeated in the asset data, and bringing the asset data into a structured associated data form; mortgage information and judicial action information for the asset is retrieved.
In the embodiment of the invention, the method for searching the mortgage information and the judicial litigation information of the assets comprises the following steps: and extracting the amount of the mortgage information and the judicial litigation information on the asset by using semantic identification, and correspondingly deducting the asset data according to the amount.
In specific implementation, the data processing unit can receive and process asset information and main body information submitted by an enterprise, and can also apply big data technology to retrieve through a network open platform, for a listed company, a related financial report can be retrieved, and the financial report can more specifically record related information of tangible assets, intangible assets, main profit products (services) and the like of the company. For all companies, information can be obtained through a public website, for example, intangible asset data such as patents and trademarks can be inquired, judicial litigation information can be inquired through a referee document public website, and asset mortgage information such as real estate can be inquired. The data processing unit can query according to a preset website and a query path, extracts key information by using a semantic recognition and statement extraction algorithm model after related contents are obtained through query, obtains the amount of mortgage and the amount of asset punishment by judicial action, and deducts asset data correspondingly according to the amount.
In specific implementation, the structured association processing means dividing the data file according to the data type and the association relation, and outputting the corresponding structured association data form. For example, the products and services sold by the target subject are classified into business targets, the properties and vehicles purchased by the target subject are classified into physical assets, and the patents and trademarks of the target subject are classified into intangible assets.
In the embodiment of the invention, a corresponding algorithm is determined according to the type of the business target, and an analysis prediction model is established, wherein the method comprises the following steps: inquiring annual patent application quantity in the technical field of the operation target, if the quantity exceeds the standard quantity (corresponding setting can be carried out according to actual application scenes), determining that the operation target belongs to a technical guide type, and otherwise, determining that the operation target belongs to a brand guide type; the service is brand-oriented; the revenue of the technology-oriented operation target exceeds the standard revenue of the target main body, and a random forest algorithm is selected to establish an analysis prediction model; and (4) the revenue of the brand-oriented business target exceeds the revenue of the target main body standard, and a long-term and short-term memory network is selected to establish an analysis and prediction model.
In the embodiment of the invention, the gross earnings, the historical profit rate, the historical liability data and the research and development investment of a target subject in unit time are input, and the repayment rate of tangible assets, the repayment rate of intangible assets and the repayment rate of earnings are respectively calculated; the historical liability data comprises liability amount and liability frequency; the research and development investment is used as an influence variable (variable in a random forest algorithm) of the total revenue and earnings; the value of the intangible asset is calculated according to the following formula:
V＝(S/A)×5PN，
wherein S represents research and development investment, A represents earning total amount, P represents profit margin of the business object, and N represents sales amount of the business object.
In concrete implementation, the annual patent application quantity in the technical field of all the business targets is inquired, for example, the business targets of the target main body company are mainly household appliances such as an air conditioner and a washing machine, the annual patent application quantity in the technical field of the household appliances can be inquired, the technical development speed and the technological intensive degree in the technical field can be judged visually through the patent application quantity, if the annual patent application quantity exceeds the standard quantity, the technical development speed in the technical field can be determined to be high, the technological intensive degree is high, the business targets belong to the technical guidance type, otherwise, the business targets belong to the brand guidance type. For the technology-oriented business target, the influence of technology research and development is large, the breakthrough or the research and development result of a certain technology can greatly improve the sales volume of products and the value of intangible assets, and further, the technology-oriented business target has a variable of technology, and because the research and development and breakthrough of the technology have certain contingency and are difficult to predict according to historical tracks, while the brand-oriented business target has large value in products and services, and the revenue of a target main body is difficult to break through in a short period, so that the effective prediction can be performed according to the historical tracks.
In specific implementation, the random forest classification algorithm can process a large number of input variables, the importance of the variables is evaluated when the categories are determined, technology research and development and breakthrough can be used as the variables, and revenues in the repayment period of the loan money can be calculated better according to the historical revenues of the enterprise operating targets through the random forest classification algorithm. The long-term and short-term memory network can better analyze and predict according to historical data, so that for the brand-oriented management target, better analysis and prediction can be carried out through the algorithm model, and the earnings and earnings in the repayment period of the loan money are calculated.
In implementations, the value of the tangible asset may be calculated from data submitted by the enterprise, or the corresponding value may be calculated from network public information. The total amount of the operation in the unit time of the target main body is calculated according to the operation of the operation target. And the historical profit margin is obtained by calculating an average value according to the data submitted by the enterprises and the data of other enterprises in the same industry. Historical liability data, and the amount of liability of the target subject is calculated according to the data submitted by the enterprise. The repayment rate is a proportion of the loan amount that can be paid out when other liabilities and the cost of the target subject are deducted, and may be, for example, completely repayed, with a repayment rate of 100%, which is only half, and a repayment rate of 50%.
In the concrete implementation, as the relationship between the value V of the intangible assets, particularly the value of the technology, and the research and development is large, the value of the intangible assets which are difficult to accurately calculate the value is calculated by researching and developing the proportion of the intakes in the total earnings, and the value of the intangible assets is higher for the business target with higher profit margin, so the profit margin is introduced into the calculation.
In the embodiment of the invention, the picture of the authorized patent literature in the intangible asset is obtained, the similarity between the picture and the product is calculated, and the similarity is used as the association degree between the business target and the intangible asset.
In a particular implementation, the value of an intangible asset is significant to the target subject only if the intangible asset, particularly a patent, is associated with its product. However, in some cases, the patents are irrelevant or less relevant to actual sale of products, and the patents are not completely used for protecting the products of the patents, so that the market value of the patents is low. The patent with higher association degree with the product aims to protect the product of the patent, and the market value of the part of the patent is higher. Whether the image is related to the product or not can be judged, and the similarity between the image of the patent document and the product can be calculated. Of course, more elaborate evaluations can also be made by human reading, but the time costs and labor costs incurred are higher.
In the embodiment of the invention, the weight is calculated according to the following formula:
Q 1 ＝P×(R+0.5) 2 ；
Q 2 ＝|1-P×(R+0.5) 2 |，
wherein Q is 1 Weight of repayment rate for intangible assets, Q 2 R is the degree of association between the subject and the intangible asset.
In a specific implementation, in the case that the association degree is higher than 0.5, it can be stated that the protection degree of the intangible asset to the product is greater, and the weight of the intangible asset can be increased.
In the embodiment of the invention, the risk level is calculated according to the total amount of the repayment rate and the profit rate of the loan.
In the embodiment of the invention, the risk level calculation comprises the following steps:
the following formula is adopted for calculation:
R＝Q z +C，
wherein Q is z Denotes the total amount of the repayment rate after the calculation of the weight, C denotes the guarantee rate, R denotes the risk level, and the larger the value of R, the lower the risk.
In particular implementations, the total amount of the payback rate includes the payback rate of the tangible asset, the payback rate of the intangible asset, and the payback rate of the earnings after the weight is calculated. The guarantee rate represents the proportion of the guarantee value provided by the enterprise and the amount of the loan money.
In specific implementation, more comprehensive and real financial data and main body information are collected through a network channel and a big data technology, a reasonable calculation mode for intangible assets of an enterprise is introduced, the repayment capability of the enterprise for the money is further judged, and the risk of the loan money is more reasonably and accurately analyzed and predicted.
Claims (10)
1. A financial data analysis and prediction platform based on big data modeling is characterized by comprising the following components: the system comprises a human-computer interaction interface, a data processing unit, a model establishing unit, a weight distribution unit and a data analysis prediction unit, wherein:
the human-computer interaction interface is used for displaying the data files of the input platform in an icon form, displaying an algorithm for processing the data files and displaying results output by the data analysis and prediction unit;
the data processing unit receives the data file and performs structured association processing on the data file; the data file comprises financial data and subject information, the financial data is asset data of a target subject, and the subject information comprises the target subject and an operating target of the target subject; the business target refers to a product or service for business of the target main body;
the model establishing unit is used for determining a corresponding algorithm according to the type of the operation target, establishing an analysis prediction model, and outputting the repayment rate of the tangible assets, the repayment rate of the intangible assets and the repayment rate of the earnings by operating the analysis prediction model; the repayment rate refers to the repayment rate of the target main body for the loan money;
the weight distribution unit is used for calculating the association degree between the management target and the intangible asset and carrying out weight distribution on the repayment rate of the intangible asset and the repayment rate of the tangible asset according to the association degree;
and the data analysis and prediction unit is used for outputting the loan risk according to the total amount of the repayment rate and the guarantee rate of the loan money.
2. The big-data-modeling-based financial data analysis and prediction platform according to claim 1, wherein the performing of the structured association process on the data file comprises:
and establishing a structured association data form according to the investment and invested relation between the main bodies and the intangible assets and tangible assets corresponding to the main bodies, and displaying the structured association data form on a human-computer interaction interface.
3. The big-data-modeling-based financial data analysis and prediction platform according to claim 2, wherein the performing structured association processing on the data file further comprises:
retrieving, from a network publishing platform, tangible assets and intangible assets of a target subject;
carrying out repeatability inspection on the asset data obtained by retrieval and the existing asset data, reserving the asset data which is not repeated in the asset data, and bringing the asset data into a structured associated data form;
mortgage information and judicial action information for the asset is retrieved.
4. The big-data-modeling-based financial data analytics prediction platform of claim 3 wherein retrieving collateral information and judicial litigation information for an asset comprises:
and extracting the amount of the mortgage information and the judicial litigation information on the asset by using semantic identification, and correspondingly deducting the asset data according to the amount.
5. The financial data analysis and prediction platform based on big data modeling according to claim 4, wherein the determining the corresponding algorithm according to the type of the business objective and establishing the analysis and prediction model comprises:
inquiring the annual patent application number in the technical field of the operation target, if the number exceeds the standard number, determining that the operation target belongs to a technical guide type, otherwise, determining that the operation target belongs to a brand guide type; the service is brand-oriented;
the revenue of the technology-oriented operation target exceeds the standard revenue of the target main body, and a random forest algorithm is selected to establish an analysis prediction model; and (4) the revenue of the brand-oriented business target exceeds the revenue of the target main body standard, and a long-term and short-term memory network is selected to establish an analysis and prediction model.
6. The big data modeling based financial data analytics prediction platform of claim 5 wherein said outputting the payback rate of tangible assets, the payback rate of intangible assets and the payback rate of revenues by running analytics prediction models comprises:
inputting the total revenue amount, the historical profit rate, the historical liability data and the research and development investment of a target subject in unit time, and respectively calculating the repayment rate of tangible assets, the repayment rate of intangible assets and the repayment rate of revenue; the historical liability data comprises liability amount and liability frequency; the research and development investment is used as an influence variable of the gross revenue; the value of the intangible asset is calculated according to the following formula:
V＝(S/A)×5PN，
wherein S represents research and development investment, A represents earning total amount, P represents profit margin of the business object, and N represents sales amount of the business object.
7. The big-data-modeling-based financial data analysis and prediction platform of claim 6, wherein said calculating the degree of association between the subject and the intangible asset comprises:
and acquiring pictures of authorized patent documents in intangible assets, calculating the similarity between the pictures and products, and taking the similarity as the association degree between the business objective and the intangible assets.
8. The big-data-modeling-based financial data analysis and prediction platform of claim 7 wherein the repayment rates of tangible assets and the repayment rates of intangible assets are assigned weights according to the relevance;
the weights are calculated according to the following formula:
Q 1 ＝P×(R+0.5) 2 ；
Q 2 ＝|1-P×(R+0.5) 2 |，
wherein Q 1 Weight of repayment rate for intangible assets, Q 2 R is the degree of association between the business target and the intangible asset.
9. The big-data-modeling-based financial data analytics prediction platform of claim 8 wherein said outputting a loan risk comprises:
and calculating the risk level according to the total amount of the repayment rate and the profit rate of the loan.
10. The big-data-modeling-based financial data analysis and prediction platform of claim 9, wherein the calculating a risk level comprises:
the following formula is used for calculation:
R＝Q z +C，
wherein Q is z Represents the total amount of the repayment rate after the calculation of the weight, C represents the guarantee rate, R represents the risk level, and the larger the value of R, the lower the risk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210921012.2A CN115409631A (en) | 2022-08-02 | 2022-08-02 | Financial data analysis and prediction platform based on big data modeling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210921012.2A CN115409631A (en) | 2022-08-02 | 2022-08-02 | Financial data analysis and prediction platform based on big data modeling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115409631A true CN115409631A (en) | 2022-11-29 |
Family
ID=84158914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210921012.2A Pending CN115409631A (en) | 2022-08-02 | 2022-08-02 | Financial data analysis and prediction platform based on big data modeling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115409631A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116523659A (en) * | 2023-03-13 | 2023-08-01 | 武汉凌禹信息科技有限公司 | Financial data risk monitoring platform with real-time reminding function |
-
2022
- 2022-08-02 CN CN202210921012.2A patent/CN115409631A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116523659A (en) * | 2023-03-13 | 2023-08-01 | 武汉凌禹信息科技有限公司 | Financial data risk monitoring platform with real-time reminding function |
| CN116523659B (en) * | 2023-03-13 | 2023-10-24 | 武汉凌禹信息科技有限公司 | Financial data risk monitoring platform with real-time reminding function |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102009309B1 (en) | Management automation system for financial products and management automation method using the same | |
| Kopanas et al. | The role of domain knowledge in a large scale data mining project | |
| CN109191282A (en) | Methods of marking and system are monitored in a kind of loan of Behavior-based control model | |
| EP2506207A1 (en) | Computer system, computer-implemented method and computer program product for managing operations of a system | |
| CN110689438A (en) | Enterprise financial risk scoring method and device, computer equipment and storage medium | |
| CN114066242A (en) | Enterprise risk early warning method and device | |
| JP7017149B2 (en) | Information processing equipment, information processing method and information processing program using deep learning | |
| KR102336041B1 (en) | AI-based small business credit rating system and credit rating method using it | |
| CN115271912A (en) | Credit business intelligent wind control approval system and method based on big data | |
| JP2010225103A (en) | Investment income/expenditure risk analysis method, program and investment income/expenditure risk analysis device | |
| CN113642923A (en) | Bad asset pack value evaluation method based on historical collection urging data | |
| CN115409631A (en) | Financial data analysis and prediction platform based on big data modeling | |
| RU2630169C1 (en) | Automated calculating system for forming and monitoring investment portfolio of shares | |
| CN116228403A (en) | Personal bad asset valuation method and system based on machine learning algorithm | |
| KR102499182B1 (en) | Loan regular auditing system using artificia intellicence | |
| CN117252677A (en) | Credit line determination method and device, electronic equipment and storage medium | |
| TW201506828A (en) | Apparatus and method for total loss prediction | |
| CN113298575A (en) | Method, system, equipment and storage medium for trademark value batch evaluation | |
| CN113421155A (en) | Steel trade enterprise portrait multidimensional model construction method, wind control management method and device | |
| CN113870020A (en) | Overdue risk control method and device | |
| CN113269412A (en) | Risk assessment method and related device | |
| CN112508689A (en) | Method for realizing decision evaluation based on multiple dimensions | |
| CN112927071A (en) | Post-loan behavior feature processing method and device | |
| CN113421154A (en) | Credit risk assessment method and system based on control chart | |
| Kumar et al. | Bank loan approval prediction using data mining technique |
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 |