CN116596674A - External trade risk assessment method based on big data analysis - Google Patents
External trade risk assessment method based on big data analysis Download PDFInfo
- Publication number
- CN116596674A CN116596674A CN202310875414.8A CN202310875414A CN116596674A CN 116596674 A CN116596674 A CN 116596674A CN 202310875414 A CN202310875414 A CN 202310875414A CN 116596674 A CN116596674 A CN 116596674A
- Authority
- CN
- China
- Prior art keywords
- risk
- data
- foreign trade
- association rule
- degree
- 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
- 238000012502 risk assessment Methods 0.000 title claims abstract description 93
- 238000000034 method Methods 0.000 title claims abstract description 89
- 238000007405 data analysis Methods 0.000 title claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims abstract description 28
- 238000011156 evaluation Methods 0.000 claims abstract description 11
- 238000013210 evaluation model Methods 0.000 claims abstract description 10
- 239000003016 pheromone Substances 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 4
- 241000257303 Hymenoptera Species 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 5
- 238000007726 management method Methods 0.000 description 8
- 238000009499 grossing Methods 0.000 description 5
- 230000008676 import Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000013501 data transformation Methods 0.000 description 2
- 239000000945 filler Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000019637 foraging behavior Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000013068 supply chain management 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an external trade risk assessment method based on big data analysis, which relates to the technical field of big data analysis and comprises the steps of obtaining foreign trade data of a target foreign trade enterprise, carrying out internal association rule analysis and external association rule analysis on the foreign trade data, and calculating a risk assessment index. Further comprises risk category assessment and risk degree assessment to help enterprises comprehensively and accurately assess foreign trade risks. The method adopts an internal association rule model, an external association rule model, an ant colony algorithm and the like, so that the accuracy of risk assessment is improved; the detailed evaluation of various risks is realized through a risk type evaluation model and a risk degree evaluation model; meanwhile, the method is suitable for foreign trade enterprises of different types, and is beneficial to improving the risk management level of the enterprises.
Description
Technical Field
The invention relates to the technical field of external trade management, in particular to an external trade risk assessment method based on big data analysis.
Background
With the acceleration of globalization process, the position of external trade in international economic communication is more and more important. However, there are many risks in foreign trade, such as credit risk, funding risk, market risk, legal risk, and the like. Therefore, accurate assessment of these risks is critical to external trade enterprises in conducting business. With the development of big data technology, it is gradually possible to evaluate foreign trade risks by using big data analysis methods. However, existing risk assessment methods still have some problems and require improvement.
In the prior art, there are many patents on foreign trade risk assessment. For example, chinese patent document CN105130172a provides an international trade risk analysis method based on big data, which mainly analyzes the international trade data to obtain trade risk indexes, and evaluates the trade risk indexes to predict future trade risk. However, this approach focuses mainly on the overall situation of trade data, without careful analysis of different kinds of foreign trade data, possibly resulting in some important risk factors being ignored.
In addition, chinese patent document CN104895278A provides a foreign trade risk assessment method based on data mining, which uses a data mining technique to analyze historical transaction data of a foreign trade enterprise, thereby assessing credit risk of the enterprise. However, this approach only focuses on credit risk, and does not involve other types of risk, such as funding risk, market risk, and legal risk, which may result in less than comprehensive risk assessment results.
In addition, chinese patent document CN105844554a proposes a foreign trade risk assessment method based on multidimensional correlation analysis, which can evaluate multiple types of risks simultaneously by performing correlation analysis on multidimensional data. However, this method requires a large amount of data preprocessing work, such as data noise reduction, feature extraction, etc., which may result in higher computational complexity and is not beneficial to practical application.
Disclosure of Invention
The invention aims to provide an external trade risk assessment method based on big data analysis, which can improve the accuracy of risk assessment, comprehensively assess various risks, refine the risk degree, be applicable to foreign trade enterprises of different types, optimize decision support, improve the risk management level of the enterprises, improve the analysis capability of the foreign trade data, save enterprise resources and improve the capability of the enterprises to cope with sudden events.
In order to solve the technical problems, the invention provides a three-dimensional matching method based on mixed tree filtering, which comprises the following steps:
an external trade risk assessment method based on big data analysis, the method comprising:
step S1: obtaining foreign trade data of a target foreign trade enterprise, wherein the foreign trade data at least comprises the following categories: trade financing data, trade market data, industry chain data, trade agreement data, and customs import-export data;
step S2: internal association rule analysis is carried out on the obtained foreign trade data by using an internal association rule model so as to judge the rationality of the foreign trade data of different types and find out unreasonable foreign trade data; for unreasonable foreign trade data, using an internal association rule model to generate filling data to replace the unreasonable foreign trade data;
step S3: carrying out external association rule analysis on the foreign trade data to find risk assessment indexes of the foreign trade data of each type; the risk assessment index at least comprises the following categories: support, confidence, lifting degree, mutual information, jacquard coefficient and lifting degree ratio;
step S4: using a preset risk degree evaluation model, and calculating to obtain a risk degree value according to a risk evaluation index; the risk degree value characterizes the total risk degree of the target foreign trade enterprise; a corresponding table of risk values and risk degrees is predefined, and the risk degrees of target foreign trade enterprises are obtained according to the corresponding table;
step S5: using a preset risk type assessment model, and calculating to obtain a risk type according to a risk assessment index;
step S6: and generating an evaluation result of the target foreign trade enterprise according to the risk degree and the risk type of the target foreign trade enterprise.
Further, the risk level at least includes 4 different levels, respectively: level 1, level 2, level 3 and level 4; the risk degree of each grade corresponds to a risk degree value interval, and the risk degree value intervals are respectively 1 grade risk degree value interval, 2 grade risk degree value interval, 3 grade risk degree value interval and 4 grade risk degree value interval.
Further, the risk categories include: credit risk, funding risk, market risk, and legal risk.
Further, the executing process of the internal association rule model in step S2 includes: using foreign trade data as a transaction set, including a plurality of item sets, and using an ant colony algorithm to find frequent item sets in the transaction set; based on the found frequent item set, an internal association rule is constructed, which specifically comprises: setting a confidence threshold and a support threshold of the internal association rule; the confidence threshold is used for controlling the accuracy of the association rules, and the support threshold is used for controlling the quantity of the association rules; for each item set in the frequent item sets, generating a plurality of sub-internal association rules, and for each sub-internal association rule, calculating the confidence and support of the sub-internal association rule; wherein the support degree represents the proportion of the transaction number containing the sub-internal association rule to the total transaction number, and the confidence degree represents the proportion of the transaction number containing the sub-internal association rule and the other item set to the transaction number containing the association rule; screening sub-internal association rules meeting the conditions as internal association rules according to the set confidence coefficient threshold and the set support coefficient threshold; based on the internal association rule, carrying out support and confidence calculation on each item set in the transaction set, judging whether each item set meets the internal association rule according to a calculation result, and if not, taking foreign trade data corresponding to the item set as unreasonable foreign trade data; for unreasonable foreign trade data, the data value is continuously changed on the basis of the original data value, and a new data value is generated until the item set corresponding to the new data value meets the internal association rule.
Further, the process of finding frequent item sets in the transaction set by using the ant colony algorithm specifically includes: step 2.1: initializing an ant colony, wherein each ant randomly selects one item set as a starting point; step 2.2: each ant selects the next item set according to the pheromone content and heuristic rules; step 2.3: after each ant walks a path, calculating the increment of the pheromone on the path, and updating the pheromone matrix; repeating the steps 2.2-2.3 until the stopping condition is met; finding frequent item sets according to the pheromone matrix; the pheromone matrix represents the similarity degree between different item sets, and the larger the pheromone content is, the higher the similarity degree is.
Further, the pheromone matrix is:
；
wherein ,representing a collection of items,/->Representing an item set,/->Representing item set->Is the pheromone content of (2); the heuristic is expressed as the following formula:
；
wherein ,representing the current item set,/->Represents the next selectable item set,/-for>Representing item set-> and />Pheromone content between->Representing heuristic functions, ++>Representation and item set->Adjacent item set, < -> and />Parameters for adjusting the influence of the pheromone content and the heuristic function on the probability are represented;
assume thatRepresenting item set-> and />The increment of the pheromone in between, and the update of the pheromone is expressed as the following formula:
；
wherein ,representing the volatility coefficient of pheromone->Representing the number of ants, < >>Indicate->Ant only in the item set-> and />Increment of pheromone on the path traversed in between;
the stop condition is the upper limit set by the ant colony traversal times and is a set value.
Further, the step S3: the method for carrying out external association rule analysis on the foreign trade data to find the risk assessment index of each kind of foreign trade data comprises the following steps: generating frequent item sets of different types of trade data according to the foreign trade data obtained in the step S1; performing attribute mapping on each frequent item set; based on the result of the attribute mapping, various risk assessment indexes are calculated respectively.
Further, when the risk category assessment model calculates a risk degree value, a method based on weighted average is used, which specifically includes: and setting different risk degree weight values for each risk assessment index, multiplying each risk assessment index by the risk degree weight value, and accumulating to obtain a risk degree value.
Further, when the risk degree evaluation model calculates the risk category, a weighted average method is used, which specifically includes: setting different risk category weight values for each risk assessment index, multiplying each risk assessment index by the risk category weight values, accumulating to obtain a risk category value, and comparing the risk category value with element values in a preset risk category standard value set according to the risk category value to determine the risk category.
Further, in the step S1, after obtaining the foreign trade data of the target foreign trade enterprise, a process of data denoising is further included.
The external trade risk assessment method based on big data analysis has the following beneficial effects:
1. improving the risk assessment accuracy: according to the invention, the foreign trade data is analyzed by adopting the internal association rule model and the external association rule model, so that reasonable foreign trade data is found and a risk assessment index is generated. Meanwhile, the invention reduces the data noise of the foreign trade data and improves the data quality. These processes and analyses help to improve the accuracy of risk assessment, providing more reliable risk assessment results for the enterprise.
2. Comprehensive assessment of multiple risks: the invention provides a risk type assessment model which can assess various risks such as credit risks, fund risks, market risks, legal risks and the like. The risk assessment method and the risk assessment system enable the risk assessment result to be more comprehensive, help enterprises to comprehensively understand foreign trade risks, and provide basis for enterprises to formulate risk precautionary measures and coping strategies.
3. Risk degree refinement: the risk degree evaluation model provided by the invention considers four different grades, namely grade 1, grade 2, grade 3 and grade 4, and the risk degree of each grade corresponds to a risk degree value interval. The risk assessment result is further refined, corresponding countermeasures are taken by enterprises aiming at risks of different degrees, and the capability of the enterprises for coping with the risks is improved.
4. Is suitable for foreign trade enterprises of different types: the method is suitable for various foreign trade enterprises, whether large-scale across-country enterprises or small-scale enterprises, and the foreign trade risk can be evaluated by the method. This helps to promote the application of the present invention and improve the overall risk prevention capability of foreign trade enterprises. The risk assessment result provided by the invention can provide powerful support for the decision-making layer of the enterprise. The enterprise can adjust the business strategy, the risk control measures and the response schemes according to the risk assessment result, so that the possibility and the influence degree of risks are reduced. This helps the enterprise develop business more robustly in foreign market, improves the competitive advantage of enterprise. By using the method provided by the invention, enterprises can develop risk assessment work more systematically. This helps the enterprise build a sound risk management system, increasing the enterprise risk management level. In long-term practice, enterprises can continuously summarize experiences, optimize a risk assessment model, enable a risk assessment result to be closer to reality, and provide more valuable references for enterprise risk management.
5. And the foreign trade data analysis capability is improved: the invention adopts big data analysis method such as ant colony algorithm, etc. to process and mine foreign trade data. This helps businesses to increase data analysis capabilities, exploring potential commercial value and risk factors. Meanwhile, enterprises can deeply analyze risk sources according to risk assessment results to know reasons for risk generation, so that risk precautionary measures are formulated in a targeted manner.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic system structure diagram of an external trade risk assessment method based on big data analysis according to an embodiment of the present invention.
Detailed Description
The core of the invention is to provide an external trade risk assessment method based on big data analysis, which not only can carry out detailed analysis on different types of foreign trade data, but also can assess various types of risks, such as credit risks, fund risks, market risks, legal risks and the like. In addition, the invention also adopts an internal association rule model and an external association rule model to effectively process and analyze the foreign trade data, thereby improving the accuracy of risk assessment. Meanwhile, the invention reduces the data noise of the foreign trade data, improves the data quality, and is beneficial to further improving the accuracy of risk assessment. In addition, the risk degree value and the risk category are calculated by adopting a weighted average method, so that the risk assessment result is more comprehensive and reasonable. The risk degree evaluation model provided by the invention considers four different grades, namely grade 1, grade 2, grade 3 and grade 4, and the risk degree of each grade corresponds to a risk degree value interval. The risk assessment result is further refined, and enterprises can take corresponding countermeasures for risks of different degrees. In addition, the invention also provides a risk type assessment model which can assess various risks such as credit risks, fund risks, market risks, legal risks and the like, so that the risk assessment result is more comprehensive. In the implementation process, the method adopts the ant colony algorithm to find the frequent item set in the transaction set, and the algorithm has better searching capability and can find the optimal frequent item set. Meanwhile, the invention also uses various risk assessment indexes such as support degree, confidence degree, lifting degree, mutual information, jacquard coefficient, lifting degree ratio and the like, which can reflect foreign trade risks from different angles and are beneficial to improving the accuracy of risk assessment.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
An external trade risk assessment method based on big data analysis, the method comprising:
step S1: obtaining foreign trade data of a target foreign trade enterprise, wherein the foreign trade data at least comprises the following categories: trade financing data, trade market data, industry chain data, trade agreement data, and customs import-export data;
first, foreign trade data of a target foreign trade enterprise is collected. Such data includes trade financing data (e.g., financing amounts, financing periods, etc.), trade market data (e.g., market size, market share, etc.), industry chain data (e.g., upstream and downstream business information, supply chain relationships, etc.), trade agreement data (e.g., agreement terms, agreement expiration dates, etc.), and customs import and export data (e.g., import and export amounts, tariffs, etc.).
Step S2: internal association rule analysis is carried out on the obtained foreign trade data by using an internal association rule model so as to judge the rationality of the foreign trade data of different types and find out unreasonable foreign trade data; for unreasonable foreign trade data, using an internal association rule model to generate filling data to replace the unreasonable foreign trade data;
the collected foreign trade data is analyzed using an internal association rule model. The analysis can judge the rationality of foreign trade data of different types and find out unreasonable foreign trade data. For unreasonable foreign trade data, the filler data is generated using an internal association rule model to replace them.
Step S3: carrying out external association rule analysis on the foreign trade data to find risk assessment indexes of the foreign trade data of each type; the risk assessment index at least comprises the following categories: support, confidence, lifting degree, mutual information, jacquard coefficient and lifting degree ratio;
and carrying out external association rule analysis on the foreign trade data to find risk assessment indexes of the foreign trade data of each category. These risk assessment metrics include support (for measuring the frequency of occurrence of events), confidence (for measuring rule confidence), boost (for measuring rule independence), mutual information (for measuring correlation between variables), jaccard coefficients (for measuring similarity of data sets), and boost ratios (for measuring rule relative independence).
Step S4: using a preset risk degree evaluation model, and calculating to obtain a risk degree value according to a risk evaluation index; the risk degree value characterizes the total risk degree of the target foreign trade enterprise; a corresponding table of risk values and risk degrees is predefined, and the risk degrees of target foreign trade enterprises are obtained according to the corresponding table;
and calculating a risk degree value by using a risk assessment index according to a preset risk degree assessment model. The risk value reflects the overall risk level of the target foreign business enterprise. And (3) predefining a corresponding table of the risk degree value and the risk degree, and obtaining the risk degree of the target foreign trade enterprise according to the corresponding table.
Step S5: using a preset risk type assessment model, and calculating to obtain a risk type according to a risk assessment index;
step S6: and generating an evaluation result of the target foreign trade enterprise according to the risk degree and the risk type of the target foreign trade enterprise.
And generating an evaluation result according to the risk degree and the risk type of the target foreign trade enterprise. The assessment results can help enterprises to know own risk conditions, make corresponding risk management strategies and provide valuable information for decision makers.
The support is used to measure how often the item set appears in the dataset. The calculation formula is as follows:
；
wherein ,representing item sets->Representing item set->Probability of occurrence in all transactions.
Confidence is used to measure the reliability of the association rule. The calculation formula is as follows:
confidence level；
wherein , and />Representing item sets->Expressed in item set +.>In the case of occurrence, item set->Probability of occurrence, ++>Representing item set-> and />Probability of simultaneous occurrence.
The degree of promotion is used to measure the strength of the association rule, i.e. in association rulesUnder the condition of->Probability of occurrence and item set->The ratio of the probabilities of occurrence in the population. The calculation formula is as follows:
；
wherein , and />Representing a set of items.
Mutual information measures the correlation between two sets of items, i.e. how information that appears in one set affects information that appears in the other set. The calculation formula is as follows:
；
wherein ,representing item set-> and />Mutual information between->Representing item set-> and />Probability of simultaneous occurrence, < >> and />Representing item sets +.> and />Probability of occurrence.
The jaccard coefficient is used to measure the similarity between two sets of terms. The calculation formula is as follows:
；
wherein ,representing item set-> and />Between Jacquard coefficients, +.>Representing item set-> and />Intersection element number of->Representing item set-> and />The number of union elements of (a).
The boost ratio is used to measure the strength of the association rule, i.e. in association rulesUnder the condition of->Probability of occurrence and item set->The difference between the probabilities of occurrence in the population. The calculation formula is as follows:
；
wherein , and />Representing item sets->Representing item set-> and />Probability of simultaneous occurrence, < >>Andrepresenting item sets +.> and />Probability of occurrence.
In practical application, the external trade risk assessment method based on big data analysis can help enterprises to discover potential risks in time, and loss is reduced. The application scene is as follows:
credit rating: the financial institution may provide credit ratings for the foreign trade enterprises based on the evaluation results, thereby determining whether to provide financing services and financing conditions thereto.
Policy establishment: the government may formulate corresponding policy actions based on the evaluation, such as reinforcing supervision for high-risk enterprises or providing preferential policies for low-risk enterprises.
Enterprise strategic planning: the foreign trade enterprises can optimize supply chain management, adjust market strategies and the like according to the evaluation results, and potential risks are reduced.
Risk prevention: through the risk assessment of foreign trade enterprises, insurance companies can more accurately provide customized insurance schemes for the enterprises, and the enterprises are helped to avoid risks.
First, foreign trade data of a target foreign trade enterprise is collected. Such data includes trade financing data (e.g., financing amounts, financing periods, etc.), trade market data (e.g., market size, market share, etc.), industry chain data (e.g., upstream and downstream business information, supply chain relationships, etc.), trade agreement data (e.g., agreement terms, agreement expiration dates, etc.), and customs import and export data (e.g., import and export amounts, tariffs, etc.).
Specifically, the risk level includes at least 4 different levels, respectively: level 1, level 2, level 3 and level 4; the risk degree of each grade corresponds to a risk degree value interval, and the risk degree value intervals are respectively 1 grade risk degree value interval, 2 grade risk degree value interval, 3 grade risk degree value interval and 4 grade risk degree value interval.
Each risk level corresponds to a risk value interval, for example: class 1 risk value interval: 0-25; class 2 risk value interval: 26-50 parts; class 3 risk value interval: 51-75; class 4 risk value interval: 76-100.
In calculating the risk level value, a preset risk level evaluation model may be used. The model comprehensively calculates the risk degree value according to various risk assessment indexes (such as support degree, confidence degree, lifting degree and the like). The higher the risk value, the higher the risk level the enterprise is at.
According to the calculated risk level value, foreign trade enterprises can be classified into corresponding risk level grades. For example, if a risk level value of a certain enterprise is 35, the enterprise belongs to a level 2 (medium-low risk) risk level.
By dividing the risk level into four levels and corresponding to different risk level value intervals, the patent provides a practical framework for assessing and managing the risk of foreign trade enterprises. Enterprises, financial institutions and government authorities can develop corresponding risk management policies based on this framework to reduce potential losses.
The risk categories include: credit risk, funding risk, market risk, and legal risk.
Credit risk: credit risk refers to the risk that foreign trade enterprises may cause default, delay payment or no payment due to poor credit status of trade parties in the international trade process. The credit risk assessment may help businesses learn about the credit status of the transaction party, taking measures to reduce potential losses, such as requiring advance payment, use of credit insurance, etc.
Fund risk: the fund risk refers to that in the trade process of a foreign trade enterprise, due to unsmooth fund flow or difficult financing, the enterprise can not fulfill contractual obligations on time or can not support normal production and operation activities. The funding risk assessment may help enterprises predict and address potential funding issues such as optimizing cash flow management, seeking financing channels, etc.
Market risk: market risk refers to that in the trade process of a foreign trade enterprise, due to factors such as market demand fluctuation, price fluctuation or competitive environment change, the sales income of the enterprise may be reduced or profits may be compressed. The market risk assessment can help enterprises to know market conditions, so that corresponding market strategies, such as product combination adjustment, new market expansion and the like, are formulated.
Legal risk: legal risk means that foreign trade enterprises can bear legal responsibility or lose due to changes of laws and regulations, contract disputes or intellectual property problems and the like in the trade process. Legal risk assessment may help businesses identify potential legal issues, taking measures to reduce risk, such as engaging professional lawyers, perfecting contractual terms, and so forth.
Specifically, the executing process of the internal association rule model in step S2 includes: foreign trade data is included as a transaction set including a plurality of item sets. This means that the whole foreign trade data set is treated as one large transaction database, each transaction consisting of a plurality of data items. The ant colony algorithm is used to find frequent item sets in the transaction set. The ant colony algorithm is an optimization algorithm for simulating the foraging behavior of ants in nature, and frequent item sets can be quickly found in a large-scale data set. Based on the found frequent item set, an internal association rule is constructed. This includes setting confidence and support thresholds for the internal association rules. The confidence threshold is used for controlling the accuracy of the association rules, and the support threshold is used for controlling the number of the association rules. For each of the frequent item sets, a plurality of sub-internal association rules are generated. Then, the confidence and support of each sub-internal association rule is calculated. And screening sub-internal association rules meeting the conditions as internal association rules according to the set confidence threshold and the set support threshold. And carrying out supporting degree and confidence degree calculation on each item set in the transaction set based on the internal association rule. And judging whether each item set meets the internal association rule according to the calculation result. If the foreign trade data corresponding to the item set does not meet the requirement, the foreign trade data corresponding to the item set is regarded as unreasonable foreign trade data. For unreasonable foreign trade data, the data value is continuously changed on the basis of the original data value, and a new data value is generated until the item set corresponding to the new data value meets the internal association rule. Thus, we can repair unreasonable foreign trade data to make it conform to internal association rules. Through this process, the internal association rule model can effectively detect unreasonable foreign trade data and generate filler data to replace the unreasonable foreign trade data. This helps to improve the quality of the foreign trade data, providing a more accurate input for subsequent risk assessment.
Specifically, step S3: the method for carrying out external association rule analysis on the foreign trade data to find the risk assessment index of each kind of foreign trade data comprises the following steps: generating frequent item sets of different types of trade data according to the foreign trade data obtained in the step S1; performing attribute mapping on each frequent item set; based on the result of the attribute mapping, various risk assessment indexes are calculated respectively.
And generating frequent item sets of different types of trade data according to the foreign trade data obtained in the step S1. This means that frequently occurring combinations of data items are found separately for each kind of foreign trade data, such as trade financing data, trade market data, industry chain data, trade agreement data and customs import-export data, which can provide valuable information to us.
And carrying out attribute mapping on each frequent item set. This process maps data items in the frequent item set to corresponding risk factor attributes for further analysis. For example, loan amounts and repayment terms in trade financing data may be mapped to credit risk attributes, trade volume and price fluctuations in trade market data may be mapped to market risk attributes, supplier and customer relationships in industry chain data may be mapped to fund risk attributes, and so on.
Based on the result of the attribute mapping, various risk assessment indexes are calculated respectively. These risk assessment metrics include support, confidence, boost, mutual information, jacquard coefficients, boost ratios, etc., which can quantify the importance and relevance of various risk factor attributes. By analyzing the indexes, risk assessment indexes of foreign trade data of each type can be obtained, so that basis is provided for subsequent risk degree assessment and risk type assessment.
When the risk category assessment model calculates a risk degree value, a method based on weighted average is used, and the method specifically comprises the following steps: and setting different risk degree weight values for each risk assessment index, multiplying each risk assessment index by the risk degree weight value, and accumulating to obtain a risk degree value.
When calculating the risk degree value, the risk type assessment model adopts a method based on weighted average, and the method can allocate different weight values according to the importance of each risk assessment index. The method specifically comprises the following steps:
for each risk assessment index, such as support, confidence, promotion, mutual information, jacquard coefficient, promotion ratio, etc., different risk weighting values are set. These weight values may be determined based on the experience of a domain expert, historical data analysis, or other relevant methods. The weight values should be set to ensure that the contribution of the individual indicators in calculating the risk value matches its importance.
Each risk assessment indicator is multiplied by its corresponding risk weighting value. This results in weighted risk assessment index values that reflect the actual contribution of each index in calculating the risk value.
And accumulating the weighted risk assessment index values to obtain a risk degree value. The risk degree value integrates the contribution of each risk assessment index in the calculation process, and can more accurately reflect the overall risk degree of the target foreign trade enterprise.
By using a method based on weighted average, the risk category assessment model can calculate the risk degree value more accurately, thereby providing a more reliable basis for assessing the risk degree and risk category of the target foreign trade enterprise.
The risk level assessment model uses a weighted average method when calculating the risk categories, which allows assigning different weight values according to the importance of each risk assessment index. The method specifically comprises the following steps: for each risk assessment index, such as support, confidence, promotion, mutual information, jacquard coefficient, promotion ratio, etc., different risk category weight values are set. These weight values may be determined based on the experience of a domain expert, historical data analysis, or other relevant methods. The weight values should be set to ensure that the contribution of the individual indicators in calculating the risk category value matches its importance.
Each risk assessment index is multiplied by its corresponding risk category weight value. This results in weighted risk assessment index values reflecting the actual contribution of each index in calculating the risk category value.
And accumulating the weighted risk assessment index values to obtain a risk category value. This risk category value integrates the contributions of the individual risk assessment indicators in the calculation process.
And comparing the calculated risk category value with element values in a preset risk category standard value set. This set of standard values may be formulated based on historical data, industry standards, or expert experience. By comparing the risk category value with a preset risk category standard value, the risk category to which the target foreign trade enterprise belongs, such as credit risk, fund risk, market risk, legal risk and the like, can be determined.
By using a weighted average method, the risk degree evaluation model can calculate the risk category value more accurately, thereby providing a more reliable basis for evaluating the risk category of the target foreign trade enterprise.
In step S1, after obtaining the foreign trade data of the target foreign trade enterprise, the data denoising process is further included.
In step S1, after the foreign trade data of the target foreign trade enterprise is obtained, a data noise reduction process is added, which is helpful to improve the quality of the data and the accuracy of the analysis result. The data denoising process specifically comprises the following steps:
data cleaning: and cleaning the obtained foreign trade data, including removing repeated data, correcting error data, filling missing data and the like. The purpose of data cleansing is to ensure the integrity, consistency and validity of the data, providing a reliable basis for subsequent analysis.
Abnormal value detection: it is checked whether there is an abnormal value in the foreign trade data, such as data whose value is abnormally high or abnormally low. Outliers can adversely affect subsequent analysis and therefore need to be handled. The processing method includes deleting outliers, replacing outliers with reasonable data values, etc.
Smoothing data: to eliminate short-term fluctuations in foreign trade data, a data smoothing method may be employed. Common data smoothing methods include moving average, exponential smoothing, and the like. The data smoothing can reduce the influence of data noise on subsequent analysis and improve the accuracy of analysis results.
And (3) data transformation: according to the requirement of subsequent analysis, proper transformation is carried out on the foreign trade data, such as normalization processing, logarithmic transformation and the like. The data transformation is helpful for simplifying the subsequent analysis process and improving the analysis efficiency.
The foreign trade data after the data noise reduction treatment has higher quality, and can provide more accurate input for the subsequent processes of internal association rule analysis, external association rule analysis and the like, thereby improving the accuracy of the whole external trade risk assessment method based on big data analysis.
In the description, each embodiment is described in a progressive manner, and each embodiment is mainly described by the differences from other embodiments, so that the same similar parts among the embodiments are mutually referred. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The stereoscopic matching method and the stereoscopic matching system based on the mixed tree filtering provided by the invention are described in detail. The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to facilitate an understanding of the method of the present invention and its core ideas. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the invention can be made without departing from the principles of the invention and these modifications and adaptations are intended to be within the scope of the invention as defined in the following claims.
Claims (10)
1. An external trade risk assessment method based on big data analysis, which is characterized by comprising the following steps:
step S1: obtaining foreign trade data of a target foreign trade enterprise, wherein the foreign trade data at least comprises the following categories: trade financing data, trade market data, industry chain data, trade agreement data, and customs import-export data;
step S2: internal association rule analysis is carried out on the obtained foreign trade data by using an internal association rule model so as to judge the rationality of the foreign trade data of different types and find out unreasonable foreign trade data; for unreasonable foreign trade data, using an internal association rule model to generate filling data to replace the unreasonable foreign trade data;
step S3: carrying out external association rule analysis on the foreign trade data to find risk assessment indexes of the foreign trade data of each type; the risk assessment index at least comprises the following categories: support, confidence, lifting degree, mutual information, jacquard coefficient and lifting degree ratio;
step S4: using a preset risk degree evaluation model, and calculating to obtain a risk degree value according to a risk evaluation index; the risk degree value characterizes the total risk degree of the target foreign trade enterprise; a corresponding table of risk values and risk degrees is predefined, and the risk degrees of target foreign trade enterprises are obtained according to the corresponding table;
step S5: using a preset risk type assessment model, and calculating to obtain a risk type according to a risk assessment index;
step S6: and generating an evaluation result of the target foreign trade enterprise according to the risk degree and the risk type of the target foreign trade enterprise.
2. The method of claim 1, wherein the risk level comprises at least 4 different levels, each: level 1, level 2, level 3 and level 4; the risk degree of each grade corresponds to a risk degree value interval, and the risk degree value intervals are respectively 1 grade risk degree value interval, 2 grade risk degree value interval, 3 grade risk degree value interval and 4 grade risk degree value interval.
3. The method of claim 1, wherein the risk categories include: credit risk, funding risk, market risk, and legal risk.
4. A method according to claim 2 or 3, wherein the execution of the internal association rule model in step S2 comprises: using foreign trade data as a transaction set, including a plurality of item sets, and using an ant colony algorithm to find frequent item sets in the transaction set; based on the found frequent item set, an internal association rule is constructed, which specifically comprises: setting a confidence threshold and a support threshold of the internal association rule; the confidence threshold is used for controlling the accuracy of the association rules, and the support threshold is used for controlling the quantity of the association rules; for each item set in the frequent item sets, generating a plurality of sub-internal association rules, and for each sub-internal association rule, calculating the confidence and support of the sub-internal association rule; wherein the support degree represents the proportion of the transaction number containing the sub-internal association rule to the total transaction number, and the confidence degree represents the proportion of the transaction number containing the sub-internal association rule and the other item set to the transaction number containing the association rule; screening sub-internal association rules meeting the conditions as internal association rules according to the set confidence coefficient threshold and the set support coefficient threshold; based on the internal association rule, carrying out support and confidence calculation on each item set in the transaction set, judging whether each item set meets the internal association rule according to a calculation result, and if not, taking foreign trade data corresponding to the item set as unreasonable foreign trade data; for unreasonable foreign trade data, the data value is continuously changed on the basis of the original data value, and a new data value is generated until the item set corresponding to the new data value meets the internal association rule.
5. The method of claim 4, wherein the process of finding frequent item sets in a transaction set using an ant colony algorithm specifically comprises: step 2.1: initializing an ant colony, wherein each ant randomly selects one item set as a starting point; step 2.2: each ant selects the next item set according to the pheromone content and heuristic rules; step 2.3: after each ant walks a path, calculating the increment of the pheromone on the path, and updating the pheromone matrix; repeating the steps 2.2-2.3 until the stopping condition is met; finding frequent item sets according to the pheromone matrix; the pheromone matrix represents the similarity degree between different item sets, and the larger the pheromone content is, the higher the similarity degree is.
6. The method of claim 5, wherein the pheromone matrix is:
；
wherein ,representing a collection of items,/->Representing an item set,/->Representing item set->Is the pheromone content of (2); the heuristic is expressed as the following formula:
；
wherein ,representing the current item set,/->Represents the next selectable item set,/-for>Representing item set-> and />Pheromone content between->Representing heuristic functions, ++>Representation and item set->Adjacent item set, < -> and />Parameters for adjusting the influence of the pheromone content and the heuristic function on the probability are represented;
assume thatRepresenting item set-> and />The increment of the pheromone in between, and the update of the pheromone is expressed as the following formula:
；
wherein ,representing the volatility coefficient of pheromone->Representing the number of ants, < >>Indicate->Ant only in the item set and />Increment of pheromone on the path traversed in between;
the stop condition is the upper limit set by the ant colony traversal times and is a set value.
7. The method according to claim 6, wherein said step S3: the method for carrying out external association rule analysis on the foreign trade data to find the risk assessment index of each kind of foreign trade data comprises the following steps: generating frequent item sets of different types of trade data according to the foreign trade data obtained in the step S1; performing attribute mapping on each frequent item set; based on the result of the attribute mapping, various risk assessment indexes are calculated respectively.
8. The method of claim 7, wherein the risk category assessment model uses a weighted average based method when calculating the risk score, and specifically comprises: and setting different risk degree weight values for each risk assessment index, multiplying each risk assessment index by the risk degree weight value, and accumulating to obtain a risk degree value.
9. The method of claim 7, wherein the risk level assessment model calculates the risk category using a weighted average method, and specifically comprising: setting different risk category weight values for each risk assessment index, multiplying each risk assessment index by the risk category weight values, accumulating to obtain a risk category value, and comparing the risk category value with element values in a preset risk category standard value set according to the risk category value to determine the risk category.
10. The method of claim 1, wherein the step S1 further comprises a process of data denoising the foreign trade data after obtaining the foreign trade data of the target foreign trade enterprise.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310875414.8A CN116596674A (en) | 2023-07-18 | 2023-07-18 | External trade risk assessment method based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310875414.8A CN116596674A (en) | 2023-07-18 | 2023-07-18 | External trade risk assessment method based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116596674A true CN116596674A (en) | 2023-08-15 |
Family
ID=87608359
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310875414.8A Pending CN116596674A (en) | 2023-07-18 | 2023-07-18 | External trade risk assessment method based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116596674A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116934098A (en) * | 2023-09-14 | 2023-10-24 | 山东省标准化研究院(Wto/Tbt山东咨询工作站) | Risk quantitative evaluation method for technical trade measures |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170213168A1 (en) * | 2016-01-22 | 2017-07-27 | Wipro Limited | Methods and systems for optimizing risks in supply chain networks |
| CN109783485A (en) * | 2018-12-30 | 2019-05-21 | 国网天津市电力公司电力科学研究院 | Distribution historical metrology data bearing calibration based on data mining and support vector machines |
| CN112465393A (en) * | 2020-12-09 | 2021-03-09 | 南威软件股份有限公司 | Enterprise risk early warning method based on correlation analysis FP-Tree algorithm |
| CN114723287A (en) * | 2022-04-08 | 2022-07-08 | 浙江万里学院 | Quantitative statistical method for risk formation based on enterprise characteristics and operation behaviors |
| CN115495505A (en) * | 2022-10-11 | 2022-12-20 | 国网甘肃省电力公司电力科学研究院 | Airport group data correlation analysis method based on new energy |
-
2023
- 2023-07-18 CN CN202310875414.8A patent/CN116596674A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170213168A1 (en) * | 2016-01-22 | 2017-07-27 | Wipro Limited | Methods and systems for optimizing risks in supply chain networks |
| CN109783485A (en) * | 2018-12-30 | 2019-05-21 | 国网天津市电力公司电力科学研究院 | Distribution historical metrology data bearing calibration based on data mining and support vector machines |
| CN112465393A (en) * | 2020-12-09 | 2021-03-09 | 南威软件股份有限公司 | Enterprise risk early warning method based on correlation analysis FP-Tree algorithm |
| CN114723287A (en) * | 2022-04-08 | 2022-07-08 | 浙江万里学院 | Quantitative statistical method for risk formation based on enterprise characteristics and operation behaviors |
| CN115495505A (en) * | 2022-10-11 | 2022-12-20 | 国网甘肃省电力公司电力科学研究院 | Airport group data correlation analysis method based on new energy |
Non-Patent Citations (1)
| Title |
|---|
| 佘雅莉等: ""基于混合蚁群关联规则挖掘的危险源分析算法"", 《计算机技术与发展》, vol. 28, no. 11, pages 137 - 146 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116934098A (en) * | 2023-09-14 | 2023-10-24 | 山东省标准化研究院(Wto/Tbt山东咨询工作站) | Risk quantitative evaluation method for technical trade measures |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4358475B2 (en) | Credit evaluation system | |
| CN111476660B (en) | Intelligent wind control system and method based on data analysis | |
| WO2012018968A1 (en) | Method and system for quantifying and rating default risk of business enterprises | |
| US20110246385A1 (en) | Automatically recalibrating risk models | |
| CN111401798A (en) | Enterprise waste escaping and debt risk early warning system and construction method | |
| Huang et al. | Contractor financial prequalification using simulation method based on cash flow model | |
| US20110099101A1 (en) | Automated validation reporting for risk models | |
| CN111738843B (en) | Quantitative risk evaluation system and method using running water data | |
| Song et al. | Predicting accounting fraud: Evidence from Japan | |
| CN116596674A (en) | External trade risk assessment method based on big data analysis | |
| CN112037006A (en) | Credit risk identification method and device for small and micro enterprises | |
| CN116468536A (en) | Automatic risk control rule generation method | |
| Liu et al. | Financial credit risk assessment of online supply chain in construction industry with a hybrid model chain | |
| CN114742402A (en) | Information monitoring method, device, equipment and medium | |
| Huang et al. | Dynamic threshold cash flow–based structural model for contractor financial prequalification | |
| CN112766814A (en) | Training method, device and equipment for credit risk pressure test model | |
| Zeng | [Retracted] Research on Risk Measurement and Early Warning of Electronic Banking Business Based on GMDH Algorithm | |
| CN115860924A (en) | Supply chain financial credit risk early warning method and related equipment | |
| CN116167629A (en) | Distributed policy automatic generation method, system and storage medium | |
| An et al. | Impact of transition risks of climate change on Chinese financial market stability | |
| CN113421014A (en) | Target enterprise determination method, device, equipment and storage medium | |
| CN117455681A (en) | Service risk prediction method and device | |
| CN113298575A (en) | Method, system, equipment and storage medium for trademark value batch evaluation | |
| Li et al. | Identification of Enterprise Financial Risk Based on Clustering Algorithm | |
| Zeng | A comparison study on the era of internet finance China construction of credit scoring system model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230815 |