CN116911986A - Business risk identification method and system - Google Patents
Business risk identification method and system Download PDFInfo
- Publication number
- CN116911986A CN116911986A CN202311147215.1A CN202311147215A CN116911986A CN 116911986 A CN116911986 A CN 116911986A CN 202311147215 A CN202311147215 A CN 202311147215A CN 116911986 A CN116911986 A CN 116911986A
- Authority
- CN
- China
- Prior art keywords
- information
- stakeholders
- data
- risk
- business
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000002372 labelling Methods 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims description 23
- 230000007246 mechanism Effects 0.000 claims description 11
- 238000013058 risk prediction model Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 230000008901 benefit Effects 0.000 claims description 8
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000012954 risk control Methods 0.000 abstract description 2
- 238000012502 risk assessment Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 230000001965 increasing effect Effects 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003090 exacerbative effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of risk control of internet financial services, in particular to a service risk identification method and system. The business risk identification method provided by the invention comprises the following steps: selecting a target service and determining a stakeholder of the target service; acquiring multidimensional data of a target service, and acquiring the knowledge degree of different stakeholders on the multidimensional data; labeling the multidimensional data according to the degree of understanding, and clustering the labeled multidimensional data by taking a stakeholder as a clustering center; obtaining information asymmetry and information distribution coefficients among different stakeholders by using clustering results of different stakeholders; and identifying the information asymmetry risks of different stakeholders based on the target service by combining the information asymmetry and the information distribution coefficient. The method provides an accurate information asymmetric risk identification tool for the internet finance field, is beneficial to early finding potential information asymmetric risks, and provides a powerful support for business decision.
Description
Technical Field
The invention relates to the field of risk control of internet financial services, in particular to a service risk identification method and system.
Background
In the field of internet finance, which is rapidly developed nowadays, rapid progress of information technology provides rich opportunities for innovation and development of financial business, but is accompanied by risks of diversification and complexity. Where an asymmetric risk of information refers to the risk that parties involved in a transaction or collaboration face uncertainty and potential risk in decision making due to different levels of information. First, investment and financial services face the trouble of risk of information asymmetry. On an internet platform, it is often difficult for investors to obtain sufficiently transparent project information, and the risk and expected benefits of the project cannot be accurately assessed, which makes it difficult for investors to make informed decisions, possibly resulting in the selection of high-risk projects or the missing of potential opportunities. Second, credit businesses face similar problems. In the internet credit consumption business, the credit condition of borrowers may be underestimated or overestimated, so that the borrowers and the lenders suffer loss in the cooperation process, and the information asymmetry may promote bad behaviors such as false propaganda, hidden risks and the like, thereby exacerbating market instability. In addition, financial technology innovations such as blockchains and smart contracts are also subject to the risk of information asymmetry, which, when applied, can be difficult for investors and users to understand their risk and mechanism due to technical complexity. Therefore, there is a need for a business risk identification method and system, and for early identification of potential information asymmetry risk in internet financial business.
Disclosure of Invention
In order to overcome the defects of the prior art and the needs of practical application, the invention provides a business risk identification method, which aims at identifying potential information asymmetric risks in internet financial business. The business risk identification method provided by the invention comprises the following steps: selecting one or more target services, and determining stakeholders of the target services, wherein the number of stakeholders comprises two or more than two; acquiring multidimensional data of the target service, and acquiring the knowledge degree of different stakeholders on the multidimensional data; labeling the multidimensional data according to the knowledge degree, and clustering the labeled multidimensional data by taking the stakeholder as a clustering center; obtaining information asymmetry and information distribution coefficients among different stakeholders by using clustering results of different stakeholders; and combining the information asymmetry and the information distribution coefficient, and identifying information asymmetry risks of different stakeholders based on the target service. The invention provides an innovative business risk identification method aiming at the problem of asymmetric risk of information in internet financial business. According to the method and the system, the degree of knowledge of a plurality of stakeholders of the target service on the multidimensional data is analyzed, and the corresponding information asymmetry degree and information distribution coefficient are calculated, so that the risk of information asymmetry among different stakeholders is realized. The method provides an accurate information asymmetric risk identification tool for the internet finance field, is beneficial to early finding potential information asymmetric risks, and provides a powerful support for business decision.
Optionally, the business risk identification method further includes the following steps: setting an information asymmetry risk threshold, and triggering an early warning mechanism when the information asymmetry risk exceeds the information asymmetry risk threshold. According to the method, the real-time monitoring of the information asymmetry risk is increased, the corresponding information asymmetry risk threshold is set, and once the information asymmetry risk exceeds the threshold, an early warning mechanism is automatically triggered, so that service participants are timely reminded, and the method is beneficial to rapidly coping with potential risks.
Optionally, the obtaining the knowledge degree of the multidimensional data by different stakeholders includes the following steps: sorting the multidimensional data, and eliminating sensitive data in the multidimensional data; based on the multi-dimensional data after the arrangement, designing a corresponding knowledge degree questionnaire; and acquiring the knowledge degree of the multidimensional data by the different stakeholders by using the knowledge degree questionnaire. The selectable item provides a reasonable and effective method for obtaining the knowledge degree of the stakeholder on the multidimensional data, and the subsequent analysis is more objective and accurate by arranging the data, designing a questionnaire and collecting feedback, so that more valuable information is provided for the subsequent information asymmetric risk assessment.
Optionally, the labeling the multidimensional data according to the knowledge degree, and clustering the labeled multidimensional data by using the stakeholder as a clustering center includes the following steps: labeling the multidimensional data according to the understanding degree, wherein any one dimensional data in the labeled multidimensional data comprises at least two stakeholder labels and understanding degree labels corresponding to the stakeholder labels; summarizing the marked multidimensional data, and splitting the data of the multi-benefit related party labels into the data of the single-benefit related party labels; and summarizing the data of the labels of the single benefit related parties, and carrying out feature clustering by taking the labels of different benefit related parties as clustering centers. The selectable item provides more accurate information for subsequent analysis through labeling and clustering of multidimensional data, so that the asymmetric risk assessment of the information has more depth and operability.
Optionally, the obtaining the information asymmetry and the information distribution coefficient between different stakeholders by using the clustering results of different stakeholders includes the following steps: constructing an information distribution expression matrix according to the dimension characteristics of the multidimensional data; respectively constructing information distribution matrixes of different stakeholders by combining the clustering results with the information distribution expression matrixes; and obtaining the information asymmetry and the information distribution coefficient among different stakeholders according to the data representation in different dimensionalities in the information distribution matrixes of the different stakeholders. The information asymmetry degree and distribution situation among different stakeholders are quantified through construction and analysis of the information distribution matrix, and a more comprehensive basis and accuracy are provided for information asymmetry risk identification.
Optionally, the information asymmetry satisfies the following formula:wherein->，Representing packages in an information distribution expression matrixThe number of dimensions involved>Indicate->Stakeholders and->Information asymmetry of the stakeholder in the ith dimension,/for>Indicate->A data representation of a stakeholder in the ith dimension,indicate->A data representation of the interested party in the ith dimension; />Is indicated at->And->Taking the maximum value.
Optionally, the information distribution coefficient satisfies the following model:=wherein->Indicate->Stakeholders and->Information distribution coefficient between stakeholders, < ->，/>Representing the number of dimensions contained in the information distribution expression matrix,/->Weighting coefficients representing the jth stakeholder in the ith dimension, ++>Indicate->Data representation of the stakeholder in the ith dimension,>indicate->Within the individual dimension->Weighting coefficients of the stakeholders, +.>Indicate->The interested party is at->Data representation in the individual dimensions.
Optionally, the identifying the risk of information asymmetry of different stakeholders based on the target service by combining the information asymmetry and the information distribution coefficient includes the following steps: constructing an information asymmetry risk prediction model by using the information asymmetry and the information distribution coefficient; predicting the information asymmetric risk intensity of different stakeholders based on the target service by using the information asymmetric risk prediction model; and evaluating the information asymmetric risks of different stakeholders based on the target service according to the information asymmetric risk intensity. The selectable item accurately predicts the information asymmetric risk intensity of different stakeholders in the target service by constructing the information asymmetric risk prediction model, thereby helping to realize more accurate risk assessment and decision.
Optionally, the information asymmetric risk prediction model comprises an information asymmetric risk intensity prediction model of any two stakeholders based on the target service and an information asymmetric risk intensity prediction model of all stakeholders based on the target service; wherein, any two stakeholders based on the information asymmetric risk intensity prediction model of the target service satisfy the following formula:wherein->Indicate->Stakeholders and->Information asymmetric risk intensity between stakeholders, < ->，/>Representing the number of dimensions contained in the information distribution expression matrix,/->Indicate->Stakeholders and->Information distribution coefficient between stakeholders, < ->Indicate->Stakeholders and->Information asymmetry of the interested party in the ith dimension; and all stakeholders meet the following formulas based on the information asymmetric risk intensity prediction model of the target service: />Wherein->Information asymmetric risk intensity representing that all stakeholders are based on the same target service,/for>Indicate->Stakeholders and->Information asymmetric risk intensity between stakeholders, < ->，/>，/>，/>Indicating the number of stakeholders.
In a second aspect, in order to better execute the service risk identification method, the invention further provides a service risk identification system. The business risk identification system provided by the invention comprises the following steps: the system comprises an input device, a processor, a memory and an output device, wherein the input device, the processor, the memory and the output device are mutually connected, the memory is used for storing a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the business risk identification method provided by the first aspect of the invention. The business risk identification system provided by the invention adopts the structures of the input equipment, the processor, the memory and the output equipment, and can realize the efficient execution of the innovative business risk identification method provided by the invention through corresponding stored computer programs and program instructions.
Drawings
FIG. 1 is a flowchart of a business risk identification method provided by an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a business risk identification system according to an embodiment of the present invention.
Detailed Description
Specific embodiments of the invention will be described in detail below, it being noted that the embodiments described herein are for illustration only and are not intended to limit the invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that: no such specific details are necessary to practice the invention. In other instances, well-known circuits, software, or methods have not been described in detail in order not to obscure the invention.
Throughout the specification, references to "one embodiment," "an embodiment," "one example," or "an example" mean: a particular feature, structure, or characteristic described in connection with the embodiment or example is included within at least one embodiment of the invention. Thus, the appearances of the phrases "in one embodiment," "in an embodiment," "one example," or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. Moreover, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and that the illustrations are not necessarily drawn to scale.
In an alternative embodiment, please refer to fig. 1, fig. 1 is a flowchart of a business risk identification method according to an embodiment of the present invention. As shown in fig. 1, the business risk identification method includes the following steps:
s01, one or more target services are selected, and stakeholders of the target services are determined, wherein the number of stakeholders comprises two or more than two.
The target business proposed by the present invention refers to a specific financial transaction, activity or service. In the field of internet finance, the target business may be one or more investment projects, loan transactions, financial products, or other businesses involving funds movement and transactions. For example, for an internet financial platform, the target business may be one or more internet consumer credit products on the internet financial platform.
Further, the stakeholder refers to each party having a direct or indirect stakeholder with the business result and process in the target business. For example, in an internet consumer credit service, interested parties may include interested parties on any two or more of a paybank, a credit bureau, a service operations platform.
Specifically, based on the internet financial platform, for an internet consumed credit product on the platform, a stakeholder of the internet consumed credit product comprises a paying bank and a letter increasing organization.
S02, acquiring multidimensional data of the target service, and acquiring the knowledge degree of different stakeholders on the multidimensional data.
The multi-dimensional data particularly refers to various data of different types related to the target business obtained from a plurality of different incoming channels. Further, the multidimensional data includes one or more types of data among business data, transaction data, operational data, user data, market data, risk data, financial data, or technical data.
Wherein, the service data refers to basic information directly related to the target service, and covers the property, type, scale and the like of the service. In the target business based on the internet financial platform, the business data may include characteristics, interest rate, repayment modes and the like of different consumed credit products.
The transaction data refers to data generated by a target service in the actual transaction process, including the amount, time, place and the like of the transaction. For investment projects, the transaction data may be an investment amount, an investment time, etc.
The operation data refers to the operation and management of the target service, and may include the operation cost, efficiency, user activity and the like of the platform. In investment projects, the operational data may include operating status of the project, operating costs, etc.
The user data refers to information of target service participants, including their personal information, historical behavior, preferences, etc. In an investment project, the user data may be personal information of an investor, investment history, or the like.
The market data refers to information related to the market where the target business is located, such as market trend, competition condition and the like. In the lending business, the market data may include supply and demand conditions, interest rate trends, etc. of the lending market.
The risk data refers to information about risks related to target business, including historical risk events, loss conditions and the like. In financial product sales, the risk data may be historical performance of similar products, risk ratings, and the like.
The financial data refers to funding information related to a target business, such as an equity sheet, a cash flow sheet, etc. In investment projects, financial data may include the flow of funds, revenue, etc. for the project.
The technical data refers to data related to technologies and systems related to target business, such as technical architecture, security and the like of a platform. In the field of financial science and technology, technical data may include adopted technical schemes, system performances and the like.
Further, the step S02 of obtaining knowledge of the multidimensional data by different stakeholders includes the following steps:
s021, sorting the multidimensional data, and eliminating sensitive data in the multidimensional data.
Step S021 cleans and sorts the data passing through multiple channels or sources to ensure the accuracy and consistency of the data. Meanwhile, data of sensitive information related to personal privacy and the like needs to be removed or anonymized to protect privacy and comply with regulations.
S022, designing a corresponding knowledge degree questionnaire based on the tidied multidimensional data.
Step S022 designs a corresponding knowledge degree questionnaire according to the tidied multidimensional data so as to evaluate the knowledge degree of different stakeholders on the target service. Further, the awareness questionnaire contains questions of different dimensions related to the business, the number of questions in any dimension including one or more, and any of the questions may be in the form of a choice question, a judgment question, or an openness question.
In this embodiment, based on an internet credit consumption product in the internet financial platform, a learning degree questionnaire is designed, where the learning degree questionnaire includes questions covering multiple dimensions of business data, operation data, market data, and the like, and a plurality of options are provided in any dimension, where the options of any option include: "unaware", "basically understood", "very understood".
S023, obtaining the knowledge degree of the multidimensional data by different stakeholders by using the knowledge degree questionnaire.
Step S023 distributes questionnaires to different stakeholders and collects answers using the designed awareness questionnaire. The answers to the questionnaire will reflect the degree of knowledge of the target business by the various stakeholders, either quantitatively (e.g., scores, ratings) or qualitatively (e.g., word descriptions) for subsequent analysis and evaluation.
In this embodiment, a learning level questionnaire designed based on an internet credit product consumed by the internet in the internet financial platform is issued to the corresponding issuing bank and credit enhancing organization, and further, a score is calculated for each stakeholder according to the collected answers. Specifically, the option for the question "does not know" the score of 0, "basically knows" the score of 1, and "very knows" the score of 2. The scores of each question are accumulated to obtain a comprehensive awareness score of a dimensional question.
In this embodiment, by collecting the questionnaire answers of different stakeholders and calculating the scores, we can quantify the degree of knowledge of different aspects, providing basis for subsequent information analysis and risk assessment.
And S03, labeling the multidimensional data according to the knowledge degree, and clustering the labeled multidimensional data by taking the stakeholder as a clustering center.
When the financial field involves businesses in which multiple stakeholders participate, there may be significant differences in the degree of understanding and points of interest of different stakeholders for a particular business. By introducing a questionnaire, the data can be marked and clustered, so that the degree of information asymmetry among different stakeholders can be quantitatively evaluated. Further, based on the knowledge degree obtained by the questionnaire, the step S03 of labeling the multidimensional data according to the knowledge degree, and clustering the labeled multidimensional data by using the stakeholder as a clustering center includes the following steps:
s031, labeling the multi-dimensional data according to the learning degree, wherein any one of the labeled multi-dimensional data comprises at least two stakeholder labels and learning degree labels corresponding to the stakeholder labels.
It should be understood that step S031 is a labeling operation performed based on the collated multidimensional data. In this embodiment, the scores of the different dimension types of questions in the knowledge questionnaire for a stakeholder are respectively marked as the labels of the corresponding dimension data for the stakeholder and the score of the corresponding dimension question. Since there are at least two stakeholders of the target service, at least two stakeholder tags are included for any one data, and scores corresponding to the two stakeholder tags, respectively.
In this embodiment, any dimension data in the noted multidimensional label satisfies the following form (multi-stakeholder label): (data type i, "stakeholder 1", "score of stakeholder 2", … "," score of stakeholder M "), wherein,，/>dimension number characterizing data type, +.>Indicating the number of stakeholders.
S032, summarizing the marked multidimensional data, and splitting the data of the multi-benefit related party labels into the data of the single-benefit related party labels.
In this embodiment, after any dimension data in the labeled multidimensional label is split into data of a single benefit related party label, the following form is satisfied: (data type i, "stakeholder 1", "score of stakeholder 1"), (data type i, "stakeholder 2", "score of stakeholder 2"), … …, (data type i, "stakeholder M", "score of stakeholder M").
S033, summarizing the data of the labels of the single benefit related parties, and carrying out feature clustering by taking the labels of different benefit related parties as clustering centers.
Step S033 performs cluster analysis on the multidimensional data by stakeholder labels, classifying the data having the same stakeholder as one type.
S04, obtaining information asymmetry and information distribution coefficients among different stakeholders by using clustering results of different stakeholders.
In an optional embodiment, the obtaining the information asymmetry and the information distribution coefficient between different stakeholders by using the clustering results of the different stakeholders includes the following steps:
s041, constructing an information distribution expression matrix according to the dimension characteristics of the multidimensional data.
In this embodiment, the information distribution expression matrix satisfies the following formula:wherein Q represents an information distribution expression matrix, < >>To->Data representations respectively representing different dimensions in the information distribution expression matrix,/for>Representing the number of dimensions contained in the information distribution expression matrix,/->Is determined by the total number of data types contained in the multidimensional data.
In particular, the method comprises the steps of,a data representation representing the 1 st dimension of the information distribution expression matrix, namely the 1 st dimension of the multidimensional data>A data representation of a seed data type; />A data representation representing the 2 nd dimension of the information distribution expression matrix, namely the +.>A data representation of a seed data type; />A data representation representing the nth dimension of the information distribution expression matrix, namely the +_th of the multidimensional data>A data representation of a data type. Further, the data representation of any of the data types in the multidimensional data described above may be a score of the corresponding stakeholder on the corresponding dimensional question.
S042, combining the information distribution expression matrixes by using the clustering result, and respectively constructing information distribution matrixes of different stakeholders.
It should be understood that, since the knowledge degree of the target service by different stakeholders is different, the specific data information contained in the information distribution matrix of the different stakeholders is also different; because the information distribution matrixes of different stakeholders are set based on the same information distribution expression matrix Q, the information distribution matrix of any stakeholder satisfies the following formula:wherein->，/>Representing the number of stakeholders, ++>Information distribution matrix representing the jth stakeholder, further,/>Data representation representing the jth stakeholder in the 1 st data dimension ++>Data representation representing the jth stakeholder in the 2 nd data dimension,/for>A data representation representing the jth stakeholder in the nth data dimension.
S043, according to data representation in different dimensions in the information distribution matrixes of different stakeholders, obtaining the information asymmetry and the information distribution coefficient among different stakeholders.
In this embodiment, the degree of information asymmetry in any dimension between the different stakeholders satisfies the following formula:wherein->，/>Representing the number of dimensions contained in the information distribution expression matrix,/->Indicate->Stakeholders and->Information asymmetry of the stakeholder in the ith dimension,/for>Indicate->Data representation of the stakeholder in the ith dimension,>indicate->A data representation of the interested party in the ith dimension; />Is indicated at->And->Taking the maximum value.
In this embodiment, the information distribution coefficient is used to measure the degree of asymmetry of data distribution of different stakeholders in different dimensions. Specifically, the information distribution coefficient satisfies the following model:=/>wherein->Indicate->Stakeholders and->Information distribution coefficient between stakeholders, < ->，/>Representing the number of dimensions contained in the information distribution expression matrix,/->Weighting coefficients representing the jth stakeholder in the ith dimension, ++>Indicate->Data representation of the stakeholder in the ith dimension,>indicate->Within the individual dimension->Weighting coefficients of the stakeholders, +.>Indicate->The interested party is at->Data representation in the individual dimensions.
S05, combining the information asymmetry degree and the information distribution coefficient, and identifying information asymmetry risks of different stakeholders based on the target service.
In an alternative embodiment, the identifying the risk of information asymmetry of different stakeholders based on the target service by combining the information asymmetry and the information distribution coefficient includes the steps of:
s051, constructing an information asymmetry risk prediction model by using the information asymmetry degree and the information distribution coefficient.
In this embodiment, the information asymmetric risk prediction model includes an information asymmetric risk intensity prediction model of any two different stakeholders based on the same target service, and an information asymmetric risk intensity prediction model of all stakeholders based on the same target service.
Further, the information asymmetric risk intensity prediction model of the same target service is based on any two different stakeholders, and the following formula is satisfied:wherein->Indicate->Stakeholders and->Information asymmetric risk intensity between stakeholders, < ->，/>Representing the number of dimensions contained in the information distribution expression matrix,/->Indicate->Stakeholders and->Information distribution coefficient between stakeholders, < ->Indicate->Stakeholders and->Information asymmetry of the stakeholder in the i-th dimension.
Further, the information asymmetric risk intensity prediction model of the same target service is based on all stakeholders, and the following formula is satisfied:wherein->Information asymmetric risk intensity representing that all stakeholders are based on the same target service,/for>Indicate->Stakeholders and->Information asymmetric risk intensity between stakeholders, < ->，/>，/>，/>Indicating the number of stakeholders.
S052, predicting the information asymmetric risk intensity of different stakeholders based on the target service by using the information asymmetric risk prediction model.
In this embodiment, the constructed information asymmetric risk prediction model is used to predict the information asymmetric risk intensity of different stakeholders based on the specific target service. Specifically, according to the prediction model set up in step S051, the information asymmetric risk intensity between any two different stakeholders and the overall information asymmetric risk intensity of all stakeholders can be calculated respectively.
S053, evaluating the information asymmetric risk of different stakeholders based on the target service according to the information asymmetric risk intensity.
According to the predicted information asymmetric risk intensity of different stakeholders and the overall information asymmetric risk intensity of all stakeholders, the information asymmetric degree of different stakeholders based on specific target service and the overall information asymmetric degree of all stakeholders can be respectively and quantitatively judged. A greater intensity of information asymmetry risk indicates a higher risk of potential information asymmetry, while a smaller intensity indicates a more balanced information.
Step S01 to step S05 calculate corresponding information asymmetry and information distribution coefficient by analyzing the knowledge degree of a plurality of stakeholders of the target service to the multidimensional data, thereby realizing the information asymmetry risk among different stakeholders.
In yet another alternative embodiment, please refer to fig. 1, fig. 1 is a flowchart of a business risk identification method according to an embodiment of the present invention. As shown in fig. 1, the business risk identification method further includes the following steps:
s06, setting an information asymmetry risk threshold, and triggering an early warning mechanism when the information asymmetry risk exceeds the information asymmetry risk threshold.
Further, the early warning mechanism is to send out an alarm in time to pay attention to and take appropriate measures when the risk of information asymmetry exceeds a set threshold, and it can be understood that the early warning mechanism can be set in a personalized manner based on different service conditions.
In a specific embodiment, an internet financial platform of an internet consumption credit service related to a paying bank and a credit enhancing mechanism sets corresponding information asymmetry risk thresholds according to historical data for a plurality of internet consumption credit services on the internet financial platform; and the service risk identification method is utilized to monitor the asymmetric risks of information of two parties of the paying bank and the letter increasing organization corresponding to the internet consumption credit service in real time.
If the asymmetric risk of information in a certain service exceeds a preset threshold, the system automatically triggers an early warning mechanism, and once the early warning is triggered, the system can inform related personnel, such as a cash deposit bank, a letter adding mechanism, a platform manager and the like, in a mode of short message, mail, APP notification and the like, so as to remind the related personnel of possible risk conditions. After the early warning is triggered, relevant personnel can take appropriate measures according to the situation, such as re-evaluating investment or borrowing decisions, adjusting platform operation strategies and the like, so as to reduce potential risks.
Step S06 increases real-time monitoring of information asymmetry risk, and through setting an information asymmetry risk threshold, once the information asymmetry risk exceeds the threshold, an early warning mechanism is automatically triggered, service participants are timely reminded, and potential risks can be rapidly handled.
In order to better implement the above-mentioned business risk identification method, in yet another alternative embodiment, the present invention further provides a business risk identification system, please refer to fig. 2, fig. 2 is a schematic structural diagram of the business risk identification system provided by the embodiment of the present invention.
As shown in fig. 2, the business risk identification system includes an input device, a processor, a memory, and an output device, where the input device, the processor, the memory, and the output device are connected to each other, and the memory is used to store a computer program, where the computer program includes program instructions, and the processor is configured to call the program instructions to execute the business risk identification method provided by the present invention.
Further, the input device may be a keyboard, a mouse, a touch screen, etc. for inputting relevant data and information into the system. For example, in the financial field, various data of investment items may be input into the system through an input device.
Further, the above-described processor is a core component of the system, responsible for performing various calculations and operations. In the present invention, the processor is configured to invoke a computer program stored in the memory to perform the business risk identification method. The processor processes, analyzes and calculates the input data to generate a risk assessment result.
Further, the above memory is used for storing computer programs, data and information. In this case the memory stores the computer program required for the invention, including the program instructions required for performing the business risk identification method.
Further, the output device may be a display screen, a printer, a report generator, etc. for presenting the results processed by the system to the user. In the business risk recognition system, the output device may display a risk assessment result, a graph, or the like.
The business risk identification system provided by the invention can receive input data by connecting the components, generate a risk assessment result after processing and analyzing, and present the result to a user for business decision reference.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (10)
1. The business risk identification method is characterized by comprising the following steps of:
selecting one or more target services, and determining stakeholders of the target services, wherein the number of stakeholders comprises two or more than two;
acquiring multidimensional data of the target service, and acquiring the knowledge degree of different stakeholders on the multidimensional data;
labeling the multidimensional data according to the knowledge degree, and clustering the labeled multidimensional data by taking the stakeholder as a clustering center;
obtaining information asymmetry and information distribution coefficients among different stakeholders by using clustering results of different stakeholders;
and combining the information asymmetry and the information distribution coefficient, and identifying information asymmetry risks of different stakeholders based on the target service.
2. The business risk identification method according to claim 1, characterized in that the business risk identification method further comprises the steps of:
setting an information asymmetry risk threshold, and triggering an early warning mechanism when the information asymmetry risk exceeds the information asymmetry risk threshold.
3. The business risk identification method according to any one of claims 1-2, wherein the obtaining the knowledge of the multidimensional data by different stakeholders includes the steps of:
sorting the multidimensional data, and eliminating sensitive data in the multidimensional data;
based on the multi-dimensional data after the arrangement, designing a corresponding knowledge degree questionnaire;
and acquiring the knowledge degree of the multidimensional data by the different stakeholders by using the knowledge degree questionnaire.
4. The business risk identification method according to claim 3, wherein the labeling of the multidimensional data according to the degree of knowledge and clustering the labeled multidimensional data with the stakeholder as a cluster center includes the steps of:
labeling the multidimensional data according to the understanding degree, wherein any one dimensional data in the labeled multidimensional data comprises at least two stakeholder labels and understanding degree labels corresponding to the stakeholder labels;
summarizing the marked multidimensional data, and splitting the data of the multi-benefit related party labels into the data of the single-benefit related party labels;
and summarizing the data of the labels of the single benefit related parties, and carrying out feature clustering by taking the labels of different benefit related parties as clustering centers.
5. The business risk identification method according to claim 4, wherein the step of obtaining the information asymmetry and the information distribution coefficient between different stakeholders by using the clustering results of the different stakeholders includes the steps of:
constructing an information distribution expression matrix according to the dimension characteristics of the multidimensional data;
respectively constructing information distribution matrixes of different stakeholders by combining the clustering results with the information distribution expression matrixes;
and obtaining the information asymmetry and the information distribution coefficient among different stakeholders according to the data representation in different dimensionalities in the information distribution matrixes of the different stakeholders.
6. The business risk identification method of claim 5, wherein the degree of information asymmetry satisfies the following formula:wherein->，/>Representing the number of dimensions contained in the information distribution expression matrix,/->Indicate->Stakeholders and->Information asymmetry of the stakeholder in the ith dimension,/for>Indicate->Data representation of the stakeholder in the ith dimension,>indicate->A data representation of the interested party in the ith dimension; />Is indicated at->And->Taking the maximum value.
7. The business risk identification method of claim 6, wherein the information distribution coefficient satisfies the following model:=/>wherein->Indicate->Stakeholders and->Information distribution coefficient between stakeholders, < ->，/>Representing the number of dimensions contained in the information distribution expression matrix,/->Weighting coefficients representing the jth stakeholder in the ith dimension, ++>Indicate->Data representation of the stakeholder in the ith dimension,>indicate->Within the individual dimension->Weighting coefficients of the stakeholders, +.>Indicate->The interested party is at->Data representation in the individual dimensions.
8. The business risk identification method according to claim 5, wherein the step of identifying the information asymmetry risk of different stakeholders based on the target business by combining the information asymmetry and the information distribution coefficient comprises the steps of:
constructing an information asymmetry risk prediction model by using the information asymmetry and the information distribution coefficient;
predicting the information asymmetric risk intensity of different stakeholders based on the target service by using the information asymmetric risk prediction model;
and evaluating the information asymmetric risks of different stakeholders based on the target service according to the information asymmetric risk intensity.
9. The business risk identification method of claim 8, wherein the information asymmetric risk prediction model comprises an information asymmetric risk intensity prediction model based on the target business for any two stakeholders and an information asymmetric risk intensity prediction model based on the target business for all stakeholders;
the information asymmetric risk intensity prediction model of any two stakeholders based on the target service satisfies the following formula:wherein->Indicate->Stakeholders and->Information asymmetric risk intensity between stakeholders, < ->，/>Representing the number of dimensions contained in the information distribution expression matrix,/->Indicate->Stakeholders and->Information distribution coefficient between stakeholders, < ->Indicate->Stakeholders and->Information asymmetry of the interested party in the ith dimension;
and all stakeholders meet the following formulas based on the information asymmetric risk intensity prediction model of the target service:wherein->Representing the asymmetric risk intensity of information based on the same target service for all stakeholders,indicate->Stakeholders and->Information asymmetric risk intensity between stakeholders, < ->，，/>，/>Indicating the number of stakeholders.
10. A business risk identification system, the business risk identification system comprising: input device, processor, memory and output device, said input device, processor, memory and output device being interconnected, wherein the memory is adapted to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the business risk identification method according to any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311147215.1A CN116911986A (en) | 2023-09-07 | 2023-09-07 | Business risk identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311147215.1A CN116911986A (en) | 2023-09-07 | 2023-09-07 | Business risk identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116911986A true CN116911986A (en) | 2023-10-20 |
Family
ID=88354961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311147215.1A Pending CN116911986A (en) | 2023-09-07 | 2023-09-07 | Business risk identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116911986A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150227869A1 (en) * | 2014-02-10 | 2015-08-13 | Bank Of America Corporation | Risk self-assessment tool |
| CN105631742A (en) * | 2015-12-24 | 2016-06-01 | 安徽融信金模信息技术有限公司 | Small and medium enterprise credit evaluation method |
| CN109214617A (en) * | 2017-06-29 | 2019-01-15 | 格局商学教育科技（深圳）有限公司 | A kind of internet financial risks qualitative assessment auditing system |
| CN112669039A (en) * | 2020-12-31 | 2021-04-16 | 重庆银行股份有限公司 | Client risk control system and method based on knowledge graph |
| CN115082209A (en) * | 2022-06-28 | 2022-09-20 | 平安银行股份有限公司 | Business data risk early warning method and device, computer equipment and storage medium |
| CN115600818A (en) * | 2022-10-27 | 2023-01-13 | 中国农业银行股份有限公司（Cn） | Multi-dimensional scoring method and device, electronic equipment and storage medium |
| CN116305168A (en) * | 2023-05-11 | 2023-06-23 | 北京双鑫汇在线科技有限公司 | Multi-dimensional information security risk assessment method, system and storage medium |
-
2023
- 2023-09-07 CN CN202311147215.1A patent/CN116911986A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150227869A1 (en) * | 2014-02-10 | 2015-08-13 | Bank Of America Corporation | Risk self-assessment tool |
| CN105631742A (en) * | 2015-12-24 | 2016-06-01 | 安徽融信金模信息技术有限公司 | Small and medium enterprise credit evaluation method |
| CN109214617A (en) * | 2017-06-29 | 2019-01-15 | 格局商学教育科技（深圳）有限公司 | A kind of internet financial risks qualitative assessment auditing system |
| CN112669039A (en) * | 2020-12-31 | 2021-04-16 | 重庆银行股份有限公司 | Client risk control system and method based on knowledge graph |
| CN115082209A (en) * | 2022-06-28 | 2022-09-20 | 平安银行股份有限公司 | Business data risk early warning method and device, computer equipment and storage medium |
| CN115600818A (en) * | 2022-10-27 | 2023-01-13 | 中国农业银行股份有限公司（Cn） | Multi-dimensional scoring method and device, electronic equipment and storage medium |
| CN116305168A (en) * | 2023-05-11 | 2023-06-23 | 北京双鑫汇在线科技有限公司 | Multi-dimensional information security risk assessment method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Beck et al. | Bank supervision and corruption in lending | |
| Kallberg et al. | The value of private sector business credit information sharing: the US case | |
| US8930254B2 (en) | Financial methodology to valuate and predict the news impact of major events on financial instruments | |
| Ding et al. | A machine learning-based peer selection method with financial ratios | |
| Mousavi et al. | Multi-criteria ranking of corporate distress prediction models: empirical evaluation and methodological contributions | |
| US20220343433A1 (en) | System and method that rank businesses in environmental, social and governance (esg) | |
| Paul et al. | Why do firms invest in accounts receivable? An empirical investigation of the Malaysian manufacturing sector | |
| Mathews | Innovation portfolio architecture—Part 2: Attribute selection and valuation | |
| Dass | Data mining in banking and finance: a note for bankers | |
| Okoye et al. | Effect of intangible assets on performance of quoted companies in Nigeria | |
| Jackson | CRM: From ‘art to science’ | |
| Vuković et al. | Corporate bankruptcy prediction: evidence from wholesale companies in the Western European countries | |
| Sheikhi et al. | Financial distress prediction using distress score as a predictor | |
| KR102249028B1 (en) | System for Debt Repayment Capability Evaluation Of Corporation | |
| Abdullah et al. | Credit risk assessment models of retail microfinancing: The case of a Malaysian national savings bank’s branch | |
| CN116911986A (en) | Business risk identification method and system | |
| Fanani et al. | The Effect of Managerial Ability and Tone of Earnings Announcements towards Market Reactions | |
| CA3170618A1 (en) | Data processing method and device | |
| Darshi et al. | The Adoption of Computerized Accounting System (CAS) in Small and Medium Scale Enterprises (SMEs): With Special Reference to SMEs located in Matara District, Sri Lanka | |
| Spruit et al. | Bidqi: the business impacts of data quality interdependencies model | |
| Son et al. | Supply chain information in analyst reports on publicly traded companies | |
| Elsayed | Predictability of financial statements fraud-risk | |
| Bandyopadhyay | Basic statistics for risk management in banks and financial institutions | |
| CN112634048A (en) | Anti-money laundering model training method and device | |
| Sandu et al. | The R&D and innovation systems in Romania and Bulgaria in the EU context |
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 |