CN112801528A - Vehicle insurance risk monitoring method and device, storage medium and computer equipment - Google Patents
Vehicle insurance risk monitoring method and device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN112801528A CN112801528A CN202110162944.9A CN202110162944A CN112801528A CN 112801528 A CN112801528 A CN 112801528A CN 202110162944 A CN202110162944 A CN 202110162944A CN 112801528 A CN112801528 A CN 112801528A
- Authority
- CN
- China
- Prior art keywords
- insurance
- risk
- vehicle
- insurance company
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Technology Law (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a method and a device for monitoring risk of vehicle insurance, a storage medium and computer equipment, and relates to the technical field of big data analysis. The method comprises the following steps: collecting vehicle insurance policy data of each insurance company on a national vehicle insurance information platform; generating risk monitoring index data of each insurance company based on the vehicle insurance policy data of each insurance company, wherein the risk monitoring index data comprise one or more of vehicle insurance business development health index, vehicle insurance market perception index, market pricing deviation degree, vehicle insurance market risk disturbance index and risk screening capacity index; and obtaining the classified supervision indexes of the insurance companies and the classified risk supervision grades of the insurance companies according to the risk monitoring index data of the insurance companies. The method can reflect the real level of each insurance company in the aspect of risk management and control capability from each dimension, and improves the risk supervision efficiency and the risk supervision effect of the car insurance industry.
Description
Technical Field
The invention relates to the technical field of big data analysis, in particular to a method and a device for monitoring risk of vehicle insurance, a storage medium and computer equipment.
Background
At present, the vehicle insurance industry in China implements a unified standard rate system, wherein the standard rate is issued by insurance industry association and comprises a unified basic premium standard and a non-reimbursement preferential treatment factor (NCD coefficient) discount standard, namely, an insurance company can establish a corresponding independent discount coefficient on the basis of the standard rate and form a final quote for consumers. Then, the insurance company records the product scheme in advance in a supervision agency, wherein the product scheme comprises the upper and lower bounds of the planned implementation average independent discount coefficient, and the supervision agency reviews and evaluates the product scheme provided by the insurance company.
In addition, the supervising agencies such as the bank insurance bureau and the local bank insurance bureau also regularly require the insurance company to report related business data and financial data, such as: the data such as premium income and the number of insurance policy are used for grasping the business condition of each insurance company, and relevant supervision auxiliary systems such as supervision information statistical systems are established, and the systems mainly perform statistical analysis on the existing business condition of the insurance company.
However, there are many problems in managing and controlling the car insurance risk of the insurance company by the currently established system of the regulatory organization, for example, when the existing regulatory system monitors the car insurance risk of the insurance company, the established regulatory indexes have an obvious hysteresis problem, that is, the existing regulatory indexes can only reflect the existing market insurance conditions, such as premium scale and number of insurance policy, but these indexes cannot reflect the real risk of the market. Moreover, the existing monitoring system is usually based on the related financial data submitted by the insurance company to the monitoring department for monitoring, and the financial data has the possibility of artificial regulation, so that the existing monitoring system is not objective and fair. In addition, the existing monitoring system cannot accurately and pertinently monitor the potential risks of each insurance company, so that the risk monitoring efficiency of the car insurance industry is low and the monitoring effect is poor. These problems result in the inability of regulatory agencies to effectively standardize and monitor market entities, thereby making it difficult to lead insurance companies to develop rational competition based on risk management.
Disclosure of Invention
In view of this, the present application provides a method and an apparatus for monitoring a risk of car insurance, a storage medium, and a computer device, and mainly aims to solve the technical problems of low efficiency and poor supervision effect of monitoring a risk of car insurance.
According to a first aspect of the present invention, there is provided a vehicle insurance risk monitoring method, the method comprising:
collecting vehicle insurance policy data of each insurance company on a national vehicle insurance information platform;
generating risk monitoring index data of each insurance company based on the vehicle insurance policy data of each insurance company, wherein the risk monitoring index data comprise one or more of vehicle insurance business development health index, vehicle insurance market perception index, market pricing deviation degree, vehicle insurance market risk disturbance index and risk screening capacity index;
and obtaining the classified supervision indexes of the insurance companies and the classified risk supervision grades of the insurance companies according to the risk monitoring index data of the insurance companies.
According to a second aspect of the present invention, there is provided a vehicle insurance risk monitoring apparatus, the apparatus comprising:
the data acquisition module is used for acquiring the vehicle insurance policy data of each insurance company on a national vehicle insurance information platform;
the data processing module is used for generating risk monitoring index data of each insurance company based on the vehicle insurance policy data of each insurance company, wherein the risk monitoring index data comprise one or more of vehicle insurance business development health indexes, vehicle insurance market perception indexes, market pricing deviation degrees, vehicle insurance market risk disturbance indexes and risk screening capacity indexes;
and the result output module is used for obtaining the classified supervision indexes of the insurance companies and the classified supervision grades of the risks of the insurance companies according to the risk monitoring index data of the insurance companies.
According to a third aspect of the present invention, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described vehicle risk monitoring method.
According to a fourth aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above-mentioned risk monitoring method when executing the program.
The invention provides a vehicle insurance risk monitoring method, a device, a storage medium and computer equipment. According to the method, objective vehicle insurance policy data are collected on a national vehicle insurance information platform, and index measurement and risk prediction are carried out by utilizing the collected vehicle insurance policy data, so that multiple risk monitoring index data can be obtained. The multiple risk monitoring index data can quantitatively monitor the real level of each insurance company in the vehicle insurance industry in the aspects of service development quality, market reflection effect, market pricing deviation degree, risk management and control, risk screening capacity and the like, and can also be synthesized to quantitatively evaluate the risk classification supervision levels of each insurance company, so that each insurance company is accurately divided into the risk classification supervision levels, the risk supervision efficiency and the risk supervision effect of the vehicle insurance industry are improved, a supervision mechanism can conveniently predict the potential market risk of the vehicle insurance industry in advance, and the supervision mechanism can be helped to accurately implement market regulation and supervision measures.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a schematic flow chart illustrating a vehicle insurance risk monitoring method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating another vehicle insurance risk monitoring method according to an embodiment of the present invention;
FIG. 3 illustrates a risk monitoring diagram for an insurance company provided by an embodiment of the present invention;
FIG. 4 is a diagram illustrating risk classification monitoring in the vehicle insurance industry according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram illustrating a vehicle insurance risk monitoring device according to an embodiment of the present invention;
fig. 6 shows a schematic structural diagram of another vehicle insurance risk monitoring device provided by the embodiment of the invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In one embodiment, as shown in fig. 1, a method for monitoring risk of vehicle insurance is provided, which is described by taking the method as an example of being applied to a computer device such as a client or a server, and includes the following steps:
101. and acquiring the vehicle insurance policy data of each insurance company on the national vehicle insurance information platform.
The national vehicle insurance information platform is also called an industry vehicle insurance information platform, and is a comprehensive vehicle insurance information platform integrating functions of strong insurance, business insurance underwriting and claim settlement. At present, all the insurance policies implemented in continental areas of China need to be issued on national insurance information platforms. Therefore, the national vehicle insurance information platform can carry out efficient monitoring and analysis on real insurance policy data, and is more efficient compared with other supervision systems for post-reporting data.
Specifically, the computer device may collect, on a regular basis or in real time, the total vehicle insurance policy data of each insurance company from the national vehicle insurance information platform, wherein the vehicle insurance policy data mainly includes vehicle underwriting data and vehicle settlement data, and for example, the vehicle insurance policy data may include underwriting areas of each insurance company, endorsement insurance fees (including endorsement insurance fees for strong insurance and business insurance), the number of endorsements, average insurance fees, insurance rates, quotations, independent discount coefficients, and the like. In this embodiment, the computer device may collect the full production data of the car insurance industry from the national car insurance information platform, then perform cleaning and grouping on the collected full production data to obtain various types of car insurance policy data required for calculation, and finally perform classified storage on the various types of car insurance policy data according to dimensions such as date, area, insurance company, car price, and insurance amount, so that the computer device can further process the collected data.
102. And generating risk monitoring index data of each insurance company based on the vehicle insurance policy data of each insurance company.
Specifically, the computer device may generate one or more risk monitoring index data of each insurance company based on the vehicle insurance policy data of each insurance company collected from the national vehicle insurance information platform. In this embodiment, the risk monitoring indicator data may include one or more of an automobile insurance business development health index, an automobile insurance market perception index, a market pricing deviation degree, an automobile insurance market risk disturbance index, and a risk screening capability index. The risk monitoring index data can be obtained by means of calculation of some actuarial prediction models.
In this embodiment, the car insurance business development health index can be used to reflect the situation of the car insurance business development and the development quality of the car insurance business development of the insurance company. Specifically, the car insurance business development health index can be obtained by comparing the total charge increase rate of the ticket insurance premium, the total charge increase rate of the number of the tickets and the procedure rate of the current preset period in the car insurance policy data of each insurance company with the total charge increase rate of the ticket insurance premium of the previous preset period and the procedure rate of the current preset period, and comparing the total charge increase rate of the ticket insurance premium, the total charge increase rate of the number of the tickets and the procedure rate of the current preset period with the current preset period in the whole car insurance policy data of the car insurance industry. The preset period can be set according to actual conditions, for example, one month, one quarter or one year, when comparing, each item of data of the insurance company needs to be compared with the corresponding item of data in the overall data of the car insurance industry, for example, the procedure rate of the current preset period of the insurance company is compared with the procedure rate of the current preset period of the overall car insurance industry, and the car insurance business development health index of each insurance company can be obtained by inputting one or more comparison values of the total increase rate of the signoff premium, the total increase rate of the number of signoff pieces and the procedure rate into the car insurance business development actuarial model. By using the index data of the development health index of the car insurance business, the business scale expansion situation and the cost input situation of each insurance company can be effectively measured, so that whether the business development situation of each insurance company is in a benign state or not can be effectively monitored.
Further, the vehicle insurance market awareness index may be used to reflect the extent of coverage and assurance of the vehicle insurance against the consumer's risk and the consumer's acceptance of the market. Specifically, the vehicle insurance market perception index is obtained by a comparison value between a ratio (insurance application rate) of the number of business insurance policy items to the number of strong insurance policy items in vehicle insurance policy data of each insurance company, a ratio (insurance application rate) of the number of high insurance policy items to the number of the three insurance policy items to the number of strong insurance policy items in a current preset period and a promotion ratio of the average premium income of each insurance policy in the previous preset period compared with the current preset period, and a ratio (insurance application rate) of the number of business insurance policy items to the number of strong insurance policy items in the whole vehicle insurance policy data of the vehicle insurance industry, a ratio (insurance application rate) of the number of high insurance policy items to the number of high insurance policy items in the three insurance policy items and a promotion ratio of the average premium income of each insurance. The preset period can be set according to actual conditions, for example, one month, one quarter or one year, when comparing, each item of data of the insurance company needs to be compared with corresponding data in the overall data of the vehicle insurance industry, for example, the number ratio of the high-insurance policy items of the insurance company is compared with the number ratio of the high-insurance policy items of the vehicle insurance industry, and the vehicle insurance market perception index of each insurance company can be obtained by inputting one or more contrast values into the vehicle insurance market perception precision model. Through the index data of the car insurance market perception index, the guarantee degree of each insurance company to the consumer and the market acceptance degree of the consumer to each insurance company can be effectively measured.
Further, the market pricing deviation may be used to reflect the deviation of the premium discount level of the insurer from the market average discount and the delivery regulatory discount, wherein the autonomic discount factor refers to the company adjusted rate of the insurer on an industry flat rate basis, i.e., the discount price that the insurer offers to the consumer. Specifically, the market pricing deviation degree can be obtained by a contrast value between the average autonomous discount coefficient of all the insurance policies in the vehicle insurance policy data of each insurance company and the average autonomous discount coefficient of all the insurance policies of the whole vehicle insurance industry, and a contrast value between the average autonomous discount coefficient of all the insurance policies in the vehicle insurance policy data of each insurance company and the average autonomous discount coefficient of all the insurance policies reported to the supervision mechanism by each insurance company, and the market pricing deviation degree of each insurance company can be obtained by inputting one or more contrast values into the market pricing deviation degree actuariation model. The pricing level of each insurance company can be effectively measured through the index data of the market pricing deviation degree, so that the pricing situation of each insurance company is monitored.
Further, the risk disturbance index of the vehicle insurance market can be used for reflecting future reimbursement risk of the insurance policy and disturbance conditions of the whole market. Specifically, the vehicle insurance market risk disturbance index can be obtained by a contrast value of the overall predicted pay-out rate of all insurance policies in the vehicle insurance policy data of each insurance company and the overall predicted pay-out rate of all insurance policies of the vehicle insurance industry as a whole, and a contrast value of the total vehicle insurance premium income of each insurance company and the total vehicle insurance premium income of the vehicle insurance industry as a whole. The predicted pay-off rate refers to a predicted value of future pay-off risk of each policy, and the predicted pay-off rate can be obtained by utilizing a pre-established predicted pay-off rate actuarial prediction model to output. Further, the risk disturbance index of the vehicle insurance market of each insurance company can be obtained by inputting the one or more comparison values into the vehicle insurance market risk disturbance actuarial model. Through the index data of the risk disturbance index of the car insurance market, the risk management level of each insurance company can be effectively measured, and therefore whether the future claims of each insurance company are in a reasonable level or not and the disturbance degree of the whole market are effectively monitored.
Further, the risk screening ability index may be used to reflect the insurance company's ability to identify and screen policy risks, i.e., whether the insurance company can offer matching premiums for policies with different risks. Specifically, the risk screening capability index can be obtained by averagely grouping all insurance policy terms of the insurance company and then calculating a contrast value of a standard deviation of the predicted odds of the grouped vehicle insurance policy data and the overall predicted odds of all insurance policies of the insurance company. The predicted odds can also be obtained by using the pre-established predicted odds actuarial prediction model output. Through the index data of the risk screening capacity index, the risk management level and the pricing level of each insurance company can be effectively measured, so that whether each insurance company has defects in the risk screening capacity or not can be effectively monitored, and a supervision mechanism is assisted to quickly and effectively identify the insurance company with poor risk screening capacity.
Through the risk monitoring index data, the real level of the insurance company in the aspects of service development quality, market reflection effect, market pricing deviation degree, risk control, risk screening capacity and the like can be quantitatively monitored, and a supervision mechanism can conveniently predict the potential market risk of the car insurance industry in advance, so that the accurate implementation of market regulation and control and supervision measures by the supervision mechanism is facilitated.
103. And obtaining the classified supervision indexes of the insurance companies and the classified risk supervision grades of the insurance companies according to the risk monitoring index data of the insurance companies.
Specifically, the computer device may integrate the risk monitoring index data of each insurance company obtained by measurement and calculation to obtain a classification supervision index of each insurance company, and then compare the classification supervision index of each insurance company with a classification supervision index threshold of each category to obtain a risk classification supervision level to which each insurance company belongs. For example, insurance companies with a categorical administration index exceeding a preset high risk threshold may be classified as high risk companies, insurance companies with a categorical administration index exceeding a preset medium risk threshold may be classified as medium risk companies, other insurance companies may be classified as low risk companies, and so forth. Through the classified supervision indexes of the insurance companies and the classified supervision levels of the risks divided by the insurance companies, the supervision mechanism can quickly track the market performance of the insurance companies and discover part of objects needing key supervision, particularly the insurance companies which develop malignant competition and possibly cause fluctuation of the whole market, and can quickly discover and issue supervision early warning according to the malignant competition and the classified supervision grades.
The vehicle insurance risk monitoring method provided by the embodiment includes the steps of firstly collecting vehicle insurance policy data of each insurance company on a national vehicle insurance information platform, then generating one or more risk monitoring index data of each insurance company based on the vehicle insurance policy data of each insurance company, wherein the risk monitoring index data comprises vehicle insurance business development health indexes, vehicle insurance market perception indexes, market pricing deviation degrees, vehicle insurance market risk disturbance indexes, risk screening capacity indexes and the like, and finally obtaining classification supervision indexes of each insurance company and the risk classification supervision grades of the insurance companies according to the risk monitoring index data of each insurance company. According to the method, objective vehicle insurance policy data are collected on a national vehicle insurance information platform, and index measurement and risk prediction are carried out by utilizing the collected vehicle insurance policy data, so that multiple risk monitoring index data can be obtained. The multiple risk monitoring index data can quantitatively monitor the real level of each insurance company in the vehicle insurance industry in the aspects of service development quality, market reflection effect, market pricing deviation degree, risk management and control, risk screening capacity and the like, and can also be synthesized to quantitatively evaluate the risk classification supervision levels of each insurance company, so that each insurance company is accurately divided into the risk classification supervision levels, the risk supervision efficiency and the risk supervision effect of the vehicle insurance industry are improved, a supervision mechanism can conveniently predict the potential market risk of the vehicle insurance industry in advance, and the supervision mechanism can be helped to accurately implement market regulation and supervision measures.
Further, as a refinement and an extension of the specific implementation of the above embodiment, in order to fully illustrate the implementation process of the embodiment, a method for monitoring risk of vehicle insurance is provided, as shown in fig. 2, the method includes the following steps:
201. and acquiring the vehicle insurance policy data of each insurance company on the national vehicle insurance information platform.
Specifically, the computer device may collect, on a regular basis or in real time, the total vehicle insurance policy data of each insurance company from the national vehicle insurance information platform, wherein the vehicle insurance policy data mainly includes vehicle underwriting data and vehicle settlement data, and for example, the vehicle insurance policy data may include underwriting areas of each insurance company, endorsement insurance fees (including endorsement insurance fees for strong insurance and business insurance), the number of endorsements, average insurance fees, insurance rates, quotations, independent discount coefficients, and the like. In this embodiment, the computer device may collect the full production data of the car insurance industry from the national car insurance information platform, then perform cleaning and grouping on the collected full production data to obtain various types of car insurance policy data required for calculation, and finally perform classified storage on the various types of car insurance policy data according to dimensions such as date, area, insurance company, car price, and insurance amount, so that the computer device can further process the collected data.
202. And generating risk monitoring index data of each insurance company based on the vehicle insurance policy data of each insurance company.
Specifically, the computer device may generate one or more risk monitoring index data of each insurance company based on the vehicle insurance policy data of each insurance company collected from the national vehicle insurance information platform. In this embodiment, the risk monitoring indicator data may include one or more of an automobile insurance business development health index, an automobile insurance market perception index, a market pricing deviation degree, an automobile insurance market risk disturbance index, and a risk screening capability index. The risk monitoring index data can be obtained by means of calculation of some actuarial prediction models.
In an optional implementation manner of this embodiment, the risk monitoring index data may include a car insurance business development health index. The car insurance business development health index can be used for reflecting the conditions of the car insurance business development and the development quality of the car insurance business of the insurance company. Specifically, for an insurance company i, the health degree index A of the vehicle insurance business development can be obtained through the following vehicle insurance business development actuarial modeliWherein, the model formula of the vehicle insurance service development actuarial model is as follows:
wherein, a1Is a weight coefficient, and the value range is 0-1.5, k1Is a power exponent with a value range of 0-2.3, XiThe speed of the total amount of the charge of the sign sheet in the current preset period in the vehicle insurance policy data of the insurance company i is increased compared with the speed in the previous preset period, and X is the speed of the total amount of the charge of the sign sheet in the current preset period in the whole vehicle insurance policy data of the vehicle insurance industry is increased compared with the speed in the previous preset period; a is2Is a weight coefficient, and the value range is 0-1.5, k2Is a power exponent with a value range of 0-2, YiThe total number of the signposts in the current preset period in the vehicle insurance policy data of the insurance company i is increased compared with the speed in the previous preset period, and Y is the total number of the signposts in the current preset period in the whole vehicle insurance policy data of the vehicle insurance industry is increased compared with the speed in the previous preset period; a is3Is a weight coefficient, and the value range is 0-2, k3Is a power exponent with a value range of 0-2.6, ZiThe procedure rate in the current preset period in the vehicle insurance policy data of the insurance company i, and the procedure rate in the current preset period in the overall vehicle insurance policy data of the vehicle insurance industry, wherein the preset period can be set according to the actual situation, such as one month, one quarter or one year.
In the vehicle insurance service development actuarial model, each weight parameter and power index can be adjusted according to actual conditions, and in addition, the vehicle insurance service development health index can be obtained according to one or more input values of the vehicle insurance service development actuarial model. By using the index data of the development health index of the car insurance business, the business scale expansion situation and the cost input situation of each insurance company can be effectively measured, so that whether the business development situation of each insurance company is in a benign state or not can be effectively monitored.
In an optional implementation manner of this embodiment, the risk monitoring index data may further include an automobile insurance market awareness index. Wherein, the vehicle insurance market perception index can be used for reflecting the covering and guarantee degree of the vehicle insurance to the risk of the consumer and the acceptance degree of the consumer to the market. Specifically, for a certain insurance company i, the following vehicle insurance market perception actuarial model can be used for obtaining the vehicle insurance market perception index BiWherein, the model formula of the vehicle insurance market perception actuarial model is as follows:
wherein, b1Is a weight coefficient, with a value range of 0-2.6, t1Is a power exponent with a value range of 0 to 1.5, FiIs the ratio of the number of the business insurance policy pieces and the number of the compulsory insurance policy pieces in the vehicle insurance policy data of the insurance company i (namely the business insurance application rate), and F is the ratio of the number of the business insurance policy pieces and the number of the compulsory insurance policy pieces in the vehicle insurance policy data of the whole vehicle insurance industry; b2Is a weight coefficient, and the value range is 0-2, t2Is a power exponent with a value range of 0-2.5, GiThe number of the three high-insurance premium policy in the vehicle insurance policy data of the insurance company i is in proportion, G is the number of the three high-insurance premium policy in the whole vehicle insurance policy data of the vehicle insurance industry, wherein the three high-insurance premium policy refers to the policy that the insurance premium of the three exceeds the preset insurance premium; b3Is a weight coefficient, the value range is 0-1.5, t3Is a power exponent with a value range of 0-2.3, HiIs the improvement ratio of the average premium income of each policy in the current preset period in the vehicle insurance policy data of the insurance company i to the average premium income of each policy in the previous preset period, and H is the average premium income of each policy in the current preset period in the overall vehicle insurance policy data of the vehicle insurance industry to the average premium income of each policy in the previous preset periodThe lift ratio of the inner.
In the vehicle insurance market perception degree actuarial model, each weight parameter and power exponent can be adjusted according to actual conditions, and in addition, the vehicle insurance market perception degree exponent can be obtained according to one or more input values in the actuarial model. Through the index data of the car insurance market perception index, the guarantee degree of each insurance company to the consumer and the market acceptance degree of the consumer to each insurance company can be effectively measured.
In an optional implementation of this embodiment, the risk monitoring indicator data may further include a market pricing deviation. Wherein, the autonomous discount coefficient refers to a rate which is made by the insurance company and is unified relative to the industry, namely the price discount given to the consumer by the insurance company, and the market pricing deviation degree can be used for reflecting the deviation degree of the premium discount level of the insurance company relative to the market average discount and the submission of the supervision discount. Specifically, for a certain insurance company i, the market pricing deviation C can be obtained through the following market pricing deviation actuarial modeliAnd the market pricing deviation degree actuarial model formula is as follows:
wherein, c1Is a weight coefficient, and the value range is 0 to 2, s1Is a power exponent with a value range of 0-2.8, IiThe average independent discount coefficient of all the insurance policies of the insurance company I, and the average independent discount coefficient of all the insurance policies of the vehicle insurance industry as a whole; c. C2Is a weight coefficient, and the value range is 0 to 2, s2The power index is a power index, the value range is 0-2.5, and J is the average independent discount coefficient of all insurance policies reported to a supervision organization by an insurance company i.
In the market pricing deviation degree actuarial model, each weight parameter and power exponent can be adjusted according to actual conditions, and in addition, the market pricing deviation degree can be obtained according to one or more input values in the actuarial model. The difference between the actual pricing level of each insurance company and the market and delivery supervision can be effectively measured by the index data of the market pricing deviation, so that the pricing situation of each insurance company is monitored.
In an optional implementation manner of this embodiment, the risk monitoring index data may further include a risk disturbance index of the vehicle insurance market. The risk disturbance index of the vehicle insurance market can be used for reflecting future reimbursement risk of the insurance policy and disturbance conditions of the whole market. Specifically, for a certain insurance company i, the risk disturbance index D of the vehicle insurance market can be obtained through the following vehicle insurance market risk disturbance actuarial modeliWherein, the model formula of the vehicle insurance market risk disturbance actuarial model is as follows:
wherein d is1Is a weight coefficient, the value range is 0-2.8, h1Is a power exponent with a value range of 0-1.8, KiIs the overall predicted odds for all insurance policies of insurance company i, K is the overall predicted odds for all insurance policies of the vehicle insurance industry as a whole, d2Is a weight coefficient, the value range is 0 to 2.5, h2Is a power exponent with a value range of 0-1, LiIs the insurance company i's insurance premium income, and L is the overall insurance premium income of the automobile insurance industry.
In the vehicle insurance market risk disturbance actuarial model, each weight parameter and power index can be adjusted according to actual conditions, and in addition, the vehicle insurance market risk disturbance index can be obtained according to one or more input values in the actuarial model. Through the index data of the risk disturbance index of the car insurance market, the risk management level of each insurance company can be effectively measured, and therefore whether the future claims of each insurance company are in a reasonable level or not and the disturbance degree of the whole market are effectively monitored.
In an optional implementation manner of this embodiment, the risk monitoring index data may further include a risk screening capability index. Wherein the risk screening capability index refers to insurance policy system of insurance company for different market risksThe accuracy of the premium price to which it corresponds, this index data may be used to reflect the insurance company's ability to identify and screen policy risks, i.e. whether the insurance company can offer matching premiums for policies of different risks. Specifically, the risk screening ability index can be implemented in the following manner: firstly, sequencing each vehicle insurance policy data of each insurance company according to the sequence of the predicted claims from low to high, and averagely dividing the insurance policies of each insurance company into a plurality of groups according to the sequencing result, wherein the overall claims rate of the first group of insurance policies is lowest, the overall claims rate of the last group of insurance policies is highest, and then calculating the standard deviation e of the predicted claims rate of the vehicle insurance policy data under the condition of grouping by taking the total premium income of each group as weight1Finally, the mean value e of the predicted odds of all the insurance policies of each insurance company is calculated2By standard deviation e1And mean value e2The risk screening ability index of each insurance company can be obtained according to the ratio. In the present embodiment, the number of groups may be determined according to actual conditions, for example, the vehicle insurance policy data of each insurance company is equally divided into ten groups, and the present embodiment is not limited herein. It should be noted that the smaller the risk screening ability index of an insurance company is, the higher the risk screening ability of the insurance company is represented. Because the smaller the risk screening ability index is, the insurance company can identify risks in different risk groups, and insurance cost prices with difference are made for customers with different risks, so that the difference of the overall paying rate is not great. Through the index data of the risk screening capacity index, the risk management and control level and the pricing level of each insurance company can be effectively measured, so that whether each insurance company has defects in the risk screening capacity or not can be effectively monitored, and a supervision mechanism is assisted to quickly and effectively identify the insurance company with poor risk management and control capacity.
In the above embodiment, the calculation process of the predicted odds of each vehicle insurance policy data of each insurance company, the overall predicted odds of all the policies of each insurance company, and the overall predicted odds of all the policies of the vehicle insurance industry as a whole is as follows: firstly, vehicle insurance policy data of each insurance company are input into a pre-trained predicted benefits rate actuarial prediction model one by one to obtain predicted risk cost of each vehicle insurance policy of each insurance company, then, the predicted benefits rate of each vehicle insurance policy data of each insurance company is obtained according to the ratio of the predicted risk cost of each vehicle insurance policy of each insurance company to standard benefits (i.e. benefits discounted according to NCD coefficient) of each policy after conversion of benefits factors without benefits, then, the overall predicted benefits rate of each insurance company is obtained according to the ratio of the predicted risk cost sum of all vehicle insurance policies of each insurance company to the standard benefits sum of all vehicle insurance policies of the insurance company after conversion of benefits factors without benefits, and finally, the ratio of the predicted risk cost sum of all vehicle insurance policies of the whole industry to the standard benefits sum of all vehicle insurance policies of the whole industry after conversion of benefits factors without benefits is obtained, and obtaining the overall predicted odds ratio of the automobile insurance industry.
In the above embodiment, the training method of the predicted odds ratio actuarial prediction model may specifically include the following steps: the method comprises the steps of firstly, collecting historical vehicle insurance policy data of each insurance company, cleaning and grouping the historical vehicle insurance policy data to obtain modeling factors of the historical vehicle insurance policy data, wherein the modeling factors include but are not limited to insurance areas, vehicle prices, vehicle insurance amounts and the like, then extracting claim data in the historical vehicle insurance policy data, generating actual risk cost (the risk cost is the ratio of the claim amount to the full vehicle year) of each historical vehicle insurance policy data, finally, taking the actual risk cost of each historical vehicle insurance policy data as a dependent variable, taking the modeling factors of the historical vehicle insurance policy data as an independent variable, establishing a generalized linear actuarial model by utilizing tededie distribution, and training to obtain an actuarial prediction model. In addition, the actuarial prediction model may also be obtained by training other actuarial models, and this embodiment is not limited in particular. By utilizing the actuarial prediction model, the modeling factor of any policy can be extracted and input into the model to obtain the predicted risk cost of the policy, namely the predicted claim value of the policy, and then the predicted claim rate of the policy can be obtained according to the ratio of the predicted claim value to the standard premium of the policy after the conversion of the policy by the non-claim benefit factor (namely, the premium discounted according to the NCD coefficient). The actuarial prediction model is established by collecting the real vehicle insurance policy data on the national vehicle insurance information platform, and the dividend rate of each insurance policy is predicted one by one through the reckoning prediction model, so that the accuracy and the prediction efficiency of the dividend rate prediction of the insurance company can be effectively improved.
The risk monitoring index data are obtained through a precise calculation model through precise measurement and calculation, and can truly and accurately reflect the risk control condition of each insurance company in each dimension, so that the true level of the insurance company in the aspects of service development quality, market reflection effect, market pricing deviation degree, risk control, risk screening capacity and the like can be quantitatively monitored, a supervision mechanism can conveniently predict the potential market risk of the car insurance industry in advance, and the accurate implementation of market regulation and control and supervision measures by the supervision mechanism is facilitated.
203. And obtaining the classified supervision indexes of the insurance companies and the classified risk supervision grades of the insurance companies according to the risk monitoring index data of the insurance companies.
Specifically, the computer device may integrate the risk monitoring index data of each insurance company obtained by measurement and calculation to obtain a classification supervision index of each insurance company, and then compare the classification supervision index of each insurance company with a classification supervision index threshold of each category to obtain a risk classification supervision level to which each insurance company belongs. For example, insurance companies with a categorical administration index exceeding a preset high risk threshold may be classified as high risk companies, insurance companies with a categorical administration index exceeding a preset medium risk threshold may be classified as medium risk companies, other insurance companies may be classified as low risk companies, and so forth.
In the present embodiment, for an insurance company i, its classification supervision index FiThe risk classification supervision level prediction model can be obtained by the following risk classification supervision level prediction model, wherein the model formula of the risk classification supervision level prediction model is as follows:
Fi=f1Ai+f2Bi+f3Ci+f4Di+f5Ei
wherein A isiIs a business development health index, B, of insurance company iiIs the market perception index, C, of insurance company iiIs the market pricing deviation, D, of insurance company iiIs the market risk disturbance index, E, of insurance company iiIs the risk screening ability index of insurance company i. f. of1,f2,f3,f4,f5Is a weight coefficient, f1,f2,f3,f4,f5The value ranges of the weight parameters are-2.5 to 2.8, and the weight parameters can be dynamically adjusted according to the supervision target of each supervision stage.
Further, by comparing the classification supervision indexes of the insurance companies according to the classification supervision index threshold preset by the supervision authority, the risk classification supervision levels (such as class a, class B and class C) specifically attributed to the insurance companies can be obtained. By using the classified supervision indexes and the risk classified supervision levels, the supervision mechanism can quickly track the market performance of each insurance company and discover part of objects needing important supervision, particularly, for part of insurance companies which develop malignant competition and possibly cause fluctuation of the whole market, the supervision mechanism can quickly discover and issue supervision early warning according to the object. Specifically, for insurance companies classified as class a, the computer device does not send out early warning information, so that supervision departments do not need to take supervision measures; for insurance companies classified as B-type, the computer equipment can send out moderate early warning information, and a supervision organization can supervise and inquire the B-type company after checking the moderate early warning information; for insurance companies classified as class C, the computer equipment can send out heavy early warning information, the supervision mechanism can send out supervision warning to the class C company after checking the heavy early warning information, and supervision measures such as field inspection, penalty execution, service stopping and the like can be implemented if necessary. Through the mode, the vehicle insurance risk monitoring efficiency and the vehicle insurance risk monitoring effect can be effectively improved.
In an optional implementation manner of this embodiment, each item of risk monitoring index data and classification supervision index of each insurance company may include both risk monitoring index data and classification supervision index for all vehicle types, and may also include risk monitoring index data and classification supervision index for each vehicle type. For example, the classification regulatory index for each insurance company may include a classification regulatory index for all vehicle types and a classification regulatory index for domestic vehicles. The calculation method of the risk monitoring index data or the classification supervision indexes for a certain vehicle type by each insurance company is the same as the calculation method of the risk monitoring index data or the classification supervision indexes for all vehicle types, and the calculation method of the risk monitoring index data or the classification supervision indexes for all vehicle types is only limited by the calculation method of the risk monitoring index data or the classification supervision indexes for the vehicle types, so the calculation mode of each data is not repeated herein. Further, the risk classification regulatory level to which each insurance company belongs may also include a risk classification regulatory level for all vehicle types as well as a risk classification regulatory level for each vehicle type. For example, the computer device may use the classification supervision indexes of all vehicle types as an abscissa and the classification supervision indexes of domestic vehicles as an ordinate to establish a coordinate axis, and determine the risk management and control conditions of each insurance company on all vehicle types and domestic vehicle types according to the classification supervision index conditions of each insurance company in the coordinate axis. By the method, risk classification can be accurately carried out on each insurance company, so that a supervision mechanism is assisted to prejudge the risk management and control capability of each insurance company. In addition, by analyzing the risk monitoring index data and the classification supervision indexes of various vehicle types, the risk control capability of each company on the overall vehicle insurance service and each vehicle type service can be accurately acquired, and the supervision effect is improved.
204. And outputting a risk monitoring graph of each insurance company and a risk classification monitoring graph of the car insurance industry according to the risk monitoring index data and the classification supervision indexes of each insurance company.
205. And displaying the risk monitoring graph of each insurance company and the risk classification monitoring graph of the car insurance industry.
Specifically, the computer device may output a risk monitoring map of each insurance company according to each risk monitoring index data of each insurance company, output a risk classification monitoring map of the car insurance industry according to a classification supervision index of each insurance company, and display the risk monitoring map of each insurance company and the risk classification monitoring map of the car insurance industry, so that a supervision organization can timely predict risk control conditions of each insurance company and the whole car insurance industry through the risk monitoring map and the risk classification monitoring map at any time, wherein specific forms of the risk monitoring map and the risk classification monitoring map are not limited, for example, the risk monitoring map of each insurance company may be displayed in the form of a radar map and a bar chart, and the risk classification monitoring map of the car insurance industry may be displayed in the form of a coordinate map and a bar chart. In this embodiment, the time range of the data displayed by the risk monitoring graph of each insurance company and the risk classification monitoring graph of the car insurance industry may be set according to the time range selected by the user, for example, the computer device may output and display the risk classification monitoring graph of the car insurance industry in the last quarter or the risk monitoring graph of an insurance company in the last month according to the instruction input by the user.
For example, FIG. 3 shows a risk monitoring graph for a month of an insurance company. As shown in fig. 3, the dark blocks in fig. 3 represent industry monitoring thresholds of risk monitoring index data of the car insurance industry in each dimension, and the light blocks in fig. 3 represent output values of the risk monitoring index data of an insurance company in each dimension, where the monitoring thresholds of the risk monitoring index data may be industry average values of the risk monitoring index data. In this embodiment, the risk monitoring graph of each insurance company can not only reflect the specific situation of each insurance company in the above five dimensions, but also reflect the deviation of each insurance company in each dimension relative to the overall situation of the industry, which is helpful for the supervision department to quickly track the market performance of each supervision object, and find some objects that need to be supervised in a focused manner, especially for some companies that develop malignant competition and may cause fluctuation of the overall market, and the supervision authority can issue supervision early warning accordingly. For example, it can be seen that the health index of vehicle insurance business development of an insurance company shown in fig. 3 is better than the industry development, which indicates that the vehicle insurance business of the insurance company develops faster, but the risk disturbance index and the risk screening capability index of the vehicle insurance market are higher, which indicates that the risk screening capability of the insurance company is poorer, so that it can be inferred that the insurance premium covered by the company is high-risk, and because the risk screening capability is poorer, no premium policy matching the risk is made, but a low-price policy is adopted, which can be seen from that the market pricing deviation degree is higher than the industry monitoring value. By combining the information, the insurance companies simply pursue scales, do not pay attention to risk control, carry out vicious competition in the market, and a supervision mechanism can find the problems of the insurance companies in time according to the risk monitoring graphs of the insurance companies, and can guide the insurance companies through windows so as to prevent local risk accumulation from causing market fluctuation.
By way of further example, fig. 4 illustrates a risk classification monitoring graph for the car insurance industry. As shown in fig. 4, the star position in the figure represents the average value of the classification supervision indexes of the vehicle insurance industry for all vehicle types and family vehicle types, and each circle represents the classification supervision index of one insurance company for all vehicle types and family vehicle types. It can be seen that the classification supervision indexes of the three insurance companies positioned in the dotted line circle at the upper right corner are higher, that is, the risk control level is lower, and the operation risk is easily caused. Accordingly, the computer device can classify such insurance companies into high-risk company classifications and output corresponding high-risk warning information to prompt a supervisory authority to perform key monitoring on such companies or take necessary classification supervision measures. Specifically, all insurance companies in the figure may be divided into A, B and C categories. The class A company is a company with a light color block around the asterisk and at the lower left corner in the drawing, the risk control capability of the class A company in the whole plate and household vehicle service is good, and the potential risk of paying is low in the future, so that the computer equipment cannot output warning information, and a supervision mechanism cannot take supervision measures on the class A company; the class B company is a company in a dotted line circle in the lower right corner of the drawing, the risk management and control performance of the class B company on the service plate of the home vehicle is good, but the risk management and control capability on the service of the non-home vehicle is poor, so that the whole service possibly has risks, and therefore the computer equipment can output the risk warning information of the service of the non-home vehicle to prompt a supervision mechanism to analyze the service structure of the non-home vehicle and take necessary supervision measures on the non-home vehicle; the class C company is a company in a dotted line circle at the upper right corner in the drawing, and the company has a large business risk on both the home car and the whole business plate, so the computer equipment can output high-risk warning information to prompt a supervision authority to send out a supervision letter or to order the supervision authority to perform rectification and modification, and the business of the supervision authority is suspended if necessary. It should be understood that the above examples are only for illustrating the present embodiment and are not to be construed as a limitation of the present embodiment.
In addition to the risk monitoring map of the insurance company and the risk classification monitoring map of the car insurance industry listed above, the computer device may also output other types of risk detection maps, for example, a monitoring map of mean change of each item of risk monitoring index data in a current preset period of the car insurance industry compared with a previous preset period is output, and through the monitoring map, a monitoring organization can accurately monitor the overall risk level of the car insurance industry. For example, the regulatory body can know whether the overall premium scale of the industry is accelerated steadily, whether the insurance rate continuously rises, whether the competition of the overall price in the discount aspect is good, whether the risk screening capability of the market overall has major defects, whether the future reimbursement rate of the industry overall is at a reasonable level, and the like.
According to the vehicle insurance risk monitoring method provided by the embodiment, various hidden risk dangers hidden in the vehicle insurance industry can be effectively and accurately identified by an auxiliary monitoring mechanism through one or more risk monitoring index data such as the vehicle insurance business development health index, the vehicle insurance market perception index, the market pricing deviation degree, the vehicle insurance market risk disturbance index and the risk screening capacity, so that the risk monitoring efficiency and the risk monitoring effect of the vehicle insurance industry are improved. In addition, the method comprehensively considers various factors such as market underwriting, future market risk and the like, fully reflects the real level of the insurance company in the aspects of service scale, market strategy, risk pricing capability, risk management and the like, has comprehensive and scientific monitoring dimension, improves the timeliness, objectivity and accuracy of risk monitoring in the car insurance industry, enables a supervision mechanism to develop service guidance in a targeted manner, and reduces the interference of the high-risk operation insurance company on normal market behaviors.
Further, as a specific implementation of the method shown in fig. 1 to 4, the embodiment provides a vehicle insurance risk monitoring device, as shown in fig. 5, the device includes: a data acquisition module 31, a data processing module 32 and a result output module 33.
The data acquisition module 31 can be used for acquiring the vehicle insurance policy data of each insurance company on the national vehicle insurance information platform;
the data processing module 32 is configured to generate risk monitoring index data of each insurance company based on the vehicle insurance policy data of each insurance company, where the risk monitoring index data includes one or more of a vehicle insurance business development health index, a vehicle insurance market perception index, a market pricing deviation degree, a vehicle insurance market risk disturbance index, and a risk screening ability index;
and the result output module 33 is configured to obtain the classified supervision indexes of the insurance companies and the classified risk supervision levels of the insurance companies according to the risk monitoring index data of the insurance companies.
In a specific application scenario, if the risk monitoring index data includes an automobile insurance business development health index, the data processing module 32 may be specifically configured to sequentially input automobile insurance policy data of each insurance company into a pre-trained automobile insurance business development actuarial model to obtain the automobile insurance business development health index of each insurance company, where a model formula of the automobile insurance business development actuarial model is as follows:
wherein i is the serial number of the insurance company, AiIs a business development health index of insurance company i, a1Is a weight coefficient, and the value range is 0-1.5, k1Is a power exponent with a value range of 0-2.3, XiIs the speed increase of the total amount of the charge of the sign sheet in the current preset period in the vehicle insurance policy data of insurance company i compared with the previous preset period, and X is the speed increase of the total amount of the charge of the sign sheet in the current preset period in the whole vehicle insurance policy data of the vehicle insurance industry compared with the previous preset periodIncreasing the speed; a is2Is a weight coefficient, and the value range is 0-1.5, k2Is a power exponent with a value range of 0-2, YiThe total number of the signposts in the current preset period in the vehicle insurance policy data of the insurance company i is increased compared with the speed in the previous preset period, and Y is the total number of the signposts in the current preset period in the vehicle insurance policy data of the whole vehicle insurance industry is increased compared with the speed in the previous preset period; a is3Is a weight coefficient, and the value range is 0-2, k3Is a power exponent with a value range of 0-2.6, ZiIs the procedure rate in the current preset period in the insurance company i's car insurance policy data, and Z is the procedure rate in the current preset period in the whole car insurance policy data of the car insurance industry.
In a specific application scenario, if the risk monitoring index data includes an automobile insurance market perceptibility index, the data processing module 32 may be specifically configured to sequentially input automobile insurance policy data of each insurance company into a pre-trained automobile insurance market perceptibility actuarial model to obtain the automobile insurance market perceptibility index of each insurance company, where a model formula of the automobile insurance market perceptibility actuarial model is:
wherein i is the serial number of the insurance company, BiIs the market perception index of insurance company i, b1Is a weight coefficient, with a value range of 0-2.6, t1Is a power exponent with a value range of 0 to 1.5, FiIs the ratio of the number of the business insurance policy items and the number of the compulsory insurance policy items in the vehicle insurance policy data of the insurance company i, and F is the ratio of the number of the business insurance policy items and the number of the compulsory insurance policy items in the vehicle insurance policy data of the whole vehicle insurance industry; b2Is a weight coefficient, and the value range is 0-2, t2Is a power exponent with a value range of 0-2.5, GiThe proportion of the number of the high-insurance premium policy in the vehicle insurance policy data of the insurance company i, and G is the proportion of the number of the high-insurance premium policy in the whole vehicle insurance policy data of the vehicle insurance industry; b3Is a weight coefficient, the value range is 0-1.5, t3Is a power exponent in a range of 0 to2.3,HiThe improvement proportion of the average premium income of each policy in the current preset period in the vehicle insurance policy data of the insurance company i compared with the improvement proportion in the previous preset period, and H is the improvement proportion of the average premium income of each policy in the current preset period in the overall vehicle insurance policy data of the vehicle insurance industry compared with the improvement proportion in the previous preset period.
In a specific application scenario, if the risk monitoring index data includes a market pricing deviation degree, the data processing module 32 may be specifically configured to sequentially input the vehicle insurance policy data of each insurance company into a pre-trained market pricing deviation degree actuarial model to obtain the market pricing deviation degree of each insurance company, where a model formula of the market pricing deviation degree actuarial model is:
wherein i is the serial number of the insurance company, CiIs the market pricing deviation of insurance company i, c1Is a weight coefficient, and the value range is 0 to 2, s1Is a power exponent with a value range of 0-2.8, IiThe average independent discount coefficient of all the insurance policies of the insurance company I, and the average independent discount coefficient of all the insurance policies of the vehicle insurance industry as a whole; c. C2Is a weight coefficient, and the value range is 0 to 2, s2The power index is a power index, the value range is 0-2.5, and J is the average independent discount coefficient of all insurance policies reported to a supervision organization by an insurance company i.
In a specific application scenario, if the risk monitoring index data includes an insurance market risk disturbance index, the data processing module 32 may be specifically configured to sequentially input insurance policy data of each insurance company into a pre-trained insurance market risk disturbance actuarial model to obtain the insurance market risk disturbance index of each insurance company, where a model formula of the insurance market risk disturbance actuarial model is:
wherein i is the serial number of the insurance company, DiIs the market risk disturbance index, d, of insurance company i1Is a weight coefficient, the value range is 0-2.8, h1Is a power exponent with a value range of 0-1.8, KiIs the predicted odds ratio of insurance company i, K is the predicted odds ratio of the whole vehicle insurance industry, d2Is a weight coefficient, the value range is 0 to 2.5, h2Is a power exponent with a value range of 0-1, LiIs the insurance company i's insurance premium income, and L is the overall insurance premium income of the automobile insurance industry.
In a specific application scenario, if the risk monitoring index data includes a risk screening ability index, the data processing module 32 may be specifically configured to sort each vehicle insurance policy data of each insurance company according to a sequence from low to high of predicted odds, and averagely divide the vehicle insurance policy data of each insurance company into a plurality of groups according to the number of pieces according to a sorting result; calculating the standard deviation of the predicted dividend rate of the vehicle insurance policy data after the insurance companies are grouped by taking the total premium income of each group as weight; and obtaining the risk screening capability index of each insurance company according to the standard deviation of the predicted odds of the vehicle insurance policy data after the insurance companies are grouped and the ratio of the predicted odds of each insurance company.
In a specific application scenario, the data processing module 32 may be further configured to input vehicle insurance policy data of each insurance company one by one into a pre-trained predicted odds rate actuarial prediction model, so as to obtain a predicted risk cost of each vehicle insurance policy of each insurance company; obtaining standard premium of each vehicle insurance policy of each insurance company after conversion of the claim-free benefit factor according to the basic premium of each vehicle insurance policy data of each insurance company and the claim-free benefit factor corresponding to each vehicle insurance policy data; obtaining the predicted odds ratio of each insurance company to each vehicle insurance policy data according to the ratio of the predicted risk cost of each insurance company to the standard insurance fee of each vehicle insurance policy after the conversion of the indemnity preferential treatment factor; obtaining the predicted odds ratio of each insurance company according to the ratio of the predicted risk cost sum of all the vehicle insurance policies of each insurance company to the standard insurance cost sum of all the vehicle insurance policies of each insurance company after conversion by the indemness treat factor; and obtaining the overall predicted indemnity rate of the vehicle insurance industry according to the ratio of the total predicted risk cost of all vehicle insurance policy in the overall industry to the total standard insurance cost of all vehicle insurance policy in the overall industry after conversion of the indemnity preferential treatment factor.
In a specific application scenario, as shown in fig. 6, the apparatus further includes a model training module 34, where the model training module 34 is specifically configured to collect historical vehicle insurance policy data of each insurance company, and perform cleaning and grouping on the historical vehicle insurance policy data to obtain modeling factors of the historical vehicle insurance policy data, where the modeling factors include underwriting areas, vehicle prices, and vehicle insurance amounts; extracting claim settlement data in the historical vehicle insurance policy data, and generating actual risk cost of each historical vehicle insurance policy data; and establishing a generalized linear actuarial model by using the tweedie distribution and training to obtain an actuarial prediction model by using the actual risk cost of each historical vehicle insurance policy data as a dependent variable and the modeling factor of the historical vehicle insurance policy data as an independent variable.
In a specific application scenario, the result output module 33 may be further configured to sequentially input the risk monitoring index data of each insurance company into a pre-trained risk classification supervision level prediction model to obtain a classification supervision index of each insurance company, where a model formula of the risk classification supervision level prediction model is as follows:
wherein i is the serial number of the insurance company, FiIs a Classification supervision index, A, of insurance company iiIs a business development health index, B, of insurance company iiIs the market perception index, C, of insurance company iiIs the market pricing deviation, D, of insurance company iiIs the market risk disturbance index, E, of insurance company iiIs the Risk screening Capacity index, f, of insurance company i1,f2,f3,f4,f5Is rightCoefficient of weight, f1,f2,f3,f4,f5The value ranges of (A) are all-2.5 to 2.8; and obtaining the risk classification supervision grade of each insurance company according to the classification supervision index of each insurance company and a preset classification supervision index threshold value.
In a specific application scenario, as shown in fig. 6, the apparatus further includes a picture output module 35 and a picture display module 36, where the picture output module 35 is specifically configured to output a risk monitoring graph of each insurance company and a risk classification monitoring graph of the car insurance industry according to the risk monitoring index data and the classification supervision index of each insurance company; the image display module 36 may be specifically configured to display a risk monitoring map of each insurance company and a risk classification monitoring map of the car insurance industry.
It should be noted that other corresponding descriptions of the functional units related to the vehicle insurance risk monitoring device provided in this embodiment may refer to the corresponding descriptions in fig. 1 to fig. 4, and are not described herein again.
Based on the method shown in fig. 1 to 4, correspondingly, the present embodiment further provides a storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the method for monitoring risk of vehicle insurance shown in fig. 1 to 4.
Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, and the software product to be identified may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, or the like), and include several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the method according to the implementation scenarios of the present application.
Based on the method shown in fig. 1 to 4 and the embodiment of the vehicle insurance risk monitoring apparatus shown in fig. 5 and 6, in order to achieve the above object, the embodiment further provides an entity device for vehicle insurance risk monitoring, which may specifically be a personal computer, a server, a smart phone, a tablet computer, a smart watch, or other network devices, and the entity device includes a storage medium and a processor; a storage medium for storing a computer program; a processor for executing a computer program for implementing the above-described method as shown in fig. 1 to 4.
Optionally, the entity device may further include a user interface, a network interface, a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, and the like. The user interface may include a Display screen (Display), an input unit such as a keypad (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), etc.
Those skilled in the art will appreciate that the physical device structure for monitoring the risk of vehicle insurance provided by the present embodiment does not constitute a limitation to the physical device, and may include more or less components, or combine some components, or arrange different components.
The storage medium may further include an operating system and a network communication module. The operating system is a program for managing the hardware of the above-mentioned entity device and the software resources to be identified, and supports the operation of the information processing program and other software and/or programs to be identified. The network communication module is used for realizing communication between the internal grouping backups of the storage medium and other hardware and software in the information processing entity equipment.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present application can be implemented by software plus a necessary general hardware platform, and can also be implemented by hardware. By applying the technical scheme of the application, firstly, the vehicle insurance policy data of each insurance company is collected on a national vehicle insurance information platform, then one or more risk monitoring index data of each insurance company is generated based on the vehicle insurance policy data of each insurance company, wherein the risk monitoring index data comprises a vehicle insurance business development health index, a vehicle insurance market perceptibility index, a market pricing deviation, a vehicle insurance market risk disturbance index, a risk screening capability index and the like, and finally, the classified supervision index of each insurance company and the classified supervision level of the risk of each insurance company are obtained according to the risk monitoring index data of each insurance company. Compared with the prior art, the method can obtain a plurality of risk monitoring index data by acquiring objective vehicle insurance policy data on a national vehicle insurance information platform and utilizing the acquired vehicle insurance policy data to carry out index measurement and risk prediction. The multiple risk monitoring index data can quantitatively monitor the real level of each insurance company in the vehicle insurance industry in the aspects of service development quality, market reflection effect, market pricing deviation degree, risk management and control, risk screening capacity and the like, and can also be synthesized to quantitatively evaluate the risk classification supervision levels of each insurance company, so that each insurance company is accurately divided into the risk classification supervision levels, the risk supervision efficiency and the risk supervision effect of the vehicle insurance industry are improved, a supervision mechanism can conveniently predict the potential market risk of the vehicle insurance industry in advance, and the supervision mechanism can be helped to accurately implement market regulation and supervision measures.
Those skilled in the art will appreciate that the figures are merely schematic representations of one preferred implementation scenario and that the blocks or flow diagrams in the figures are not necessarily required to practice the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario may be distributed in the devices in the implementation scenario according to the description of the implementation scenario, or may be located in one or more devices different from the present implementation scenario with corresponding changes. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above application serial numbers are for description purposes only and do not represent the superiority or inferiority of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of the present application, but the present application is not limited thereto, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present application.
Claims (13)
1. A vehicle insurance risk monitoring method, the method comprising:
collecting vehicle insurance policy data of each insurance company on a national vehicle insurance information platform;
generating risk monitoring index data of each insurance company based on the vehicle insurance policy data of each insurance company, wherein the risk monitoring index data comprise one or more of a vehicle insurance business development health index, a vehicle insurance market perception index, a market pricing deviation degree, a vehicle insurance market risk disturbance index and a risk screening capacity index;
and obtaining the classified supervision indexes of the insurance companies and the classified supervision grades of the risks of the insurance companies according to the risk monitoring index data of the insurance companies.
2. The method of claim 1, wherein the risk monitoring indicator data comprises a car insurance business development health index, and the generating the risk monitoring indicator data for each insurance company based on the car insurance policy data for each insurance company comprises:
sequentially inputting the vehicle insurance policy data of each insurance company into a pre-trained vehicle insurance business development actuarial model to obtain a vehicle insurance business development health index of each insurance company, wherein the model formula of the vehicle insurance business development actuarial model is as follows:
wherein i is the serial number of the insurance company, AiIs a business development health index of insurance company i, a1Is a weight coefficient, and the value range is 0-1.5, k1Is a power exponent with a value range of 0-2.3, XiThe speed of the total amount of the charge of the sign sheet in the current preset period in the vehicle insurance policy data of the insurance company i is increased compared with the speed in the previous preset period, and X is the speed of the total amount of the charge of the sign sheet in the current preset period in the whole vehicle insurance policy data of the vehicle insurance industry is increased compared with the speed in the previous preset period; a is2Is a weight coefficient, and the value range is 0-1.5, k2Is a power exponent with a value range of 0-2, YiThe total number of the signposts in the current preset period in the vehicle insurance policy data of the insurance company i is increased compared with the speed in the previous preset period, and Y is the total number of the signposts in the current preset period in the vehicle insurance policy data of the whole vehicle insurance industry is increased compared with the speed in the previous preset period; a is3Is a weight coefficient, and the value range is 0-2, k3Is a power exponent with a value range of 0-2.6, ZiIs the procedure rate in the current preset period in the insurance company i's car insurance policy data, and Z is the procedure rate in the current preset period in the whole car insurance policy data of the car insurance industry.
3. The method of claim 1, wherein the risk monitoring indicator data comprises a vehicle insurance market awareness index, and the generating the risk monitoring indicator data for each insurance company based on the vehicle insurance policy data for each insurance company comprises:
sequentially inputting the vehicle insurance policy data of each insurance company into a pre-trained vehicle insurance market perception degree actuarial model to obtain a vehicle insurance market perception degree index of each insurance company, wherein the model formula of the vehicle insurance market perception degree actuarial model is as follows:
wherein i is the serial number of the insurance company, BiIs the market perception index of insurance company i, b1Is a weight coefficient, with a value range of 0-2.6, t1Is a power exponent with a value range of 0 to 1.5, FiIs the ratio of the number of the business insurance policy items and the number of the compulsory insurance policy items in the vehicle insurance policy data of the insurance company i, and F is the ratio of the number of the business insurance policy items and the number of the compulsory insurance policy items in the vehicle insurance policy data of the whole vehicle insurance industry; b2Is a weight coefficient, and the value range is 0-2, t2Is a power exponent with a value range of 0-2.5, GiThe proportion of the number of the high-insurance premium policy in the vehicle insurance policy data of the insurance company i, and G is the proportion of the number of the high-insurance premium policy in the whole vehicle insurance policy data of the vehicle insurance industry; b3Is a weight coefficient, the value range is 0-1.5, t3Is a power exponent with a value range of 0-2.3, HiIs the improvement ratio of the average premium income of each policy in the current preset period in the vehicle insurance policy data of the insurance company i compared with the premium income of each policy in the previous preset period,h is the improvement ratio of the average premium income of each insurance policy in the current preset period in the overall vehicle insurance policy data of the vehicle insurance industry to the premium income of each insurance policy in the previous preset period.
4. The method of claim 1, wherein the risk monitoring indicator data comprises a market pricing deviation degree, and the generating the risk monitoring indicator data for each insurance company based on the vehicle insurance policy data for each insurance company comprises:
and sequentially inputting the vehicle insurance policy data of each insurance company into a pre-trained market pricing deviation degree actuarial model to obtain the market pricing deviation degree of each insurance company, wherein the model formula of the market pricing deviation degree actuarial model is as follows:
wherein i is the serial number of the insurance company, CiIs the market pricing deviation of insurance company i, c1Is a weight coefficient, and the value range is 0 to 2, s1Is a power exponent with a value range of 0-2.8, IiThe average independent discount coefficient of all the insurance policies of the insurance company I, and the average independent discount coefficient of all the insurance policies of the vehicle insurance industry as a whole; c. C2Is a weight coefficient, and the value range is 0 to 2, s2The power index is a power index, the value range is 0-2.5, and J is the average independent discount coefficient of all insurance policies reported to a supervision organization by an insurance company i.
5. The method of claim 1, wherein the risk monitoring indicator data comprises an automobile insurance market risk disturbance index, and the generating the risk monitoring indicator data for each insurance company based on the automobile insurance policy data for each insurance company comprises:
sequentially inputting the vehicle insurance policy data of each insurance company into a pre-trained vehicle insurance market risk disturbance actuarial model to obtain a vehicle insurance market risk disturbance index of each insurance company, wherein the model formula of the vehicle insurance market risk disturbance actuarial model is as follows:
wherein i is the serial number of the insurance company, DiIs the market risk disturbance index, d, of insurance company i1Is a weight coefficient, the value range is 0-2.8, h1Is a power exponent with a value range of 0-1.8, KiIs the predicted odds ratio of insurance company i, K is the predicted odds ratio of the whole vehicle insurance industry, d2Is a weight coefficient, the value range is 0 to 2.5, h2Is a power exponent with a value range of 0-1, LiIs the insurance company i's insurance premium income, and L is the insurance premium income for the car insurance industry as a whole.
6. The method of claim 1, wherein the risk monitoring indicator data further comprises a risk screening capability index, and the generating the risk monitoring indicator data for each insurance company based on the vehicle insurance policy data for each insurance company comprises:
sorting each vehicle insurance policy data of each insurance company according to the sequence of the predicted odds ratio from low to high, and averagely dividing the vehicle insurance policy data of each insurance company into a plurality of groups according to the number of the vehicle insurance policy data according to the sorting result;
calculating the standard deviation of the predicted dividend rate of the vehicle insurance policy data after the insurance companies are grouped by taking the total premium income of each group as weight;
and obtaining the risk screening capability index of each insurance company according to the standard deviation of the predicted odds of the vehicle insurance policy data after the insurance companies are grouped and the ratio of the predicted odds of each insurance company.
7. The method according to claim 5 or 6, wherein the method for obtaining the predicted odds of each vehicle insurance policy data of each insurance company, the predicted odds of each insurance company and the predicted odds of the whole vehicle insurance industry comprises:
inputting the vehicle insurance policy data of each insurance company into a pre-trained predicted loss rate actuarial prediction model one by one to obtain the predicted risk cost of each vehicle insurance policy of each insurance company;
obtaining standard premium of each vehicle insurance policy of each insurance company after conversion of the claim-free benefit factor according to the basic premium of each vehicle insurance policy data of each insurance company and the claim-free benefit factor corresponding to each vehicle insurance policy data;
obtaining the predicted odds ratio of each insurance company to each vehicle insurance policy data according to the ratio of the predicted risk cost of each insurance company to the standard insurance fee of each vehicle insurance policy converted by the non-reimbursement preferential treatment factor;
obtaining the predicted odds ratio of each insurance company according to the ratio of the predicted risk cost sum of all the vehicle insurance policies of each insurance company to the standard insurance cost sum of all the vehicle insurance policies of each insurance company after conversion by the indemness treat factor;
and obtaining the overall predicted indemnity rate of the vehicle insurance industry according to the ratio of the total predicted risk cost of all vehicle insurance policy of the overall industry to the total standard insurance cost of all vehicle insurance policy of the overall industry after conversion of the indemnity preferential treatment factor.
8. The method of claim 7, wherein the training of the predictive odds actuarial predictive model comprises:
collecting historical vehicle insurance policy data of each insurance company, and cleaning and grouping the historical vehicle insurance policy data to obtain modeling factors of the historical vehicle insurance policy data, wherein the modeling factors comprise underwriting areas, vehicle prices and vehicle insurance amounts;
extracting claim settlement data in the historical vehicle insurance policy data, and generating actual risk cost of each historical vehicle insurance policy data;
and establishing a generalized linear actuarial model by using the tweedie distribution with the actual risk cost of each historical vehicle insurance policy data as a dependent variable and the modeling factor of the historical vehicle insurance policy data as an independent variable, and training to obtain the actuarial prediction model.
9. The method according to claim 1, wherein the obtaining the classification supervision index of each insurance company and the risk classification supervision level of each insurance company according to the risk monitoring index data of each insurance company comprises:
and sequentially inputting the risk monitoring index data of each insurance company into a pre-trained risk classification supervision grade prediction model to obtain a classification supervision index of each insurance company, wherein the model formula of the risk classification supervision grade prediction model is as follows:
Fi=f1Ai+f2Bi+f3Ci+f4Di+f5Ei
wherein i is the serial number of the insurance company, FiIs a Classification supervision index, A, of insurance company iiIs a business development health index, B, of insurance company iiIs the market perception index, C, of insurance company iiIs the market pricing deviation, D, of insurance company iiIs the market risk disturbance index, E, of insurance company iiIs the Risk screening Capacity index, f, of insurance company i1,f2,f3,f4,f5Is a weight coefficient, f1,f2,f3,f4,f5The value ranges of (A) are all-2.5 to 2.8;
and obtaining the risk classification supervision grade of each insurance company according to the classification supervision index of each insurance company and a preset classification supervision index threshold value.
10. The method of claim 1, further comprising:
outputting a risk monitoring graph of each insurance company and a risk classification monitoring graph of the car insurance industry according to the risk monitoring index data and the classification supervision indexes of each insurance company;
and displaying the risk monitoring graph of each insurance company and the risk classification monitoring graph of the car insurance industry.
11. A vehicle insurance risk monitoring apparatus, the apparatus comprising:
the data acquisition module is used for acquiring the vehicle insurance policy data of each insurance company on a national vehicle insurance information platform;
the data processing module is used for generating risk monitoring index data of each insurance company based on the vehicle insurance policy data of each insurance company, wherein the risk monitoring index data comprise one or more of a vehicle insurance business development health index, a vehicle insurance market perceptibility index, a market pricing deviation degree, a vehicle insurance market risk disturbance index and a risk screening capacity index;
and the result output module is used for obtaining the classified supervision indexes of the insurance companies and the classified supervision grades of the risks of the insurance companies according to the risk monitoring index data of the insurance companies.
12. A storage medium having a computer program stored thereon, the computer program, when being executed by a processor, realizing the steps of the method of any one of claims 1 to 10.
13. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 10 when executed by the processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110162944.9A CN112801528A (en) | 2021-02-05 | 2021-02-05 | Vehicle insurance risk monitoring method and device, storage medium and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110162944.9A CN112801528A (en) | 2021-02-05 | 2021-02-05 | Vehicle insurance risk monitoring method and device, storage medium and computer equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112801528A true CN112801528A (en) | 2021-05-14 |
Family
ID=75814515
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110162944.9A Pending CN112801528A (en) | 2021-02-05 | 2021-02-05 | Vehicle insurance risk monitoring method and device, storage medium and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112801528A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113919959A (en) * | 2021-09-04 | 2022-01-11 | 北京优全智汇信息技术有限公司 | Comprehensive insurance risk supervision system and supervision method |
CN118172176A (en) * | 2024-05-14 | 2024-06-11 | 青岛场外市场清算中心有限公司 | Financial risk analysis method and system based on blockchain |
-
2021
- 2021-02-05 CN CN202110162944.9A patent/CN112801528A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113919959A (en) * | 2021-09-04 | 2022-01-11 | 北京优全智汇信息技术有限公司 | Comprehensive insurance risk supervision system and supervision method |
CN118172176A (en) * | 2024-05-14 | 2024-06-11 | 青岛场外市场清算中心有限公司 | Financial risk analysis method and system based on blockchain |
CN118172176B (en) * | 2024-05-14 | 2024-07-23 | 青岛场外市场清算中心有限公司 | Financial risk analysis method and system based on blockchain |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Emel et al. | A credit scoring approach for the commercial banking sector | |
Wang et al. | Regression analysis: modeling & forecasting | |
US8554589B2 (en) | Insurance product, rating system and method | |
Engelmann et al. | The Basel II risk parameters: estimation, validation, and stress testing | |
US7664690B2 (en) | Insurance claim management | |
CN102609881B (en) | System and method for the frequency that forecast is associated with following loss | |
US8812331B2 (en) | Insurance product, rating and credit enhancement system and method for insuring project savings | |
WO2002049260A2 (en) | Commercial insurance scoring system and method | |
CN111553563A (en) | Method and device for determining enterprise fraud risk | |
CN112801393A (en) | Transfer factor-based vehicle insurance risk prediction method and device and storage medium | |
CN112801528A (en) | Vehicle insurance risk monitoring method and device, storage medium and computer equipment | |
Grize | Applications of statistics in the field of general insurance: An overview | |
CN116934131A (en) | Enterprise operation condition assessment method, device and equipment | |
CN113554517A (en) | Risk assessment method and device for truck insurance market and storage medium | |
CN114707733A (en) | Risk indicator prediction method and device, electronic equipment and storage medium | |
TWI585709B (en) | Financial management diagnosis method and system thereof | |
Cheng et al. | Using fuzzy analytical hierarchy process for multi-criteria evaluation model of high-yield bonds investment | |
Kim et al. | Shareholder wealth effects of audit data analytics announcements | |
US11854087B1 (en) | Systems and methods for water loss mitigation messaging | |
KR102566466B1 (en) | Alternative Credit Rating System for Evaluating Personal Credit | |
US20240113936A1 (en) | Method and system for artificial intelligence-based acceleration of zero-touch processing | |
Partyn et al. | Use of the method of the analysis of benefits and costs for decision making on the development of enterprise financial relations with groups of economic influence (stakeholders) | |
CN117314626A (en) | Enterprise wind control method, device, equipment and medium based on internal and external double evaluation models | |
Tarigan et al. | The Influence of Liquidity, Profitability and Capital Intensity Toward Tax Avoidance in Mining Companies Listed on the Indonesia Stock Exchange | |
CN114723570A (en) | Agricultural risk monitoring method and device, storage medium and computer equipment |
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 |