Insurance risk capital assessment method, device and equipment and storage medium
By dynamically generating insurance risk capital assessment data through stochastic simulation and the Copula method, the problem of inaccurate assessment of insurance risk in existing technologies is solved, enabling refined and dynamic capital assessment and providing a more accurate basis for capital planning.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-12
- Publication Date
- 2026-03-10
AI Technical Summary
Existing financial capital assessment methods cannot achieve accurate and dynamic capital assessment, especially in insurance risk assessment, where they cannot dynamically reflect the differences in reinsurance arrangements and risk characteristics, resulting in capital calculation results that lack individual adaptability and foresight.
By acquiring historical underwriting and claims data, using stochastic simulation methods to determine loss simulation data and reserve data, and combining the Copula method to characterize the correlation between premium risk and reserve risk, future risk scenarios are dynamically generated to accurately capture potential losses and reserve requirements under extreme stress events.
It achieves refined and dynamic insurance risk capital assessment, which can accurately identify the risk contribution of different business units, providing a refined data foundation for differentiated pricing, underwriting policy formulation and reinsurance arrangements, and making the capital assessment results more scientific and reliable.
Smart Images
Figure CN121639366A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for assessing insurance risk capital. Background Technology
[0002] In the economic capital management system, economic capital refers to the amount of capital an insurance company needs to hold to withstand unexpected losses at a certain confidence level. Among these, insurance risk economic capital is one of the most important components of an insurance company's economic capital. Its accurate measurement is crucial for improving capital utilization efficiency and optimizing risk management. As the international insurance industry increasingly strengthens risk-oriented solvency management, insurance companies' internal assessment needs for economic capital are constantly increasing. This is especially true in the property insurance sector, where the scientific measurement of insurance risk, as a core component of economic capital, is particularly critical.
[0003] Currently, domestic insurance companies primarily calculate their minimum capital requirements based on the China Risk Oriented Solvency System (C-ROSS, hereinafter referred to as "C-ROSS" for ease of description). This system employs an industry-wide unified factor method, using the company's actual retained business as a basis to calculate the minimum capital requirements for each insurance category through preset risk factors. While this framework offers certain advantages in terms of regulatory compliance, it is essentially a results-oriented, standardized approach with the following significant limitations: 1. The risk exposure calculation of Solvency II relies on the current status of the company's retained business and cannot dynamically reflect process management variables such as reinsurance arrangements and reinsurance costs. Therefore, it is difficult to support the internal management needs of insurance companies in business planning, underwriting strategies, captive insurance and reinsurance decisions.
[0004] 2. The risk factors used in this system are based on historical industry data, and the calculation granularity can only reach the level of insurance category. It cannot fully consider the differences between different insurance companies in terms of business structure, risk characteristics, and reinsurance arrangements (especially complex structures such as excess-of-loss reinsurance), resulting in a lack of individual adaptability and foresight in the capital calculation results.
[0005] Therefore, how to achieve a refined and dynamic assessment of insurance risks has become an urgent technical problem to be solved. Summary of the Invention
[0006] This application provides an insurance risk capital assessment method to address the problem that existing financial capital assessment methods cannot achieve accurate and dynamic capital assessment.
[0007] This application also provides an insurance risk capital assessment device to address the problem that existing financial capital assessment methods cannot achieve accurate and dynamic capital assessment.
[0008] This application also provides an insurance risk capital assessment device to address the problem that existing financial capital assessment methods cannot achieve accurate and dynamic capital assessment.
[0009] This application also provides a computer-readable storage medium to address the problem that existing financial capital assessment methods cannot achieve accurate and dynamic capital assessment.
[0010] The embodiments of this application adopt the following technical solutions: An insurance risk capital assessment method includes: determining simulated loss data for each business portfolio using a random simulation method based on acquired historical underwriting and claims data; determining maximum loss data within a preset regression period based on the simulated loss data, and determining first risk data based on the maximum loss data; determining maximum reserve data within the preset regression period using a random simulation method based on acquired claims progress data, and determining second risk data based on the maximum reserve data; determining a correlation parameter between the first risk data and the second risk data; and determining insurance risk capital assessment data based on the first risk data, the second risk data, and the correlation parameter.
[0011] An insurance risk capital assessment device includes: a loss simulation unit, used to determine loss simulation data corresponding to each business portfolio through a random simulation method based on acquired historical underwriting and claims data; a first risk determination unit, used to determine the maximum loss data within a preset regression period based on the loss simulation data, and to determine first risk data based on the maximum loss data; a second risk determination unit, used to determine the maximum reserve data within the preset regression period through a random simulation method based on acquired claims progress data, and to determine second risk data based on the maximum reserve data; a correlation parameter determination unit, used to determine the correlation parameters between the first risk data and the second risk data; and a risk assessment unit, used to determine insurance risk capital assessment data based on the first risk data, the second risk data, and the correlation parameters.
[0012] An insurance risk capital assessment device, comprising: The processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the following operations: determining, based on acquired historical underwriting and claims data, loss simulation data corresponding to each business portfolio using a random simulation method; determining, based on the loss simulation data, maximum loss data within a preset regression period, and determining first risk data based on the maximum loss data; determining, based on acquired claims progress data, maximum reserve data within the preset regression period using a random simulation method, and determining second risk data based on the maximum reserve data; determining a correlation parameter between the first risk data and the second risk data; and determining insurance risk capital assessment data based on the first risk data, the second risk data, and the correlation parameter.
[0013] A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the following operations: determining simulated loss data for each business combination based on acquired historical underwriting and claims data using a random simulation method; determining maximum loss data within a preset regression period based on the simulated loss data, and determining first risk data based on the maximum loss data; determining maximum reserve data within the preset regression period based on acquired claims progress data using a random simulation method, and determining second risk data based on the maximum reserve data; determining a correlation parameter between the first risk data and the second risk data; and determining insurance risk capital assessment data based on the first risk data, the second risk data, and the correlation parameter.
[0014] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: Using the insurance risk capital assessment method provided in this application, when an insurance risk capital assessment is required, historical underwriting and claims data can be obtained through the business system. Based on the historical underwriting and claims data, loss simulation data corresponding to each business portfolio can be determined through a random simulation method. Based on the loss simulation data, the maximum loss data within a preset regression period can be determined. Based on the maximum loss data, the first risk data can be determined. Based on the obtained claims progress data, the maximum reserve data within the preset regression period can be determined through a random simulation method. Based on the maximum reserve data, the second risk data can be determined. The correlation parameters between the first risk data and the second risk data can be determined. Based on the first risk data, the second risk data, and the correlation parameters, the insurance risk capital assessment data can be determined. The insurance risk capital assessment method provided in this application has several advantages. First, by processing historical underwriting and claims data and claims progress data using a random simulation method, it can dynamically generate a large number of future risk scenarios. This allows for the accurate capture of potential losses and reserve requirements under extreme stress events, overcoming the shortcomings of traditional factor methods that rely on uniform factors for all companies and cannot predict tail risks based on actual company risk differences. This makes the capital assessment results more scientific and reliable. Second, it enables refined risk management at the business portfolio level, accurately identifying the risk contributions of different business units and providing a refined data foundation for differentiated pricing, underwriting policy formulation, business structure optimization, and reinsurance arrangements. Finally, the Copula method characterizes the correlation between premium risk and reserve risk, ensuring that the final aggregated insurance risk capital assessment data more accurately and comprehensively reflects the company's overall risk profile, providing a more accurate basis for capital planning. Attached Figure Description
[0015] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A schematic diagram illustrating the specific process of an insurance risk capital assessment method provided in this application embodiment; Figure 2 A schematic diagram of the specific structure of an insurance risk capital assessment device provided in this application embodiment; Figure 3 This is a schematic diagram of the specific structure of an insurance risk capital assessment device provided in an embodiment of this application. Detailed Implementation
[0016] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0017] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.
[0018] This application provides an insurance risk capital assessment method to address the problem that existing financial capital assessment methods cannot achieve accurate and dynamic capital assessment.
[0019] The execution entity of the insurance risk capital assessment method provided in this application embodiment may be, but is not limited to, at least one of banking business servers, insurance business servers, and financial business servers; in addition, the execution entity of the method may also be the system or application (APP) itself running on these servers.
[0020] For ease of description, the following text uses the insurance risk capital assessment system as the implementing entity of this method, and takes the use of the insurance risk capital assessment system to assess insurance business as an example to introduce the implementation method of this method. It should be understood that using the insurance risk capital assessment system as the implementing entity of this method is only an illustrative example and should not be construed as a limitation of this method.
[0021] The schematic diagram illustrating the specific implementation process of the insurance risk capital assessment method provided in this application is as follows: Figure 1 As shown, the main steps include the following: Step 11: Based on the obtained historical underwriting and claims data, determine the loss simulation data corresponding to each business combination through random simulation method; In this embodiment of the application, historical underwriting and claims data includes, but is not limited to: historical policy information of the insurance company, claims records, claims progress (ladder diagram data), reinsurance arrangement records, etc., while business portfolio can refer to business portfolios further divided according to the company's business lines (such as motor insurance, property insurance, liability insurance, marine insurance, accident insurance, and health insurance) and risk characteristics.
[0022] In one implementation, step 11 is specifically implemented as follows: Sub-step 1101: Obtain historical underwriting and claims data by accessing the backend database of the underwriting system; Sub-step 1102 involves preprocessing the acquired historical underwriting and claims data, cleaning and organizing the historical underwriting and claims data to ensure the continuity and integrity of the historical underwriting and claims data; Sub-step 1103: Based on the claims records in the historical underwriting and claims data, classify historical losses into the following three types: Type 1, routine loss, generally refers to losses that occur frequently but are relatively small in amount; Type 2, significant loss, generally refers to losses that occur infrequently but involve large sums of money, such as losses from large corporate property insurance policies; Type 3, accident loss, generally refers to losses that occur infrequently but cause multiple risk assets to be damaged at the same time, resulting in a huge cumulative loss. For example, multiple risk assets may be damaged simultaneously due to natural disasters or major accidents.
[0023] Sub-step 1104: Based on historical underwriting and claims data, determine the simulated loss amount data corresponding to each business combination using the Monte Carlo simulation method; In this embodiment of the application, the simulated loss amount data is used to represent the loss situation corresponding to different loss types.
[0024] In this embodiment of the application, before determining the simulated loss amount data corresponding to each business portfolio using the Monte Carlo simulation method, historical underwriting and claims data can be used to fit the probability distribution of the above three types of losses for each business portfolio using methods such as maximum likelihood estimation, thereby determining the loss distribution of different loss types. For example, conventional losses may be fitted with a log-normal distribution, major losses may be fitted with a Pareto distribution, and accident losses may be modeled using extreme value theory (such as the POT model) or a catastrophe model.
[0025] After modeling the loss distributions for the three loss types mentioned above, the insurance risk capital assessment system can perform a large number of Monte Carlo random samplings (e.g., 100,000 times) on the three loss distributions for each business portfolio, generating the regular loss value, major loss value, and accident loss value for that business portfolio in each simulation. Adding these three together yields the total loss value for that business portfolio in a single simulation. After 100,000 simulations, the simulated loss amount data for that business portfolio is obtained—a set containing 100,000 total loss values.
[0026] Sub-step 1105: Based on historical underwriting and claims data, determine the loss correlation simulation data between each business portfolio using the Copula join function and the Common Shock method; In this embodiment of the application, for the above three types of loss, the insurance risk capital assessment system can determine the loss correlation simulation data according to the following method, including: 1. Regarding conventional losses: Insurance risk capital assessment systems can use copulas to evaluate the correlation between regular losses of different business portfolios. Specifically, firstly, historical data on regular losses of each business portfolio can be transformed into a uniform distribution through probability integral transformation. Then, a suitable copula function (such as the Gaussian Copula) is selected and its parameters are estimated to capture its nonlinear, asymmetric correlation structure. Finally, in a Monte Carlo simulation, correlated random numbers of regular losses are generated based on the fitted copula model, yielding the first correlation data.
[0027] 2. Regarding significant losses and accident losses: Insurance risk capital assessment systems can employ the Common Shock method for evaluation. For example, simulating a catastrophic event (such as a typhoon) would trigger significant losses or accident losses across multiple business portfolios (such as home insurance, auto insurance, and corporate insurance) within the affected area, based on preset intensity parameters and impact range. By simulating common events of varying intensities and frequencies, highly correlated data on significant losses and accident losses can be dynamically generated, yielding secondary correlation data.
[0028] Based on the first and second correlation data, simulated loss correlation data between each business portfolio was determined.
[0029] Step 12: Based on the loss simulation data obtained by executing Step 11, determine the maximum loss data within the preset regression period, and based on the maximum loss data, determine the first risk data; In this embodiment of the application, the insurance risk capital assessment system can simulate and generate loss amount simulation data and loss correlation simulation data by performing the above step 11, and then add them together to obtain the company's overall total loss simulation data. The overall total loss simulation data is then sorted. Assuming that the preset regression period is 200 years, the loss value corresponding to the top 99.5 percentile is determined as the maximum loss data within the preset regression period. Thus, the insurance risk capital assessment system can determine the maximum loss data that occurs once every 200 years (Loss_VaR99.5%).
[0030] After determining the maximum loss data (Loss_VaR 99.5%) through the above scheme, the insurance risk capital assessment system can determine the first risk data through the following methods: determining the maximum predicted policy data within the preset regression period based on historical underwriting and claims data; determining the cost data within the preset regression period and the premium data corresponding to the maximum predicted policy data based on the maximum predicted policy data; and determining the first risk data based on the maximum loss data, all cost data, and the premium data.
[0031] Specifically, in the embodiments of this application, the insurance risk capital assessment system can determine the first risk data (i.e., premium risk economic capital, which will be referred to as parameter A below for ease of description) according to the following formula 1: A= Loss_VaR99.5%+COST-PREMIUM [1] The above formula [1] indicates that in extreme scenarios, the sum of claims payouts (Loss_VaR99.5%) and expenses (cost data) may exceed premium income, and the difference is the risk gap that needs to be covered by capital.
[0032] Step 13: Based on the obtained claims progress data, determine the maximum reserve data within the preset regression period using a random simulation method, and determine the second risk data based on the maximum reserve data; In the insurance industry, claims progress data is typically stored in the underwriting database in the form of a claims progress triangle (chain ladder table). In this embodiment, the insurance risk capital assessment system, for each business portfolio, can determine the correlation between reserve volatility and progress period based on the progress triangle in the acquired claims progress data. It uses a random simulation method to simulate the development path of outstanding claims liability reserves. Through a large number of simulations (e.g., 100,000), the simulated reserve results for each business portfolio are obtained. The simulated reserve results of all business portfolios are summed, and the values of the top 99.5 percentiles of the 100,000 simulation results are used as the maximum reserve data (Reserve_VaR99.5%).
[0033] After determining the maximum reserve data (Reserve_VaR99.5%) through the above scheme, the insurance risk capital assessment system can determine the second risk data through the following methods: obtaining the actual reserve data; and determining the second risk data based on the actual reserve data and the maximum reserve data.
[0034] Specifically, the insurance risk capital assessment system can obtain the actual reserve data actually set aside on the company's current financial statements as the actual reserve data (referred to as parameter T below for ease of description), and determine the second risk data (reserve risk economic capital, referred to as parameter B below for ease of description) according to the following formula 2: B = Reserve_VaR99.5% - T [2] The above formula [2] indicates that in extreme scenarios, the final total amount of outstanding claims may far exceed the current reserves, and the difference is the risk of insufficient reserves, which needs to be covered by capital.
[0035] Step 14: Determine the correlation parameters between the first risk data and the second risk data; It is important to note that premium risk and reserve risk are not entirely independent in insurance risk. For example, a major disaster event (such as an earthquake) may lead to a surge in claims for new policies (premium risk) or exacerbate the losses of existing claims (reserve risk).
[0036] Therefore, in this embodiment of the application, referring to international regulatory practices and industry practices, for the same business portfolio under the same business line, the correlation parameter (correlation coefficient) between the first risk data and the second risk data can be set to 0.5. Premium risks and reserve risks between different business lines or different portfolios are considered independent of each other.
[0037] Step 15: Determine the insurance risk capital assessment data based on the first risk data, the second risk data, and related parameters.
[0038] In one implementation, step 15 may include: determining, based on the first risk data and the second risk data, the maximum value of the sum of the first risk data and the second risk data within the preset regression period using a random simulation method; and determining insurance risk capital assessment data based on the maximum value, the cost data, the premium data, and the actual reserve data.
[0039] In this embodiment of the application, the insurance risk capital assessment system can specifically determine the insurance risk capital assessment data in the following ways: Specifically, the insurance risk capital assessment system can directly add the total loss simulation data and the maximum reserve data for each random simulation performed in steps 12 and 13 above to obtain the simulation results of 100,000 "total loss simulation data + maximum reserve data". The results are sorted and the top 99.5 percentile is taken to obtain the maximum value of the sum of the first risk data and the second risk data under the extreme scenario (Insurance_VaR99.5%). Then, the insurance risk capital assessment system can determine the insurance risk capital assessment data according to the following formula [4]: C= Insurance_VaR99.5% + COST-PREMIUM -T [4] Furthermore, it should be noted that, in order to assess capital utilization efficiency, in this embodiment of the application, the insurance risk capital assessment system can also determine the rate of return on capital based on the insurance risk capital assessment data determined by performing the above steps. In one implementation, the method provided in this embodiment of the application may include: determining average loss data and average reserve data based on simulated loss amount data and simulated reserve data; determining average underwriting profit data based on cost data, premium data, actual reserve data, average loss data, and average reserve data; and determining the rate of return on capital based on the average underwriting profit data and the insurance risk capital assessment data.
[0040] Specifically, the insurance risk capital assessment system can calculate average loss data and average reserve data based on simulated loss data and simulated reserve data.
[0041] The average underwriting profit data is determined according to the following formula [5]: Average underwriting profit = PREMIUM + T - COST - Average loss data - Average reserve data [5] Furthermore, the insurance risk capital assessment system can determine the rate of return on capital (RoEC) according to the following formula [6]: RoEC = Average underwriting profit / C[6] Additionally, it should be noted that in this embodiment of the application, the above method can also be used to conduct insurance risk capital assessment for the reinsurance retention business. Specifically, when determining the first risk data (i.e., premium risk economic capital), the insurance risk capital assessment system can divide all reinsurance business of the company into ceded losses and retained losses, and divide the corresponding loss data, premium data, cost data, and actual reserve data into retained loss data, retained premium data, post-reinsurance premium data, post-reinsurance cost data, and post-reinsurance actual reserve data.
[0042] Using the insurance risk capital assessment method provided in this application, when an insurance risk capital assessment is required, historical underwriting and claims data can be obtained through the business system. Based on the historical underwriting and claims data, loss simulation data corresponding to each business portfolio can be determined through a random simulation method. Based on the loss simulation data, the maximum loss data within a preset regression period can be determined. Based on the maximum loss data, the first risk data can be determined. Based on the obtained claims progress data, the maximum reserve data within the preset regression period can be determined through a random simulation method. Based on the maximum reserve data, the second risk data can be determined. The correlation parameters between the first risk data and the second risk data can be determined. Based on the first risk data, the second risk data, and the correlation parameters, the insurance risk capital assessment data can be determined. The insurance risk capital assessment method provided in this application has several advantages. First, by processing historical underwriting and claims data and claims progress data using a random simulation method, it can dynamically generate a large number of future risk scenarios. This allows for the accurate capture of potential losses and reserve requirements under extreme stress events, overcoming the shortcomings of traditional factor methods that rely on historical averages and cannot effectively predict tail risks. This makes the capital assessment results more scientific and reliable. Second, it enables refined risk management at the business portfolio level, accurately identifying the risk contributions of different business units and providing a refined data foundation for differentiated pricing, underwriting policy formulation, business structure optimization, and reinsurance arrangements. Finally, by introducing and determining the correlation parameters between premium risk and reserve risk, it effectively characterizes the correlation between different risk sources, solving the problem of traditional segmented calculations ignoring risk linkage effects. This makes the final aggregated insurance risk capital assessment data more realistic and comprehensive in reflecting the company's overall risk profile, providing a more accurate basis for capital planning.
[0043] In one embodiment, this application also provides an insurance risk capital assessment device to address the problem that existing financial capital assessment methods cannot achieve accurate and dynamic capital assessment. A schematic diagram of the specific structure of this insurance risk capital assessment device is shown below. Figure 2 As shown, it includes: a loss simulation unit 21, a first risk determination unit 22, a second risk determination unit 23, a correlation parameter determination unit 24, and a risk assessment unit 25.
[0044] Among them, the loss simulation unit 21 is used to determine the loss simulation data corresponding to each business combination through random simulation method based on the acquired historical underwriting and claims data; The first risk determination unit 22 is used to determine the maximum loss data within a preset regression period based on the loss simulation data, and to determine the first risk data based on the maximum loss data. The second risk determination unit 23 is used to determine the maximum reserve data within a preset regression period based on the acquired claims progress data through a random simulation method, and to determine the second risk data based on the maximum reserve data. The correlation parameter determination unit 24 is used to determine the correlation parameter between the first risk data and the second risk data; Risk assessment unit 25 is used to determine insurance risk capital assessment data based on the first risk data, the second risk data, and the associated parameters.
[0045] In one implementation, the loss simulation data includes: loss amount simulation data representing the loss situation corresponding to different loss types and loss correlation simulation data representing the correlation between different types of losses. Then, the loss simulation unit 21 is specifically used to: determine the loss amount simulation data corresponding to each business combination based on historical underwriting and claims data using the Monte Carlo simulation method; and determine the loss correlation simulation data between each business combination based on the historical underwriting and claims data using the Copula connection function.
[0046] In one implementation, the loss simulation unit 21 is specifically used to: determine the loss distribution of each business combination for different loss types based on the historical underwriting and claims data; and determine the simulated loss amount data corresponding to each business combination using the Monte Carlo simulation method based on the loss distribution.
[0047] In one implementation, the loss types include: routine losses, major losses, and accident losses; then the loss simulation unit 21 is specifically used to: determine the first correlation data of routine losses between each business portfolio according to the connection function Copula; determine the second correlation data of major losses and accident losses between each business portfolio according to the Common Shock method; and determine the loss correlation simulation data between each business portfolio according to the first correlation data and the second correlation data.
[0048] In one implementation, the first risk determination unit 22 is specifically used to: determine the maximum predicted policy data within the preset regression period based on the historical underwriting and claims data; determine the cost data within the preset regression period and the premium data corresponding to the maximum predicted policy data based on the maximum predicted policy data; and determine the first risk data based on the maximum loss data, all cost data, and the premium data.
[0049] In one implementation, the second risk determination unit 23 is specifically used for: acquiring actual reserve data; and determining second risk data based on the actual reserve data and the maximum reserve data.
[0050] In one implementation, the risk assessment unit 25 is specifically configured to: determine, based on the first risk data and the second risk data, the maximum value of the sum of the first risk data and the second risk data within the preset regression period using a random simulation method; and determine insurance risk capital assessment data based on the maximum value, the cost data, the premium data, and the actual reserve data.
[0051] In one embodiment, the system further includes a capital return determination unit, specifically configured to: determine average loss data and average reserve data based on the historical underwriting and claims data; determine average underwriting profit data based on the cost data, the premium data, the actual reserve data, the average loss data, and the average reserve data; and determine the capital return rate based on the average underwriting profit data and the insurance risk capital assessment data.
[0052] Using the insurance risk capital assessment device provided in this application embodiment, when an insurance risk capital assessment is required, historical underwriting and claims data can be obtained through the business system. Based on the historical underwriting and claims data, loss simulation data corresponding to each business combination can be determined through a random simulation method. Based on the loss simulation data, the maximum loss data within a preset regression period can be determined. Based on the maximum loss data, the first risk data can be determined. Based on the obtained claims progress data, the maximum reserve data within the preset regression period can be determined through a random simulation method. Based on the maximum reserve data, the second risk data can be determined. The correlation parameters between the first risk data and the second risk data can be determined. Based on the first risk data, the second risk data, and the correlation parameters, the insurance risk capital assessment data can be determined. The insurance risk capital assessment method provided in this application has several advantages. First, by processing historical underwriting and claims data and claims progress data using a random simulation method, it can dynamically generate a large number of future risk scenarios. This allows for the accurate capture of potential losses and reserve requirements under extreme stress events, overcoming the shortcomings of traditional factor methods that rely on historical averages and cannot effectively predict tail risks. This makes the capital assessment results more scientific and reliable. Second, it enables refined risk management at the business portfolio level, accurately identifying the risk contributions of different business units and providing a refined data foundation for differentiated pricing, underwriting policy formulation, business structure optimization, and reinsurance arrangements. Finally, by introducing and determining the correlation parameters between premium risk and reserve risk, it effectively characterizes the correlation between different risk sources, solving the problem of traditional segmented calculations ignoring risk linkage effects. This makes the final aggregated insurance risk capital assessment data more realistic and comprehensive in reflecting the company's overall risk profile, providing a more accurate basis for capital planning.
[0053] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 3 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.
[0054] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.
[0055] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.
[0056] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming an insurance risk capital assessment device at the logical level. The processor executes the program stored in memory and specifically performs the following operations: Based on the acquired historical underwriting and claims data, loss simulation data corresponding to each business combination is determined through random simulation. Based on the loss simulation data, the maximum loss data within a preset regression period is determined, and based on the maximum loss data, the first risk data is determined. Based on the acquired claims progress data, the maximum reserve data within the preset regression period is determined through random simulation, and based on the maximum reserve data, the second risk data is determined. The correlation parameters between the first risk data and the second risk data are determined. Based on the first risk data, the second risk data, and the correlation parameters, insurance risk capital assessment data is determined.
[0057] The above is as stated in this application. Figure 3The method for performing insurance risk capital assessment using an electronic device disclosed in the illustrated embodiments can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.
[0058] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.
[0059] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by a portable electronic device including multiple applications, enable the portable electronic device to perform... Figure 1 The method of the illustrated embodiment is specifically used to perform the following operations: Based on the acquired historical underwriting and claims data, loss simulation data corresponding to each business combination is determined through random simulation. Based on the loss simulation data, the maximum loss data within a preset regression period is determined, and based on the maximum loss data, the first risk data is determined. Based on the acquired claims progress data, the maximum reserve data within the preset regression period is determined through random simulation, and based on the maximum reserve data, the second risk data is determined. The correlation parameters between the first risk data and the second risk data are determined. Based on the first risk data, the second risk data, and the correlation parameters, insurance risk capital assessment data is determined.
[0060] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0061] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0062] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0063] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0064] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0065] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0066] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0067] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0068] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0069] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method of assessing insurance risk capital, characterized by, The method comprises the following steps: According to the obtained historical underwriting and claim data, the loss simulation data corresponding to each business portfolio is determined by a random simulation method; According to the loss simulation data, the maximum loss data in the preset regression period is determined, and the first risk data is determined according to the maximum loss data; According to the obtained claim progress data, the maximum reserve data in the preset regression period is determined by a random simulation method, and the second risk data is determined according to the maximum reserve data; Determine the correlation coefficient between the first risk data and the second risk data; According to the first risk data, the second risk data and the correlation coefficient, the insurance risk capital evaluation data is determined.
2. The method of claim 1, wherein, The loss simulation data comprises loss amount simulation data for representing loss conditions corresponding to different loss types and loss correlation simulation data for representing correlations between different types of losses. Then, the loss simulation data corresponding to each business portfolio is determined by a random simulation method, specifically comprising: According to the historical underwriting and claim data, the loss amount simulation data corresponding to each business portfolio is determined by a Monte Carlo simulation method; According to the historical underwriting and claim data, the loss correlation simulation data between each business portfolio is determined by a joint function Copula and a common event Common Shock method.
3. The method of claim 2, wherein, According to the historical underwriting and claim data, the loss amount simulation data corresponding to each business portfolio is determined by a Monte Carlo simulation method, specifically comprising: According to the historical underwriting and claim data, the loss distribution of each business portfolio for different loss types is determined; According to the loss distribution, the loss amount simulation data corresponding to each business portfolio is determined by a Monte Carlo simulation method.
4. The method of claim 2, wherein, The loss types include routine loss, major loss and accident loss. Then, the loss correlation simulation data between each business portfolio is determined by a joint function Copula and a Common Shock method, specifically comprising: According to the joint function Copula, the first correlation data of routine loss between each business portfolio is determined; According to the Common Shock method, the second correlation data of major loss and accident loss between each business portfolio is determined; According to the first correlation data and the second correlation data, the loss correlation simulation data between each business portfolio is determined.
5. The method of claim 1, wherein, According to the maximum reserve data, the second risk data is determined, specifically comprising: Obtain actual reserve data; According to the obtained claim progress data, the corresponding relationship between the volatility of the reserve of each business portfolio and the progress period is determined; According to the corresponding relationship, the reserve simulation data corresponding to each business portfolio is simulated by a Monte Carlo simulation method. According to the reserve simulation data, the maximum reserve data in the preset regression period is determined; According to the maximum reserve data and the actual reserve data, the second risk data is determined.
6. The method of claim 5, wherein, According to the first risk data, the second risk data and the correlation parameter, the insurance risk capital evaluation data is determined, specifically comprising: determining, according to the first risk data and the second risk data, a maximum value of a sum of the first risk data and the second risk data in the preset return period according to a stochastic simulation method; determining, according to the maximum value, the cost data, the premium data and the actual reserve data, insurance risk capital evaluation data.
7. The method of claim 1, wherein, Further comprising: determining, according to the loss amount simulation data and the reserve simulation data, average loss data and average reserve data; determining, according to the cost data, the premium data, the actual reserve data, the average loss data and the average reserve data, average underwriting profit data; determining, according to the average underwriting profit data and the insurance risk capital evaluation data, a capital return rate.
8. An insurance risk capital assessment apparatus, characterized by, Comprising: a loss simulation unit configured to determine, according to obtained historical underwriting and claim data, loss simulation data corresponding to each business portfolio through a stochastic simulation method; a first risk determination unit configured to determine maximum loss data in a preset return period according to the loss simulation data, and determine first risk data according to the maximum loss data; a second risk determination unit configured to determine, according to obtained claim progress data, maximum reserve data in a preset return period through a stochastic simulation method, and determine second risk data according to the maximum reserve data; a correlation parameter determination unit configured to determine a correlation parameter between the first risk data and the second risk data; a risk evaluation unit configured to determine, according to the first risk data, the second risk data and the correlation parameter, insurance risk capital evaluation data.
9. An insurance risk capital evaluation device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the method of any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is enabled to perform the method of any one of claims 1 to 7.