Risk stress testing method and device, storage medium and electronic equipment

Abstract

This invention provides a risk stress testing method, apparatus, storage medium, and electronic device. The method includes: responding to a risk stress test command, determining the risk event to be tested and its scenario information; determining the data type of the risk event; the data type is either continuous or discrete; if the data type of the risk event is continuous, acquiring the corresponding measurement model; the measurement model is established based on historical risk data and historical scenario information of the risk event; inputting the scenario information into the measurement model to obtain the output result of the measurement model; determining the occurrence frequency of the risk event and the single-event loss value of the risk event based on the output result; and determining the stress test result of the risk event based on the occurrence frequency and single-event loss value of the risk event. This method can accurately obtain stress test results.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a risk stress testing method and device, a storage medium and an electronic equipment. BACKGROUND

[0002] At present, financial institutions usually assess the adverse effects of some possible scenarios through stress testing, which is beneficial to the risk analysis and prediction of financial institutions. However, the existing stress analysis method often uses a simple historical simulation method, that is, the quantile of historical loss data is used as the loss value, which cannot accurately obtain the stress test result. SUMMARY

[0003] The technical problem to be solved by the present application is to provide a risk stress testing method which can accurately obtain the stress test result.

[0004] The present application also provides a risk stress testing device to ensure the implementation and application of the above method in practice.

[0005] A risk stress testing method, comprising:

[0006] In response to a risk stress testing instruction, determining a risk event to be tested and scenario information of the risk event;

[0007] Determining the data type of the risk event; the data type is one of continuous type and discrete type;

[0008] In the case where the data type of the risk event is continuous type, obtaining a measurement model corresponding to the risk event; the measurement model is established based on historical risk data and historical scenario information of the risk event;

[0009] Inputting the scenario information into the measurement model to obtain an output result of the measurement model;

[0010] Determining the occurrence frequency of the risk event according to the output result, and determining the single event loss value of the risk event;

[0011] Determining the stress test result of the risk event according to the occurrence frequency of the risk event and the single event loss value.

[0012] The above method, optionally, the process of establishing the measurement model based on the historical risk data and the historical scenario information of the risk event, comprises:

[0013] Obtaining historical risk data, historical scenario information and set model parameters in a plurality of historical periods of the risk event; the historical risk data at least includes the historical occurrence frequency of the risk event;

[0014] According to historical risk data, historical scenario information and the model parameters in each historical period, a measurement model is established.

[0015] The method can further include:

[0016] A test period of the risk event is determined.

[0017] An event occurrence frequency of the risk event in a previous period of the test period is obtained.

[0018] According to the event occurrence frequency of the previous period and a frequency increase rate represented by the output result, the occurrence frequency of the risk event in the test period is determined.

[0019] The method can further include:

[0020] In a case where a data type of the risk event is discrete, a loss quantile is determined according to the scenario information, a loss value of the risk event is calculated according to the loss quantile, and the loss value of the risk event is taken as the stress test result of the risk event.

[0021] The method can further include:

[0022] The stress test result of the risk event is output.

[0023] A risk stress test device includes:

[0024] A first determination unit is configured to determine a risk event to be tested and scenario information of the risk event in response to a risk stress test instruction.

[0025] A second determination unit is configured to determine a data type of the risk event; the data type is one of continuous type and discrete type.

[0026] An acquisition unit is configured to, in a case where the data type of the risk event is continuous, acquire a measurement model corresponding to the risk event; the measurement model is established based on historical risk data and historical scenario information of the risk event.

[0027] An execution unit is configured to input the scenario information into the measurement model to obtain an output result of the measurement model.

[0028] A third determination unit is configured to determine an occurrence frequency of the risk event according to the output result and determine a single-event loss value of the risk event.

[0029] A fourth determining unit is configured to determine a stress test result of the risk event according to the occurrence frequency of the risk event and the single-event loss value.

[0030] The device described above, optionally, the acquisition unit comprises:

[0031] A first acquisition sub-unit is configured to acquire historical risk data, historical scenario information and set model parameters in a plurality of historical time periods of the risk event; the historical risk data at least comprises historical occurrence frequency of the risk event;

[0032] An execution sub-unit is configured to establish a measurement model according to the historical risk data, historical scenario information and the model parameters in each of the historical time periods.

[0033] The device described above, optionally, the third determining unit comprises:

[0034] A first determining sub-unit is configured to determine a test time period of the risk event;

[0035] A second acquisition sub-unit is configured to acquire event occurrence frequency of the risk event in a previous time period of the test time period;

[0036] A second determining sub-unit is configured to determine occurrence frequency of the risk event in the test time period according to the event occurrence frequency of the previous time period and the frequency increase rate represented by the output result.

[0037] A storage medium comprises a storage instruction, wherein when the instruction is executed, the device where the storage medium is located performs the risk stress test method as described above.

[0038] An electronic device comprises a memory and one or more instructions, wherein the one or more instructions are stored in the memory and are configured to be executed by one or more processors to perform the risk stress test method as described above.

[0039] Based on the above, the method, device, storage medium and electronic equipment provided by the embodiment of the application, the method comprises: in response to a risk stress test instruction, determining a risk event to be tested and scenario information of the risk event; determining a data type of the risk event; the data type is one of a continuous type and a discrete type; in a case where the data type of the risk event is the continuous type, acquiring a measurement model corresponding to the risk event; the measurement model is established based on historical risk data and historical scenario information of the risk event; inputting the scenario information into the measurement model to obtain an output result of the measurement model; determining an occurrence frequency of the risk event according to the output result, and determining a single event loss value of the risk event; and determining a stress test result of the risk event according to the occurrence frequency of the risk event and the single event loss value. By applying the method provided by the embodiment of the application, the stress test result can be accurately determined in combination with the measurement model and the scenario information. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0041] Figure 1 The method flow chart of the risk stress test method provided by the present application;

[0042] Figure 2 The flow chart of the process of creating a software product template provided by the present application;

[0043] Figure 3 The flow chart of the process of displaying a data entry page corresponding to a software product field of a configuration instruction provided by the present application;

[0044] Figure 4 The structural schematic diagram of the risk stress test device provided by the present application;

[0045] Figure 5 The structural schematic diagram of the electronic equipment provided by the present application;

[0046] Figure 6 The example diagram of the stress test process provided by the present application. DETAILED DESCRIPTION

[0047] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments of the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0048] In the present application, the term "comprising" or "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment. Without more limitation, the element defined by the sentence "including a…" does not exclude the presence of other identical elements in the process, method, article or equipment including the element.

[0049] The embodiment of the present application provides a risk stress test method, which can be applied to an electronic device, and a method flowchart of the method is as shown in Figure 1 The embodiment of the present application provides a risk stress test method, which can be applied to an electronic device, and a method flowchart of the method is as shown in

[0050] S101: In response to a risk stress test instruction, determining a risk event to be tested and scenario information of the risk event.

[0051] In the present embodiment, the risk stress test instruction can be an instruction sent by a device establishing a communication connection with the electronic device, can be an instruction triggered by the user clicking a preset key or virtual control, and can also be an instruction automatically triggered by some application program in the running process.

[0052] Optionally, the risk stress test instruction can be used to instruct to perform stress test, and the risk event to be tested can be various operation risk events in the financial field, for example, can be external fraud risk events, customer operation risk events, product risk events and business activity operation risk events, internal fraud risk events, physical asset damage risk events, business interruption risk events, technical system paralysis risk events, workplace safety risk events, employment system risk events, transaction risk events, process management risk events and the like.

[0053] Optionally, the scenario information of the risk event can include gross domestic product, unemployment rate, gross domestic product growth rate and the like macroeconomic data.

[0054] S102: Determining a data type of the risk event; the data type is one of continuous type and discrete type.

[0055] In this embodiment, a preset configuration file can be queried to determine the data type of the risk event, and the data types of various risk events are recorded in the configuration file.

[0056] S103: In a case where the data type of the risk event is continuous, a measurement model corresponding to the risk event is acquired; the measurement model is established based on historical risk data and historical scenario information of the risk event.

[0057] In this embodiment, the measurement model can be an autoregressive moving average ARMAX model; the measurement model can be used to process the scenario information of the risk event to obtain an output result.

[0058] Optionally, the historical risk data can include the occurrence frequency of the risk event in a continuous historical time period; and the historical scenario information can include scenario information in the continuous historical time period.

[0059] S104: The scenario information is input into the measurement model to obtain an output result of the measurement model.

[0060] In this embodiment, the output result can be the occurrence frequency growth rate of the risk event.

[0061] S105: The occurrence frequency of the risk event is determined according to the output result, and a single event loss value of the risk event is determined.

[0062] In this embodiment, the occurrence frequency of the risk event in the current time period can be calculated according to the occurrence frequency growth rate of the risk event, and the single event loss value can represent the loss degree after each occurrence of the risk event.

[0063] The single event loss value can be calculated according to the total loss value in a preset time period and the event occurrence frequency in the preset time period.

[0064] S106: A stress test result of the risk event is determined according to the occurrence frequency of the risk event and the single event loss value.

[0065] In this embodiment, the stress test result can represent the loss degree caused by the risk event in the test period.

[0066] The method provided in the embodiments of the present application can accurately determine the stress test result by combining the measurement model and the scenario information.

[0067] In an embodiment provided by the present application, based on the above-described implementation process, specifically, the process of establishing the measurement model based on the historical risk data and the historical scenario information of the risk event, as shown in Figure 2 , includes:

[0068] S201: Obtain historical risk data, historical scenario information and set model parameters in a plurality of historical periods of the risk event; the historical risk data at least includes historical occurrence frequency of the risk event.

[0069] In the embodiment, the model parameters can include white noise sequence, parameter term coefficient and lag order, etc.

[0070] S202: Establish a measurement model according to the historical risk data, historical scenario information and the model parameters in each of the historical periods.

[0071] In the embodiment, the measurement model can be expressed as follows:

[0072] EXF t = β0+ β1EXF t-1 + β2EXF t-2 + … + β P EXF t-P + ε t + α1ε t-1

[0073] + α2ε t-2 + … + α q ε t-q + γ1G t-k + γ2INCOME t-s

[0074] + γ3UEM t-u

[0075] Wherein, EXF t is the risk event occurrence frequency growth rate of the t period, EXF t-p is the index value of the lag p period, ε t is the white noise sequence, β, α and γ are coefficients, G is GDP growth rate, INCOME is the disposable income growth rate of urban residents, UEM is the unemployment rate. In the model, p, q, k, s, u are all lag orders, wherein, p, q are determined by the truncation number of partial autocorrelation function and autocorrelation function, k, s, u are determined by the sign and significance level of the coefficient γ, and the selected lag order satisfies the preset condition.

[0076] In an embodiment provided by the application, based on the above-mentioned implementation process, specifically, the determination of the occurrence frequency of the risk event according to the output result, as shown in the following formula, includes: Figure 3

[0077] S301: Determine the test period of the risk event.

[0078] ​In the embodiment, the risk stress test instruction can be parsed to obtain instruction information of the risk stress test instruction, and a test period of a risk event can be obtained from the instruction information. The length of the test period can be one week, one month, one quarter, one year, etc.

[0079] S302: Obtain an event occurrence frequency of the risk event in a previous period of the test period.

[0080] S303: Determine an occurrence frequency of the risk event in the test period according to the event occurrence frequency of the previous period and the frequency increase rate represented by the output result.

[0081] In the embodiment, the manner of determining the occurrence frequency of the risk event in the test period can be represented as: P t t-1 (1+EXF t ), where P t is the occurrence frequency of the risk event in the test period t, P t-1 is the event occurrence frequency of the previous period of the test period, and EXF t is the risk event occurrence frequency increase rate of the test period t.

[0082] In an embodiment provided by the application, based on the above-described implementation process, specifically, the method further includes:

[0083] In a case where the data type of the risk event is a discrete type, a loss quantile is determined according to the scenario information, a loss value of the risk event is calculated according to the loss quantile, and the loss value of the risk event is taken as the stress test result of the risk event.

[0084] In the embodiment, the scenario GDP increase rate in the scenario information can be obtained first, and a quantile point of the scenario GDP increase rate in a historical period is determined, that is, a percentage of a period in which the GDP increase rate in the historical risk data is higher than the scenario GDP increase rate. Then, the historical loss value of the risk event is adjusted by the operating income of the financial institution. The adjustment manner is as follows:

[0085] The adjusted loss value of the nth period = the loss value before adjustment of the nth period ×

[0086] (the operating income of the financial institution in the test period / the operating income of the financial institution in the nth period).

[0087] Optionally, the loss value of the risk event is calculated by the adjusted loss value and the quantile point, and the loss value of the risk event is taken as the stress test result of the risk event.

[0088] ​In one embodiment of the present invention, based on the above implementation process, specifically, after determining the stress test result of the risk event according to the frequency of occurrence of the risk event and the single event loss value, the method further includes:

[0089] The output displays the stress test results for the aforementioned risk event.

[0090] In this embodiment, the stress test results of risk events can be output and displayed on a preset display interface.

[0091] In some embodiments, the risk test stress results can also be sent to a preset user terminal or system, so that the system can perform preset business operations based on the risk test stress results to reduce the loss value.

[0092] and Figure 1 Corresponding to the method described above, embodiments of the present invention also provide a risk stress testing device for testing... Figure 1 The specific implementation of the method, the risk stress testing device provided in this embodiment of the invention, can be applied to electronic devices, and its structural schematic diagram is shown below. Figure 4 As shown, it specifically includes:

[0093] The first determining unit 401 is used to determine the risk event to be tested and the scenario information of the risk event in response to the risk stress test command;

[0094] The second determining unit 402 is used to determine the data type of the risk event; the data type is one of continuous type and discrete type;

[0095] The acquisition unit 403 is used to acquire the measurement model corresponding to the risk event when the data type of the risk event is continuous; the measurement model is established based on the historical risk data and historical scenario information of the risk event.

[0096] Execution unit 404 is used to input the scenario information into the measurement model and obtain the output result of the measurement model;

[0097] The third determining unit 405 is used to determine the frequency of occurrence of the risk event based on the output result, and to determine the single event loss value of the risk event.

[0098] The fourth determining unit 406 is used to determine the stress test result of the risk event based on the frequency of occurrence of the risk event and the single event loss value.

[0099] In one embodiment of the present invention, based on the above-described solution, optionally, the acquisition unit 403 includes:

[0100] The first acquisition subunit is used to acquire historical risk data, historical scenario information, and set model parameters for the risk event over multiple consecutive historical time periods; the historical risk data includes at least the historical frequency of the risk event.

[0101] The execution subunit is used to establish a measurement model based on historical risk data, historical scenario information and model parameters for each of the historical periods.

[0102] In one embodiment of the present invention, based on the above-described solution, optionally, the third determining unit 405 includes:

[0103] The first determining subunit is used to determine the test period for the risk event;

[0104] The second acquisition subunit is used to acquire the frequency of occurrence of the risk event in the period preceding the test period;

[0105] The second determining subunit is used to determine the frequency of the risk event during the test period based on the frequency of the event in the previous period and the frequency growth rate represented by the output result.

[0106] In one embodiment of the present invention, based on the above-described solution, optionally, it further includes:

[0107] The fifth determining unit is used to determine the loss quantile based on the scenario information when the data type of the risk event is discrete, calculate the loss value of the risk event based on the loss quantile, and use the loss value of the risk event as the stress test result of the risk event.

[0108] In one embodiment of the present invention, based on the above-described solution, optionally, it further includes:

[0109] The output unit is used to output and display the stress test results of the risk event.

[0110] The specific principles and execution processes of each unit and module in the risk stress testing device disclosed in the above embodiments of the present invention are the same as those of the risk stress testing method disclosed in the above embodiments of the present invention. Please refer to the corresponding parts of the risk stress testing method provided in the above embodiments of the present invention, and they will not be repeated here.

[0111] This invention also provides a storage medium that includes stored instructions, wherein the execution of the instructions controls the device containing the storage medium to perform the aforementioned risk stress test method.

[0112] This invention also provides an electronic device, the structural schematic of which is shown below. Figure 5As shown, it specifically includes a memory 501 and one or more instructions 502, wherein one or more instructions 502 are stored in the memory 501 and configured to be executed by one or more processors 503 to perform the following operations:

[0113] In response to a risk stress test command, determine the risk event to be tested and the scenario information of the risk event;

[0114] Determine the data type of the risk event; the data type is either continuous or discrete.

[0115] If the data type of the risk event is continuous, obtain the corresponding econometric model for the risk event; the econometric model is established based on the historical risk data and historical scenario information of the risk event.

[0116] The scenario information is input into the measurement model to obtain the output result of the measurement model;

[0117] The frequency of occurrence of the risk event is determined based on the output results, and the single event loss value of the risk event is determined.

[0118] The stress test results of the risk event are determined based on the frequency of occurrence of the risk event and the loss value of a single event.

[0119] See Figure 6 This is an example diagram of a pressure testing process provided by an embodiment of the present invention, which specifically includes the following steps:

[0120] (A) Data cleaning and indicator determination.

[0121] This invention is based on historical operational risk loss data, including the frequency and loss value of seven types of risk events. First, the data format for modeling is determined. This invention uses time series data, and according to statistical theory and practical experience, at least five years of data are required for modeling. Subsequently, based on the data quality of the seven types of risk events, testing methods for each type of risk are determined, including econometric modeling and historical simulation methods with macro-scenario adjustments. The modeling data requirements and indicator examples are shown in Table 1.

[0122]

[0123] The econometric model method in this invention mainly adopts the ARMAX model. To ensure the stationarity of variables, it is necessary to modify the form of some indicators to meet the modeling requirements.

[0124] 1. Frequency of risk events. In practice, it is generally necessary to convert the frequency of risk events into year-on-year or cumulative year-on-year growth rates to examine the impact of macroeconomic changes.

[0125] 2. Macroeconomic Indicators. All aggregate indicators require formatting changes. For example, GDP and urban residents' disposable income need to have their year-on-year or cumulative year-on-year growth rates calculated. The unemployment rate uses its own value. Details are as follows:

[0126]

[0127]

[0128] For the cumulative year-on-year growth rate, the year-end growth rate is the same as the annual growth rate.

[0129] (B) Establish a model.

[0130] Based on historical data of various operational risk events, this invention categorizes them into risk events using econometric models and risk events using historical simulations with macro-scenario adjustments.

[0131] 1. Risk events using econometric models.

[0132] Generally, external fraud, and operational risks related to customers, products, and business activities are closely related to the macroeconomy, and historical data is relatively continuous, making econometric models suitable. For example, during periods of economic downturn, commercial banks face an increase in the number of external frauds and a rise in risks related to customers, products, and business activities. Therefore, the frequency of these risk events can be modeled against GDP, unemployment rates, and other indicators. The ARMAX model is typically chosen as the econometric modeling approach.

[0133] Econometric models can be built using statistical econometric software such as SAS, EViews, and Matlab. Once the model is built, a macroeconomic scenario is input, and the frequency of risk events can be predicted. Finally, the loss value is calculated, assuming that the loss value per event is consistent with the base period. The formula is as follows:

[0134] Event loss value = frequency of event occurrence × loss value per event in the base period.

[0135] The base period single event loss value can be determined based on the base period annual loss value of this type of event and the base period annual frequency of this type of event. Specifically, the base period annual loss value of this type of event can be the quotient of the base period annual loss value of this type of event and the base period annual frequency of this type of event.

[0136] 2. Risk events using historical simulation methods with macro-scenario adjustments.

[0137] Historical data for some operational risk events is highly discrete, making it difficult to establish econometric models with macroeconomic indicators. These risk events generally include: internal fraud, employment policies and workplace safety, damage to physical assets, business interruption and IT system failures, and execution, delivery, and process management issues. Therefore, a macro-scenario-adjusted historical simulation method is employed to fully utilize macro-scenario information and characterize the potential losses from these risk events under specific scenarios. The specific method is as follows:

[0138] First, select a core macroeconomic indicator, typically GDP growth. Determine the percentile of GDP growth in historical years, i.e., the percentage of years in which historical GDP growth exceeded the scenario's GDP growth. Then, adjust the historical loss value data for the event using commercial bank operating income. Finally, calculate the risk loss value using the adjusted loss value and the determined percentile.

[0139] (C) Conduct stress tests.

[0140] Operational risk stress testing is generally part of the overall bank stress testing, and the macro-level scenario of the overall stress test can be used directly. By substituting the macro-level scenario into the aforementioned econometric model or by using historical simulation methods adjusted for the macro-level scenario, the loss values ​​for all seven types of operational risk events can be obtained.

[0141] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0142] Finally, it should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0143] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing this invention, the functions of each unit can be implemented in one or more software and / or hardware components.

[0144] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0145] The above provides a detailed description of the risk stress testing method provided by the present invention. Specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A risk stress testing method, characterized in that, include: In response to a risk stress test instruction, the risk event to be tested and the scenario information of the risk event are determined, including gross domestic product, unemployment rate, and gross domestic product growth rate. Determine the data type of the risk event; The data type is either a continuous type or a discrete type; If the data type of the risk event is continuous, obtain the corresponding econometric model for the risk event; The econometric model is established based on historical risk data and historical scenario information of the risk event, and the output of the econometric model is the growth rate of the occurrence frequency of the risk event; The scenario information is input into the measurement model to obtain the output result of the measurement model; The frequency of occurrence of the risk event is determined based on the output results, and the single event loss value of the risk event is determined. The stress test results of the risk event are determined based on the frequency of occurrence of the risk event and the loss value of a single event; The process of establishing the econometric model based on historical risk data and historical scenario information of the risk events includes: The system acquires historical risk data, historical scenario information, and set model parameters for the risk event over multiple consecutive historical time periods. The historical risk data includes at least the historical frequency of the risk event, and the historical scenario information includes scenario information over consecutive historical time periods. Based on historical risk data, historical scenario information, and model parameters for each historical period, a measurement model is established. This measurement model is used to process scenario information of risk events to obtain output results.

2. The method according to claim 1, characterized in that, Determining the frequency of occurrence of the risk event based on the output results includes: Determine the testing period for the aforementioned risk events; Obtain the frequency of occurrence of the risk event in the period preceding the test period; The frequency of the risk event during the test period is determined based on the frequency of the event in the previous period and the frequency growth rate represented by the output results.

3. The method according to claim 1, characterized in that, Also includes: When the data type of the risk event is discrete, the loss quantile is determined based on the scenario information, the loss value of the risk event is calculated based on the loss quantile, and the loss value of the risk event is used as the stress test result of the risk event.

4. The method according to claim 1, characterized in that, After determining the stress test result of the risk event based on the frequency of occurrence of the risk event and the loss value of a single event, the method further includes: The output displays the stress test results for the aforementioned risk event.

5. A risk and stress testing device, characterized in that, include: The first determining unit is configured to, in response to a risk stress test instruction, determine the risk event to be tested and the scenario information of the risk event, wherein the scenario information includes gross domestic product, unemployment rate and gross domestic product growth rate; The second determining unit is used to determine the data type of the risk event; The data type is either a continuous type or a discrete type; The acquisition unit is used to acquire the measurement model corresponding to the risk event when the data type of the risk event is continuous. The econometric model is established based on historical risk data and historical scenario information of the risk event, and the output of the econometric model is the growth rate of the occurrence frequency of the risk event; An execution unit is used to input the scenario information into the measurement model and obtain the output result of the measurement model; The third determining unit is used to determine the frequency of occurrence of the risk event based on the output result, and to determine the single event loss value of the risk event; The fourth determining unit is used to determine the stress test result of the risk event based on the frequency of occurrence of the risk event and the loss value of a single event; The acquisition unit includes: The first acquisition subunit is used to acquire historical risk data, historical scenario information, and set model parameters for the risk event over multiple consecutive historical time periods; the historical risk data includes at least the historical frequency of the risk event, and the historical scenario information includes scenario information over consecutive historical time periods; The execution subunit is used to establish a measurement model based on historical risk data, historical scenario information and model parameters for each historical period. The measurement model is used to process the scenario information of risk events to obtain output results.

6. The apparatus according to claim 5, characterized in that, The third determining unit includes: The first determining subunit is used to determine the test period for the risk event; The second acquisition subunit is used to acquire the frequency of occurrence of the risk event in the period preceding the test period; The second determining subunit is used to determine the frequency of the risk event during the test period based on the frequency of the event in the previous period and the frequency growth rate represented by the output result.

7. A storage medium, characterized in that, The storage medium includes storage instructions, wherein, when the instructions are executed, the device containing the storage medium is controlled to perform the risk stress test method as described in any one of claims 1 to 4.

8. An electronic device, characterized in that, It includes a memory, and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described in any one of claims 1 to 4.

Images