Economic scene quality evaluation method and device, equipment and storage medium

Abstract

The invention relates to the technical field of data processing, in particular to an economic scene quality evaluation method and device, equipment and a storage medium, and the method comprises the steps: processing an economic scene historical sample based on a preset scene generation model to obtain a scene sample, and obtaining a simulation sample based on the scene sample; obtaining first statistical comparison information based on the economic scene historical sample and the simulation sample, wherein the first statistical comparison information comprises a first probability density comparison result, a first cumulative probability density comparison result and a first quantile comparison result; establishing a first statistic group based on the economic scene historical sample, and establishing a second statistic group based on the simulation sample; and obtaining first statistical magnitude difference information based on the first statistical magnitude group and the second statistical magnitude group. The method is convenient for determining the quality condition of the economic scene output by the economic scene generator.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an economic scenario quality assessment method, device, equipment and storage medium. Background Art

[0002] When predicting future fluctuations in asset prices, economic scenario generators are often used for prediction; economic scenario generators are simulation methods that build models based on specific historical data from financial markets and generate time series paths for target assets based on complex stochastic models, and can further be used to estimate asset values.

[0003] The output result of the economic scenario generator is also the economic scenario. Since economic scenario generation often relies on the selection of a specific model, the economic scenario samples generated by it have quality defects, such as the inability to meet actual production needs. Therefore, it is necessary to conduct a quality assessment of the economic scenarios output by the economic scenario generator to determine the quality of the economic scenarios. Summary of the invention

[0004] In order to facilitate determination of the quality of economic scenarios output by an economic scenario generator, the present application provides an economic scenario quality assessment method, apparatus, device and storage medium.

[0005] In a first aspect, the present application provides an economic scenario quality assessment method, comprising:

[0006] Processing economic scenario historical samples based on a preset scenario generation model to obtain scenario samples, and obtaining simulation samples based on the scenario samples;

[0007] Obtaining first statistical comparison information based on the economic scenario historical sample and the simulated sample, the first statistical comparison information including a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result;

[0008] Establishing a first statistical group based on the economic scenario historical samples, and establishing a second statistical group based on the simulated samples;

[0009] First statistical difference information is obtained based on the first statistical group and the second statistical group.

[0010] In a second aspect, the present application provides an economic scenario quality assessment device, comprising:

[0011] A sample generation module, used to process economic scenario historical samples based on a preset scenario generation model to obtain scenario samples, and to obtain simulation samples based on the scenario samples;

[0012] A statistical comparison information generation module, configured to obtain first statistical comparison information based on the economic scenario historical sample and the simulation sample, wherein the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result;

[0013] A statistics group establishment module, used to establish a first statistics group based on the economic scenario historical samples, and to establish a second statistics group based on the simulation samples;

[0014] The statistic difference information generating module is used to obtain first statistic difference information based on the first statistic group and the second statistic group.

[0015] In a third aspect, the present application provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method when executing the computer program.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the above method when executed by a processor.

[0017] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0018] The above-mentioned economic scenario quality assessment method, device, equipment and storage medium obtain scenario samples by processing economic scenario historical samples based on a preset scenario generation model, and obtain simulation samples based on the scenario samples; obtain first statistical comparison information based on the economic scenario historical samples and the simulation samples, and the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result and a first quantile comparison result; establish a first statistical group based on the economic scenario historical samples, and establish a second statistical group based on the simulation samples; obtain first statistical difference information based on the first statistical group and the second statistical group. Through the above implementation, the first statistical comparison information can be obtained by processing the economic scenario historical samples and simulation samples, and the first statistical difference information can also be obtained by processing the first statistical group and the second statistical group. The economic scenario historical samples output by the economic scenario generator can be evaluated for quality through the first statistical comparison information and the first statistical difference information, thereby determining the quality of the economic scenario.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flow chart of an economic scenario quality assessment method provided in an embodiment of the present application;

[0022] Figure 2 A schematic diagram of a scenario sample provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result provided in an embodiment of the present application;

[0024] Figure 4 This is a schematic diagram of the structure of an economic scenario quality assessment device provided in an embodiment of the present application;

[0025] Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0026] Figure 6 This is a diagram of the internal structure of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present disclosure more clear, the present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure and are not used to limit the present disclosure.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of this article and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this article described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0029] In this article, the term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the related objects before and after are in an "or" relationship.

[0030] Embodiment 1

[0031] Figure 1 A flow chart of an economic scenario quality assessment method provided in Example 1 of this application, refer to Figure 1 The method may be performed by a device for performing the method, and the device may be implemented by software and / or hardware. The method includes:

[0032] S110, processing economic scenario historical samples based on a preset scenario generation model to obtain scenario samples, and obtaining simulation samples based on the scenario samples.

[0033] The economic scenario historical sample is the sample data sampled from the given asset price historical data at a certain sampling frequency f, and the economic scenario historical sample is denoted as Ω(f); the scenario generation model is used to process the economic scenario historical sample and output the processing result, which is also the scenario sample, and the model parameter of the scenario generation model is denoted as θ, the scenario generation model is denoted as M, and the scenario sample is denoted as x f , where x f =(x 1，m ,x 2，m ,……,x t，m ,……,x N，m ), t=1,2,……,N;m=1,2,……,M;It should be noted that t is the time point of the time series, there are N time points in total, m is the simulation path of the mth asset price historical data, each time point t corresponds to M simulation paths, so x f is an N*M matrix, x f like Figure 2 As shown; x f is a sample point x that changes over time t , m An ordered set of x f Take out sample points x in random order t , m And construct a new set, so that the simulated sample Ω can be obtained x (f),Ω x (f) = {x t，m :x t，m ∈x f ,t=1,2,…,N; m=1,2,…,M}.

[0034] Specifically, the economic scenario historical sample Ω(f) sampled from the given asset price historical data at a certain frequency f is input into the preset scenario generation model M for processing, thereby obtaining the scenario sample x f ; Further, from the scenario sample x f Take out all sample points x in random order t，m And form a new set to obtain the simulated sample Ω x (f).

[0035] S120. Obtain first statistical comparison information based on the economic scenario historical samples and the simulation samples, wherein the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result.

[0036] Among them, by statistically analyzing the economic scenario historical sample Ω(f), the probability density, cumulative probability density and quantile related thereto can be obtained. In this embodiment, the quantile is specifically the quartile, and in other embodiments, it is not specifically limited. By analyzing the simulated sample Ω x (f) statistics can be used to obtain the probability density, cumulative probability density and quantile related to it; the first probability density comparison result is the economic scenario historical sample Ω(f) and the simulation sample Ω x The absolute value of the difference in the probability density of (f), the first cumulative probability density comparison result is the economic scenario historical sample Ω(f) and the simulated sample Ω x The absolute value of the difference in the cumulative probability density of (f), the first quantile comparison result is the economic scenario historical sample Ω(f) and the simulated sample Ω x (f) The absolute value of the difference in quantiles; the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result and a first quantile comparison result.

[0037] Specifically, the economic scenario historical sample Ω(f) is statistically processed to obtain the corresponding probability density, cumulative probability density and quantile. Similarly, the simulation sample Ω x (f) Perform statistical processing to obtain the corresponding probability density, cumulative probability density and quantile; further, calculate the economic scenario historical sample Ω(f) and the simulation sample Ω x The absolute value of the difference in the probability density of (f) is used to obtain the first probability density comparison result, and the economic scenario historical sample Ω(f) and the simulated sample Ω are calculated. x The absolute value of the difference in the cumulative probability density of (f) is used to obtain the first cumulative probability density comparison result, and the economic scenario historical sample Ω(f) and the simulated sample Ω x The difference of the quantiles of (f) is used to obtain the first quantile comparison result.

[0038] S130: Establish a first statistical group based on the economic scenario historical samples, and establish a second statistical group based on the simulation samples.

[0039] The first statistical group includes the mean μ, variance σ corresponding to the economic scenario historical sample Ω(f) 2 , skewness Skew, and kurtosis Kurt; the second statistical group includes the simulated sample Ω x (f) The corresponding mean μ and variance σ 2 , skewness Skew, and kurtosis Kurt.

[0040] Specifically, calculate the mean μ and variance σ corresponding to the economic scenario historical sample Ω(f) 2 , skew, and kurtosis Kurt to obtain the first statistical group and calculate the simulated sample Ω x (f) The corresponding mean μ and variance σ 2 , skewness Skew, and kurtosis Kurt obtain the second group of statistics.

[0041] S140. Obtain first statistical difference information based on the first statistical group and the second statistical group.

[0042] Among them, the mean μ and variance σ corresponding to the historical sample Ω(f) of the economic scenario are 2 , skewness Skew, and kurtosis Kurt are respectively recorded as the first mean, first variance, first skewness, and first kurtosis, and the simulated sample Ω x (f) The corresponding mean μ and variance σ 2 , skewness Skew, and kurtosis Kurt are respectively recorded as the second mean, the second variance, the second skewness and the second kurtosis; the first mean difference can be obtained by calculating the absolute value of the difference between the first mean and the second mean, the first variance difference can be obtained by calculating the absolute value of the difference between the first variance and the second variance, the first skewness difference can be obtained by calculating the absolute value of the difference between the first skewness and the second skewness, and the first kurtosis difference can be obtained by calculating the absolute value of the difference between the first kurtosis and the second kurtosis; the first statistical difference information includes the first mean difference, the first variance difference, the first skewness difference and the first kurtosis difference.

[0043] Specifically, obtain the mean μ and variance σ corresponding to the economic scenario historical sample Ω(f) in the first statistical group 2 , skewness Skew, and kurtosis Kurt to obtain the first mean, first variance, first skewness, and first kurtosis, and also obtain the simulated sample Ω in the second statistical group x (f) The corresponding mean μ and variance σ 2, skewness Skew, and kurtosis Kurt to obtain the second mean, second variance, second skewness and second kurtosis; then, calculate the absolute value of the difference between the first mean and the second mean to obtain the first mean difference, calculate the absolute value of the difference between the first variance and the second variance to obtain the first variance difference, calculate the absolute value of the difference between the first skewness and the second skewness to obtain the first skewness difference, calculate the absolute value of the difference between the first kurtosis and the second kurtosis to obtain the first kurtosis difference; combine the first mean difference, the first variance difference, the first skewness difference and the first kurtosis difference to obtain the first statistical difference information.

[0044] It should be noted that the present embodiment obtains scenario samples by processing economic scenario historical samples based on a preset scenario generation model, and obtains simulation samples based on the scenario samples; obtains first statistical comparison information based on the economic scenario historical samples and the simulation samples, and the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result; establishes a first statistical group based on the economic scenario historical samples, and establishes a second statistical group based on the simulation samples; obtains first statistical difference information based on the first statistical group and the second statistical group. Through the above implementation, the first statistical comparison information can be obtained by processing the economic scenario historical samples and simulation samples, and the first statistical difference information can also be obtained by processing the first statistical group and the second statistical group. The quality of the economic scenario historical samples output by the economic scenario generator can be evaluated through the first statistical comparison information and the first statistical difference information, thereby determining the quality of the economic scenario.

[0045] Embodiment 2

[0046] A method for evaluating the quality of economic scenarios provided in Example 2 of the present application optimizes the "obtaining first statistical comparison information based on the economic scenario historical samples and the simulated samples" in Example 1; it should be noted that for the parts not described in detail in this example, reference may be made to the descriptions of other examples, and the method includes:

[0047] S210. Processing economic scenario historical samples based on a preset scenario generation model to obtain scenario samples, and obtaining simulation samples based on the scenario samples.

[0048] S221. Establish a first probability density based on the historical samples of the economic scenario and the preset width and smoothing function, obtain a first cumulative probability density based on the first probability density, and obtain a first quantile array based on the historical samples of the economic scenario.

[0049] Among them, in order to subsequently calculate the probability density and cumulative probability density corresponding to the economic scenario historical sample Ω(f), it is necessary to first establish the empirical distribution corresponding to the economic scenario historical sample Ω(f), that is, to estimate the probability that all sample points in the economic scenario historical sample Ω(f) are less than the preset value y; but since the economic scenario historical sample Ω(f) is a collection of discrete sample points, the empirical distribution corresponding to the directly constructed economic scenario historical sample Ω(f) is not smooth enough, which makes it impossible to calculate the corresponding probability density subsequently; for this reason, on the basis of the directly constructed empirical distribution, a preset width h and a smoothing function can be further introduced to smooth the directly constructed empirical distribution, so as to obtain the probability density corresponding to the economic scenario historical sample Ω(f); in this embodiment, the density function ω of the standard normal distribution is specifically used as the smoothing function, and the probability density corresponding to the economic scenario historical sample Ω(f) The expression is:

[0050]

[0051] Where N is the number of columns of the matrix corresponding to the sample points in the economic scenario historical sample Ω(f), h is the preset width, ω is the smooth function, and x t is a sample point in the economic scenario historical sample Ω(f).

[0052] Among them, the probability density is the first probability density, the first cumulative probability density is the result of integrating the first probability density, and the expression of the first cumulative probability density is In this embodiment, the first quartile group includes a first quartile, a second quartile, a third quartile, and a fourth quartile corresponding to the economic scenario historical sample Ω(f).

[0053] Specifically, according to the number of columns N of the matrix corresponding to the sample point in the economic scenario historical sample Ω(f), the preset width h and the smoothing function ω, the preset value y, and the sample point x in the economic scenario historical sample Ω(f), t Establish the first probability density Then, for this first probability density Integrate to get the first cumulative probability density Furthermore, each sample point in the economic scenario historical sample Ω(f) is arranged in order of value from small to large to obtain a first arranged sample, and the first quartile, the second quartile, the third quartile and the fourth quartile in the first arranged sample are determined to obtain a first quartile group.

[0054] S222. Establish a second probability density based on the simulated samples, the width and the smooth function, obtain a second cumulative probability density based on the second probability density, and obtain a second quantile array based on the simulated samples.

[0055] The principle is the same as that of establishing the first probability density. A new probability density can be established according to the simulated sample, width and smooth function, and the new probability density is recorded as the second probability density. The second probability density can be integrated to obtain the corresponding second cumulative probability density. In this embodiment, the second quantile array includes the simulated sample Ω x (f) The corresponding first quartile, second quartile, third quartile and fourth quartile.

[0056] Specifically, in the manner of establishing the first probability density, the probability density of the simulated samples, i.e., the second probability density, is established according to the simulated samples, the width, and the smoothing function. Then, the second probability density is integrated to obtain the second cumulative probability density. Furthermore, the simulated samples Ω are arranged in the order of the values ​​from small to large. x Each sample point in (f) obtains a second arranged sample, and determines the first quartile, the second quartile, the third quartile and the fourth quartile in the second arranged sample, thereby obtaining a second quartile group.

[0057] S223. Obtain a first probability density comparison result based on the first probability density and the second probability density, obtain a first cumulative probability density comparison result based on the first cumulative probability density and the second cumulative probability density, and obtain a first quantile comparison result based on the first quantile array and the second quantile array.

[0058] The first probability density comparison result is the comparison result between the function curve corresponding to the first probability density and the function curve corresponding to the second probability density, which can be found in Figure 3 The probability density function diagram shown in the figure, where the historical sample corresponds to the economic scenario historical sample Ω(f), and the simulated data corresponds to the simulated sample Ω x (f); The first cumulative probability density comparison result, that is, the comparison result between the function curve corresponding to the first cumulative probability density and the function curve corresponding to the second cumulative probability density, can be found in Figure 3 The cumulative probability density function diagram shown; the first quantile comparison result, that is, the comparison result between the first quantile array and the second quantile array, can be found in Figure 3 Box plot shown.

[0059] Specifically, a function curve corresponding to the first probability density and a function curve corresponding to the second probability density are generated, and the function curve corresponding to the first probability density and the function curve corresponding to the second probability density are compared to obtain a first probability density comparison result; a function curve corresponding to the first cumulative probability density and a function curve corresponding to the second cumulative probability density are generated, and the function curve corresponding to the first cumulative probability density and the function curve corresponding to the second cumulative probability density are compared to obtain a first cumulative probability density comparison result; and the first quantile array and the second quantile array are compared to obtain a first quantile comparison result.

[0060] S224. Obtain first statistical comparison information based on the first probability density comparison result, the first cumulative probability density comparison result, and the first quantile comparison result.

[0061] The first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result.

[0062] S230: Establish a first statistical group based on the economic scenario historical samples, and establish a second statistical group based on the simulation samples.

[0063] S240: Obtain first statistical difference information based on the first statistical group and the second statistical group.

[0064] Embodiment 3

[0065] A method for evaluating the quality of economic scenarios provided in Example 3 of the present application optimizes the "establishing a second probability density based on the simulated sample, the width, and the smooth function" in Example 2; it should be noted that for the parts not described in detail in this embodiment, reference may be made to the descriptions of other embodiments, and the method includes:

[0066] S310, processing economic scenario historical samples based on a preset scenario generation model to obtain scenario samples, and obtaining simulation samples based on the scenario samples.

[0067] S321, establishing a first probability density based on the economic scenario historical samples and a preset width and smoothing function, obtaining a first cumulative probability density based on the first probability density, and obtaining a first quantile array based on the economic scenario historical samples;

[0068] S322A: Create a simulated data sample based on the simulated sample.

[0069] The simulated samples include samples corresponding to N time points, and the simulated data samples are all sample points corresponding to the Nth time point in the simulated samples.

[0070] Specifically, all samples corresponding to the Nth time point in the simulated sample are obtained to obtain the simulated data sample.

[0071] S322B, establishing a second probability density based on the simulated data sample, the width and the smooth function.

[0072] Among them, the simulated sample empirical distribution is the probability of all sample points in the simulated data sample that are less than the preset value z; in order to make the constructed simulated sample empirical distribution smooth, the corresponding width and smooth function are also introduced for the simulated data sample. The principle is the same as establishing the first probability density According to the simulated data samples, the preset value z, the preset width and the smoothing function, a probability density corresponding to the simulated data samples, ie, a second probability density, can be constructed.

[0073] Specifically, the probability density corresponding to the simulated data sample is constructed according to the simulated data sample, the preset value z corresponding to the simulated data sample, the preset width and the smooth function to obtain the second probability density

[0074] S322C. Obtain a second cumulative probability density based on the second probability density, and obtain a second quantile array based on the simulated samples.

[0075] S323. Obtain a first probability density comparison result based on the first probability density and the second probability density, obtain a first cumulative probability density comparison result based on the first cumulative probability density and the second cumulative probability density, and obtain a first quantile comparison result based on the first quantile array and the second quantile array.

[0076] S324. Obtain first statistical comparison information based on the first probability density comparison result, the first cumulative probability density comparison result, and the first quantile comparison result.

[0077] S330: Establish a first statistical group based on the economic scenario historical samples, and establish a second statistical group based on the simulation samples.

[0078] S340: Obtain first statistical difference information based on the first statistical group and the second statistical group.

[0079] Embodiment 4

[0080] Embodiment 4 of the present application provides an economic scenario quality assessment method, which can be performed by a device for performing the method, and the device can be implemented by software and / or hardware. It should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments. The method includes:

[0081] S410, processing economic scenario historical samples based on a preset scenario generation model to obtain scenario samples, and obtaining simulation samples based on the scenario samples.

[0082] S420. Obtain first statistical comparison information based on the economic scenario historical samples and the simulation samples, wherein the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result.

[0083] S430: Establish a first statistical group based on the economic scenario historical samples, and establish a second statistical group based on the simulation samples.

[0084] S440: Obtain first statistical difference information based on the first statistical group and the second statistical group.

[0085] S450: Process the economic scenario history samples based on the scenario generation model to obtain a first scenario sample and a second scenario sample.

[0086] Among them, the original model parameter of the scenario generation model is θ. At this time, the scenario generation model is recorded as the initial scenario generation model M(θ). The sample data obtained by processing the economic scenario historical sample through the initial scenario generation model M(θ) is also the first scenario sample. In order to facilitate testing the influence of different model parameters on the generated scenario samples, this embodiment adopts the delta method to apply two-directional disturbances to the original model parameter θ. The disturbances in the two directions are also ±Δθ. The model parameter after applying the two-directional disturbances to the original model parameter θ is the current model parameter With the current model parameters The scenario generation model as a model parameter is also the current scenario generation model Generate a model based on the current situation The sample data obtained by processing the historical samples of economic scenarios is also the second scenario sample.

[0087] Specifically, the economic scenario historical samples are processed by the initial scenario generation model M(θ) to obtain the first scenario sample; further, the model parameters θ of the initial scenario generation model M(θ) are perturbed in two directions to obtain the current scenario generation model Generate a model based on the current situation The economic scenario historical samples are processed to obtain the second scenario samples.

[0088] S460: Obtain second statistical comparison information and second statistical value difference information based on the first scenario sample and the second scenario sample.

[0089] Among them, according to the first scenario sample, the corresponding third probability density can be calculated. The principle of calculating the third probability density is the same as that of establishing the first probability density, which will not be repeated here; then, the third probability density is integrated to obtain the third cumulative probability density; further, the third quantile array corresponding to the first scenario sample can also be calculated. In this embodiment, the third quantile array includes the first quartile, the second quartile, the third quartile and the fourth quartile corresponding to the first scenario sample; similarly, the fourth probability density, the fourth cumulative probability density and the fourth quantile array corresponding to the second scenario sample can also be calculated.

[0090] Statistical processing of the first scenario sample can obtain a third statistical group corresponding to the first scenario sample, wherein the third statistical group includes the mean, variance, skewness and kurtosis of the first scenario sample; similarly, a fourth statistic corresponding to the second scenario sample can also be calculated.

[0091] Among them, the second statistical comparison information includes the comparison results between the third probability density and the fourth probability density, the comparison results between the third cumulative probability density and the fourth cumulative probability density, and the comparison results between the third quantile array and the fourth quantile array; the second statistical difference information includes the absolute value of the difference in mean between the third statistical group and the fourth statistical group, the absolute value of the difference in variance, the absolute value of the difference in skewness, and the absolute value of the difference in kurtosis.

[0092] Specifically, a third probability density, a third cumulative probability density, a third quantile array and a third statistic group are established based on the first scenario samples. Similarly, a fourth probability density, a fourth cumulative probability density, a fourth quantile array and a fourth statistic group are established based on the second scenario samples. Furthermore, second statistical comparison information is obtained through the comparison results between the third probability density and the fourth probability density, the comparison results between the third cumulative probability density and the fourth cumulative probability density, and the comparison results between the third quantile array and the fourth quantile array. Second statistical difference information is also obtained through the absolute values ​​of the differences between the statistics in the third statistic group and the fourth statistic group.

[0093] S470: Obtain a high-sensitivity parameter group and a low-sensitivity parameter group based on the second statistical difference information and a preset difference information threshold.

[0094] The difference information threshold includes a first threshold preset for the absolute value of the mean difference in the second statistical difference information, a second threshold preset for the absolute value of the variance difference in the second statistical difference information, a third threshold preset for the absolute value of the skewness difference in the second statistical difference information, and a fourth threshold preset for the absolute value of the kurtosis difference in the second statistical difference information; if the model parameter If the corresponding mean difference absolute value is less than the first threshold, the variance difference absolute value is less than the second threshold, the skewness difference absolute value is less than the third threshold, and the kurtosis difference absolute value is less than the fourth threshold, then the model parameters are It is recorded as a high-sensitivity parameter, otherwise, it is recorded as a low-sensitivity parameter; when the disturbance Δθ is different, multiple different model parameters will be generated In this way, multiple different model parameters can be It is divided into multiple high-sensitivity parameters and multiple low-sensitivity parameters, and the multiple high-sensitivity parameters are recorded as a high-sensitivity parameter group θ H With low sensitivity parameter group θ L .

[0095] Specifically, one of the model parameters Take this as an example to determine the model parameters Is the corresponding mean difference absolute value less than the first threshold, variance difference absolute value less than the second threshold, skewness difference absolute value less than the third threshold, kurtosis difference absolute value less than the fourth threshold? If so, the model parameters Recorded as a high-sensitivity parameter, otherwise recorded as a low-sensitivity parameter; through the above steps, multiple model parameters The judgment is performed to obtain multiple high-sensitivity parameters and multiple low-sensitivity parameters, and the multiple high-sensitivity parameters are recorded as a high-sensitivity parameter group θ H With low sensitivity parameter group θ L .

[0096] S480: Obtain third statistical comparison information based on the high-sensitivity parameter group, the low-sensitivity parameter group, the scenario generation model, and the preset step length and number of paths.

[0097] Among them, the step size is recorded as n, representing n time points, the number of paths is recorded as m, representing m paths, and each path is composed of sample points corresponding to multiple time points; by presetting the step size n and the number of paths m, a sample to be processed can be generated, and the sample to be processed corresponds to n time points, and each time point corresponds to m sample points; by setting different n and / or different m, a variety of samples to be processed can be generated, taking one of the samples to be processed as an example, by inputting the sample to be processed into the scenario generation model M for processing, the corresponding scenario sample can be obtained, and the probability density, cumulative probability density and quantile array corresponding to the scenario sample can be further calculated; therefore, a variety of samples to be processed can correspond to the calculation of multiple groups of probability density, cumulative probability density and quantile array; the comparison results between the probability densities in different groups, the comparison results between the cumulative probability densities and the comparison results between the quantile arrays can obtain the third statistical comparison information.

[0098] Specifically, by setting different step sizes n and / or path numbers m, a plurality of samples to be processed are obtained, and each sample to be processed is processed separately by the scenario generation model to obtain a plurality of scenario samples; further, the probability density, cumulative probability density and quantile array corresponding to each scenario sample are calculated to obtain a plurality of groups of probability density, cumulative probability density and quantile array, and then the comparison results between the probability densities in different groups, the comparison results between the cumulative probability densities and the comparison results between the quantile arrays are collected to obtain the third statistical comparison information.

[0099] Embodiment 5

[0100] Embodiment 5 of the present application provides an economic scenario quality assessment method, which can be performed by a device for performing the method, and the device can be implemented by software and / or hardware. It should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments. The method includes:

[0101] S510 , processing economic scenario history samples based on a preset scenario generation model to obtain scenario samples, and obtaining simulation samples based on the scenario samples.

[0102] S520. Obtain first statistical comparison information based on the economic scenario historical samples and the simulation samples, wherein the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result.

[0103] S530: Establish a first statistical group based on the economic scenario historical samples, and establish a second statistical group based on the simulation samples.

[0104] S540: Obtain first statistical difference information based on the first statistical group and the second statistical group.

[0105] S550. Obtain model estimation samples and stress test samples based on the economic scenario historical samples.

[0106] The user can perform stress tests on the economic scenario historical samples and the scenario generation model, and configure the corresponding stress test configuration conditions for the stress test. The stress test configuration conditions can decompose the economic scenario historical samples into two test samples, one of which is the model estimation sample Ω E (f), the other is the pressure test sample Ω T (f).

[0107] Specifically, according to the pre-configured stress test configuration conditions, the economic scenario historical sample Ω(f) is decomposed into the model estimation sample Ω E (f) and pressure test sample Ω T (f).

[0108] S560: Process the model estimation sample based on the scenario generation model to obtain a scenario simulation sample.

[0109] Among them, the model estimation sample Ω is processed by the scenario generation model M E The results in (f) are sample scenario simulations.

[0110] Specifically, the scenario generation model M processes the model estimation sample Ω E (f) Obtain scenario simulation samples.

[0111] S570. Obtain a sample sequence based on the scenario simulation sample, the stress test sample and a preset percentile array.

[0112] Among them, the preset percentile array includes the first percentile quant t,α and the second percentile quant t,1-α In this embodiment, t represents the time point in the scenario simulation sample, α is the significance level, and α=5% is an example. Taking a moment in the scenario simulation sample as an example, the moment corresponds to sample points on multiple paths, that is, the moment corresponds to a group of sample points, quant t,a Represents the last sample point among the first α sample points in this group of sample points; quant t,1-α Characterize the last sample point in the first 1-α sample points in this group of sample points; use the pressure test sample Ω T Take a sample point in (f) as an example and determine whether the sample point is greater than quant t,α and less than quant t,1-α If yes, then set the sample point to 1; otherwise, set it to 0; t,α With quant t,1-α For the stress test sample Ω T Each sample point x in (f) t By making a judgment, a sequence consisting of 1 and 0 can be obtained, and the sequence is recorded as a sample sequence, and the sequence element of the sample sequence is recorded as H t , sample sequence H t The expression is as follows:

[0113]

[0114] Specifically, the first percentile quantile is set according to the significance level α and a set of sample points corresponding to the time point t. t,α and the second percentile quant t,1-α , and then determine the stress test sample Ω T The sample point x in (f) t Is it greater than the first percentile quant? t,αAnd less than the second percentile quant t,1-α , if so, then the corresponding sample point x t Set to 1, otherwise set to 0, thus obtaining a sample sequence.

[0115] S580. Obtain scenario coverage based on the sample sequence and the stress test sample.

[0116] Among them, the scenario coverage is the stress test sample Ω T (f) The sequence element H corresponding to each time point t t The cumulative sum of the ratios to the total number of time points T, and the scenario coverage is recorded as

[0117] Specifically, take the stress test sample Ω T Take a time point t in (f) as an example, and calculate the sequence element H corresponding to the time t. t , then calculate the sequence element H t The ratio of the total number of time points T, and then the ratio corresponding to each time point t is accumulated to obtain the scenario coverage rate

[0118] Embodiment 6

[0119] Embodiment 6 of the present application provides an economic scenario quality assessment method, which can be performed by a device for performing the method, and the device can be implemented by software and / or hardware. It should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments. The method includes:

[0120] S610: Processing economic scenario history samples based on a preset scenario generation model to obtain scenario samples, and obtaining simulation samples based on the scenario samples.

[0121] S620. Obtain first statistical comparison information based on the economic scenario historical samples and the simulation samples, wherein the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result.

[0122] S630: Establish a first statistical group based on the economic scenario historical samples, and establish a second statistical group based on the simulation samples.

[0123] S640: Obtain first statistical difference information based on the first statistical group and the second statistical group.

[0124] S650: Generate a time series sample vector based on the scenario sample, and obtain a probability metric based on the time series sample vector.

[0125] Among them, the scenario sample xf =(x 1，m ,x 2，m ,……,x t，m ,……,x N，m ), t=1,2,……,N;m=1,2,……,M;known scenario sample x f There are m paths in total, each path corresponds to N sample points x t , m ; Based on the sample points corresponding to each path, a vector of the path is formed, and the vector is recorded as the time series sample vector X t , each time series sample vector X t Corresponding to multiple sample points, according to the time series sample vector X t Corresponding to multiple sample points, the time series sample vector X can be calculated t The probability density (empirical distribution) of the corresponding path, the collection of each time series sample vector X t The corresponding probability density obtains the probability measure

[0126] Specifically, based on the scenario sample x f The sample points corresponding to each path form the time series sample vector X of the corresponding path. t , calculate the time series sample vector X t The probability density corresponding to each sample point in , and then the sample vector X of each time series is collected t The corresponding probability density obtains the probability measure

[0127] S660. Generate a market improvement simulation scenario, a market deterioration simulation scenario, a market high volatility simulation scenario, and a market low volatility simulation scenario based on the scenario samples.

[0128] Among them, the scenario sample x f Multiple sample points x in t，m has its corresponding sample median, recorded as the first sample median, and the set is greater than the first sample median x t，m Get a simulated scenario of a market turnaround The union set is not greater than the value of the first sample x t，m Get a simulated market downturn scenario Calculate scenario sample x f For each sample point x t , m The square value of the quadratic scenario sample is obtained. The multiple sample points x in the quadratic scenario sample t，m 2 , has its corresponding sample median, recorded as the second sample median, and the set is greater than the second sample median x t , m2 The corresponding original sample point x t，m Get a high volatility simulation scenario The set is not greater than the value of x in the second sample t，m 2 The corresponding original sample point x t，m Get a low volatility market simulation scenario

[0129] Specifically, determine the scenario sample x f The sample median of the first sample is obtained, and the scenario sample x is judged f The sample point x in t，m Is it greater than the median of the first sample? Set the scenario samples x that are greater than the median of the first sample f The sample point x in t，m Get a simulated scenario of a market turnaround The set of scenario samples x that is not greater than the median value of the first sample f The sample point x in t，m Get a simulated market downturn scenario Further, calculate the scenario sample x f The square value of each sample point in the quadratic scenario sample is obtained, and the sample median in the quadratic scenario sample is determined to obtain the second sample median. The sample point x in the quadratic scenario sample is determined t，m 2 Is it greater than the median of the second sample? Set the sample points x that are greater than the median of the second sample. t，m 2 The corresponding original sample point x t，m Get a high volatility simulation scenario The set of sample points x that are not greater than the median value of the second sample t，m 2 The corresponding original sample point x t , m Get a low volatility market simulation scenario

[0130] S670. Obtain a probability metric set based on the probability metric, the market improvement simulation scenario, the market deterioration simulation scenario, the market high volatility simulation scenario, and the market low volatility simulation scenario.

[0131] Among them, the probability metric set Q m is a probability measure Market turnaround scenario Market downturn simulation scenario High market volatility simulation scenario And a collection of low volatility market simulation scenarios

[0132] S680: Obtain a path risk metric and a time risk metric based on the probability metric set.

[0133] Among them, for the scenario sample x f For each path, the risk value VaR and expected loss ES corresponding to each sample point on each path can be calculated, and the risk value VaR corresponding to each path is recorded as VaR m , and the expected loss ES corresponding to each path is recorded as ES m ; Further, through the risk value VaR corresponding to each path m The maximum value at risk maxVaR can be determined m and minimum value at risk minVaR m , according to the maximum value at risk maxVaR m and minimum value at risk minVaR m The first risk value interval [minVaR m ,maxVaR m ], similarly, we can get the maximum expected loss maxES m and minimum expected loss minES m , according to the maximum expected loss maxES m and minimum expected loss minES m The first expected loss interval [minES m ,maxES m ]; the scenario sample x f Each sample point in the quantification is the first risk value interval [minVaR m ,maxVaR m ] to obtain the first path risk measure, and convert the scenario sample x f Each sample point in is quantized to the first expected loss interval [minES m ,maxES m ] obtain a second path risk metric, the path risk metric includes the first path risk metric and the second path risk metric.

[0134] Among them, for the scenario sample x f At each time point, the risk value VaR and expected loss ES corresponding to each sample point at each time point can be calculated, and the risk value VaR corresponding to each time point is recorded as VaR t , and the expected loss ES corresponding to each time point is recorded as ES t ; Further, through the risk value VaR corresponding to each time point t The maximum value at risk maxVaR can be determined t and minimum value at risk minVaR t, according to the maximum value at risk maxVaR t and minimum value at risk minVaR t The second risk value interval [minVaR t ,maxVaR t ], similarly, we can get the maximum expected loss maxES t and minimum expected loss minES t , according to the maximum expected loss maxES t and minimum expected loss minES t The second expected loss interval [minES t ,maxES t ]; the scenario sample x f Each sample point in the quantification is the second risk value interval [minVaR t ,maxVaR t ] to obtain the first-time risk measure, and convert the scenario sample x f Each sample point in is quantized to the second expected loss interval [minES t ,maxES t ] obtain a second time risk metric, the time risk metric includes the first time risk metric and the second time risk metric.

[0135] Specifically, determine the scenario sample x f The first risk value interval corresponding to the path [minVaR m ,maxVaR m ] and the first expected loss interval [minES m ,maxES m ], the scenario sample x f The sample points in the first risk value interval [minVaR m ,maxVaR m ] to obtain the first path risk measure, and convert the scenario sample x f The sample points in are quantized to the first expected loss interval [minES m ,maxES m ] obtain the second path risk metric, and obtain the path risk metric by combining the first path risk metric and the second path risk metric.

[0136] Further, determine the scenario sample x f The second risk value interval corresponding to the time point [minVaR t ,maxVaR t ] and the second expected loss interval [minES t ,maxES t ], the scenario sample x fThe sample points in the second risk value interval [minVaR t ,maxVaR t ] to obtain the first-time risk measure, and convert the scenario sample x f The sample points in are quantized to the second expected loss interval [minES t ,maxES t ] obtain a second time risk metric, and obtain a time risk metric by combining the first time risk metric and the second time risk metric.

[0137] Embodiment 7

[0138] Embodiment 7 of the present application provides an economic scenario quality assessment method, which can be performed by a device for performing the method, and the device can be implemented by software and / or hardware. It should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments. The method includes:

[0139] S701. Processing economic scenario historical samples based on a preset scenario generation model to obtain scenario samples, and obtaining simulation samples based on the scenario samples.

[0140] S702. Obtain first statistical comparison information based on the economic scenario historical samples and the simulation samples, wherein the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result.

[0141] S703: Establish a first statistical group based on the economic scenario historical samples, and establish a second statistical group based on the simulation samples.

[0142] S704: Obtain first statistical difference information based on the first statistical group and the second statistical group.

[0143] S705 . Process the economic scenario history samples based on the scenario generation model to obtain a first scenario sample and a second scenario sample.

[0144] S706: Obtain second statistical comparison information and second statistical value difference information based on the first scenario sample and the second scenario sample.

[0145] S707: Obtain a high-sensitivity parameter group and a low-sensitivity parameter group based on the second statistical difference information and a preset difference information threshold.

[0146] S708. Obtain third statistical comparison information based on the high-sensitivity parameter group, the low-sensitivity parameter group, the scenario generation model, and the preset step length and number of paths.

[0147] S709. Obtain model estimation samples and stress test samples based on the economic scenario historical samples.

[0148] S710: Process the model estimation sample based on the scenario generation model to obtain a scenario simulation sample.

[0149] S711. Obtain a sample sequence based on the scenario simulation sample, the stress test sample and a preset percentile array.

[0150] S712. Obtain scenario coverage based on the sample sequence and the stress test sample.

[0151] S713: Generate a time series sample vector based on the scenario sample, and obtain a probability metric based on the time series sample vector.

[0152] S714. Generate a market improvement simulation scenario, a market deterioration simulation scenario, a market high volatility simulation scenario, and a market low volatility simulation scenario based on the scenario samples.

[0153] S715, obtaining a probability metric set based on the probability metric, the market improvement simulation scenario, the market deterioration simulation scenario, the market high volatility simulation scenario, and the market low volatility simulation scenario;

[0154] S716: Obtain a path risk metric and a time risk metric based on the probability metric set.

[0155] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0156] Embodiment 8

[0157] Based on the same inventive concept, this embodiment also provides an economic scenario quality assessment device for implementing the economic scenario quality assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more economic scenario quality assessment device embodiments provided below can refer to the limitations of the economic scenario quality assessment method above, and will not be repeated here.

[0158] In this embodiment, Figure 4 As shown, an economic scenario quality assessment device is provided, comprising:

[0159] A sample generation module, used to process economic scenario historical samples based on a preset scenario generation model to obtain scenario samples, and to obtain simulation samples based on the scenario samples;

[0160] A statistical comparison information generation module, configured to obtain first statistical comparison information based on the economic scenario historical sample and the simulation sample, wherein the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result;

[0161] A statistics group establishment module, used to establish a first statistics group based on the economic scenario historical samples, and to establish a second statistics group based on the simulation samples;

[0162] The statistic difference information generating module is used to obtain first statistic difference information based on the first statistic group and the second statistic group.

[0163] Each module in the above economic scenario quality assessment device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0164] It should be noted that the present embodiment obtains scenario samples by processing economic scenario historical samples based on a preset scenario generation model, and obtains simulation samples based on the scenario samples; obtains first statistical comparison information based on the economic scenario historical samples and the simulation samples, and the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result; establishes a first statistical group based on the economic scenario historical samples, and establishes a second statistical group based on the simulation samples; obtains first statistical difference information based on the first statistical group and the second statistical group. Through the above implementation, the first statistical comparison information can be obtained by processing the economic scenario historical samples and simulation samples, and the first statistical difference information can also be obtained by processing the first statistical group and the second statistical group. The quality of the economic scenario historical samples output by the economic scenario generator can be evaluated through the first statistical comparison information and the first statistical difference information, thereby determining the quality of the economic scenario.

[0165] Embodiment 9

[0166] In this embodiment, an economic scenario quality assessment device is provided, comprising:

[0167] A sample generation module, used to process economic scenario historical samples based on a preset scenario generation model to obtain scenario samples, and to obtain simulation samples based on the scenario samples;

[0168] A statistical comparison information generation module, configured to obtain first statistical comparison information based on the economic scenario historical sample and the simulation sample, wherein the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result;

[0169] A statistics group establishment module, used to establish a first statistics group based on the economic scenario historical samples, and to establish a second statistics group based on the simulation samples;

[0170] A statistic difference information generating module, configured to obtain first statistic difference information based on the first statistic group and the second statistic group;

[0171] A scenario sample generation module, used for processing the economic scenario history samples based on the scenario generation model to obtain a first scenario sample and a second scenario sample;

[0172] A comparison difference information generating module, configured to obtain second statistical comparison information and second statistical value difference information based on the first scenario sample and the second scenario sample;

[0173] A parameter group generating module, used for obtaining a high-sensitivity parameter group and a low-sensitivity parameter group based on the second statistical difference information and a preset difference information threshold;

[0174] A comparison information generation module, configured to obtain third statistical comparison information based on the high-sensitivity parameter group, the low-sensitivity parameter group, the scenario generation model, and a preset step length and number of paths;

[0175] A sample decomposition module, used to obtain a model estimation sample and a stress test sample based on the economic scenario historical sample;

[0176] An estimation sample processing module, used for processing the model estimation sample based on the scenario generation model to obtain a scenario simulation sample;

[0177] A sample sequence generation module, used to obtain a sample sequence based on the scenario simulation sample, the stress test sample and a preset percentile array;

[0178] A coverage calculation module, used to obtain scenario coverage based on the sample sequence and the stress test sample;

[0179] A probability metric generation module, used to generate a time series sample vector based on the scenario sample, and obtain a probability metric based on the time series sample vector;

[0180] A simulation scenario generation module, for generating a market improvement simulation scenario, a market deterioration simulation scenario, a market high volatility simulation scenario, and a market low volatility simulation scenario based on the scenario samples;

[0181] A probability metric set generation module, configured to obtain a probability metric set based on the probability metric, the market improvement simulation scenario, the market deterioration simulation scenario, the market high volatility simulation scenario, and the market low volatility simulation scenario;

[0182] The risk metric generation module is used to obtain a path risk metric and a time risk metric based on the probability metric set.

[0183] Embodiment 10

[0184] In this embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an economic scenario quality assessment method is implemented.

[0185] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the computer device to which the scheme of the present disclosure is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0186] Embodiment 11

[0187] In this embodiment, a computer readable storage medium is provided. Figure 6 As shown, a computer program is stored thereon, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0188] Embodiment 12

[0189] In this embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0190] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0191] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided by the present disclosure can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided by the present disclosure may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided by the present disclosure may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited thereto.

[0192] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0193] The above-described embodiments only express several implementation methods of the present disclosure, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present disclosure, and these all belong to the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the attached claims.

Claims

1. A method for evaluating the quality of economic scenarios, characterized in that: include: Processing economic scenario historical samples based on a preset scenario generation model to obtain scenario samples, and obtaining simulation samples based on the scenario samples; Obtaining first statistical comparison information based on the economic scenario historical sample and the simulated sample, the first statistical comparison information including a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result; Establishing a first statistical group based on the economic scenario historical samples, and establishing a second statistical group based on the simulated samples; First statistical difference information is obtained based on the first statistical group and the second statistical group.

2. The method according to claim 1, characterized in that: The first statistical comparison information obtained based on the economic scenario historical sample and the simulation sample includes: Establishing a first probability density based on the economic scenario historical samples and a preset width and smoothing function, obtaining a first cumulative probability density based on the first probability density, and obtaining a first quantile array based on the economic scenario historical samples; Establish a second probability density based on the simulated sample, the width and the smooth function, obtain a second cumulative probability density based on the second probability density, and obtain a second quantile array based on the simulated sample; Obtain a first probability density comparison result based on the first probability density and the second probability density, obtain a first cumulative probability density comparison result based on the first cumulative probability density and the second cumulative probability density, and obtain a first quantile comparison result based on the first quantile array and the second quantile array; First statistical comparison information is obtained based on the first probability density comparison result, the first cumulative probability density comparison result, and the first quantile comparison result.

3. The method according to claim 2, characterized in that Establishing a second probability density based on the simulated sample, the width, and the smooth function includes: establishing a simulated data sample based on the simulated sample; A second probability density is established based on the simulated data samples, the width, and the smoothing function.

4. The method according to claim 1, characterized in that: Also includes: Processing the economic scenario history samples based on the scenario generation model to obtain a first scenario sample and a second scenario sample; Obtaining second statistical comparison information and second statistical value difference information based on the first scenario sample and the second scenario sample; Obtaining a high-sensitivity parameter group and a low-sensitivity parameter group based on the second statistical difference information and a preset difference information threshold; The third statistical comparison information is obtained based on the high-sensitivity parameter group, the low-sensitivity parameter group, the scenario generation model, and the preset step length and number of paths.

5. The method according to claim 1, characterized in that Also includes: Obtain model estimation samples and stress test samples based on the economic scenario historical samples; Processing the model estimation samples based on the scenario generation model to obtain scenario simulation samples; Obtaining a sample sequence based on the scenario simulation sample, the stress test sample and a preset percentile array; The scenario coverage is obtained based on the sample sequence and the stress test sample.

6. The method according to claim 1, characterized in that Also includes: generating a time series sample vector based on the scenario sample, and obtaining a probability metric based on the time series sample vector; Generate a market improvement simulation scenario, a market deterioration simulation scenario, a market high volatility simulation scenario, and a market low volatility simulation scenario based on the scenario samples; Obtain a probability metric set based on the probability metric, the market improvement simulation scenario, the market deterioration simulation scenario, the market high volatility simulation scenario, and the market low volatility simulation scenario; A path risk metric and a time risk metric are obtained based on the probability metric set.

7. An economic scenario quality assessment device, characterized in that: The device comprises: A sample generation module, used to process economic scenario historical samples based on a preset scenario generation model to obtain scenario samples, and to obtain simulation samples based on the scenario samples; A statistical comparison information generation module, configured to obtain first statistical comparison information based on the economic scenario historical sample and the simulation sample, wherein the first statistical comparison information includes a first probability density comparison result, a first cumulative probability density comparison result, and a first quantile comparison result; A statistics group establishment module, used to establish a first statistics group based on the economic scenario historical samples, and to establish a second statistics group based on the simulation samples; The statistic difference information generating module is used to obtain first statistic difference information based on the first statistic group and the second statistic group.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images