Assessment method and device for quantitative factor variable causal intensity in financial quantification field

Abstract

The invention relates to an evaluation method and device for quantitative factor variable causal intensity in the field of financial quantification, computer equipment, a storage medium and a computer program product. According to the method, the value of the effective transfer entropy can be accurately calculated, and errors in a quantitative factor variable causal intensity evaluation result are reduced. The method comprises the following steps: inputting a first information amount, first potential energy information, first kinetic energy information, a first state number, a second state number and a target variable into a first transfer entropy calculation model to obtain a first transfer entropy; inputting the first information amount, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state number, the second state number, the third state number and the target variable into a second transfer entropy calculation model to obtain a second transfer entropy; determining an effective transfer entropy of the quantization factor variable according to the second information amount, the first transfer entropy and the second transfer entropy; the effective transfer entropy is used to evaluate the causal intensity of the quantization factor variable on the target variable.

Description

Technical Field

[0001] The present application relates to computer data processing technology and the field of financial quantification, and in particular to an evaluation method, device, computer equipment, storage medium and computer program product for the causal strength of quantitative factor variables in the field of financial quantification. Background Art

[0002] With the development of computer data processing technology, the data processing capabilities of computers have been improved.

[0003] Subsequently, a technique for analyzing quantitative factor variables emerged in the field of financial quantification. This technique evaluates the effectiveness of quantitative factors by calculating the correlation coefficient between quantitative factors and returns. Among them, the correlation coefficient can measure the strength of the linear relationship between quantitative factors and returns, but cannot give a direction.

[0004] However, the quantitative factor analysis methods provided in traditional technologies only consider a single factor when evaluating the causal strength of quantitative factors, resulting in large errors in the evaluation results of the causal strength of quantitative factor variables in current technologies. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for evaluating the causal strength of quantitative factor variables in the field of financial quantification in response to the above-mentioned technical problems.

[0006] In a first aspect, the present application provides a method for evaluating the causal strength of quantitative factor variables in the field of financial quantification. The method comprises:

[0007] Obtaining the quantitative factor variable and the target resource attribute value within a preset time series, and obtaining the target variable according to the rate of return of the target resource attribute value after a preset period;

[0008] Performing trend decomposition on the quantitative factor variables and the target resource attribute values ​​respectively to obtain detrended quantitative factor variables and detrended target resource attribute values;

[0009] Determine the first state quantity and the first information amount of the target variable according to the ranking quantile corresponding to each yield in the historical yield sequence;

[0010] Obtaining first potential energy information, first kinetic energy information, and second state quantity of the target resource attribute value after detrending, inputting the first information quantity, first potential energy information, first kinetic energy information, first state quantity, second state quantity, and target variable into a preset first transfer entropy calculation model to obtain a first transfer entropy; the second state quantity is the common state quantity of the first potential energy information and the first kinetic energy information; the first transfer entropy is the transfer entropy of the target resource attribute value after detrending to the target variable;

[0011] The second potential energy information, the second kinetic energy information and the third state quantity of the detrended quantitative factor variable are obtained, and the first information quantity, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state quantity, the second state quantity, the third state quantity and the target variable are input into a preset second transfer entropy calculation model to obtain a second transfer entropy; the third state quantity is the state quantity of the second potential energy information and the second kinetic energy information together; the second transfer entropy is the transfer entropy of the target variable when the detrended quantitative factor variable and the detrended target resource attribute value act together;

[0012] The effective transfer entropy from the quantization factor variable to the target variable is determined based on the second information amount, the first transfer entropy and the second transfer entropy; the second information amount is the amount of information about the target variable newly added by the quantization factor variable and the target resource attribute value under a random time series; the effective transfer entropy is used to evaluate the causal strength of the quantization factor variable on the target variable.

[0013] In one embodiment, the trend decomposition of the quantitative factor variable and the target resource attribute value is performed respectively to obtain the detrended quantitative factor variable and the detrended target resource attribute value, including: obtaining a first simple moving average of the quantitative factor variable and a second simple moving average of the target resource attribute value within a preset time window; obtaining the detrended quantitative factor variable based on the quantitative factor variable and the first simple moving average, and obtaining the detrended target resource attribute value based on the resource attribute value and the second simple moving average.

[0014] In one embodiment, the first state quantity and the first information amount of the target variable are determined according to the ranking quantile corresponding to each yield in the historical yield sequence, including: dividing the target variable into states according to the ranking quantile corresponding to each yield in the historical yield sequence to obtain the first state quantity; inputting the first state quantity into a first information amount calculation model to obtain the first information amount of the target variable.

[0015] In one embodiment, before determining the effective transfer entropy from the quantization factor variable to the target variable according to the second information amount, the first transfer entropy and the second transfer entropy, the method further includes:

[0016] The preset time series is rearranged to generate a random time series; based on the first transfer entropy calculation model and the second transfer entropy calculation model, a third transfer entropy and a fourth transfer entropy under the random time series are determined; the third transfer entropy and the fourth transfer entropy are input into a second information quantity calculation model to obtain the second information quantity.

[0017] In one embodiment, determining the effective transfer entropy from the quantization factor variable to the target variable according to the second information amount, the first transfer entropy and the second transfer entropy includes:

[0018] The first transfer entropy and the second transfer entropy are input into the second information amount calculation model to obtain a third information amount; the third information amount is the information amount about the target variable newly added by the quantization factor variable and the resource attribute value under the preset time series; according to the second information amount and the third information amount, the corresponding information amount difference is obtained as the effective transfer entropy.

[0019] In one of the embodiments, the method further includes: upon receiving an adjustment instruction for a determined preset period, stopping the acquisition process of the effective transfer entropy, and obtaining an adjustment amount for the preset period according to the adjustment instruction; adjusting the preset period according to the adjustment amount; and re-executing the acquisition process of the effective transfer entropy according to the adjusted preset period.

[0020] In one of the embodiments, the method further includes: providing a recalculation entry for the effective transfer entropy; in response to a triggering operation on the recalculation entry, obtaining a current quantization factor variable, and re-obtaining the effective transfer entropy from the current quantization factor variable to the target variable based on the current quantization factor variable, a target resource attribute value and a target variable.

[0021] In a second aspect, the present application also provides a device for evaluating the causal strength of quantitative factor variables in the field of financial quantification. The device comprises:

[0022] An information acquisition module is used to acquire the quantitative factor variable and the target resource attribute value within a preset time series, and obtain the target variable according to the yield of the target resource attribute value after a preset period;

[0023] A trend decomposition module, used to perform trend decomposition on the quantitative factor variables and the target resource attribute values, respectively, to obtain the detrended quantitative factor variables and the detrended target resource attribute values;

[0024] An information processing module, used for determining the first state quantity and the first information quantity of the target variable according to the ranking quantile corresponding to each yield in the historical yield sequence;

[0025] A first calculation module is used to obtain the first potential energy information, the first kinetic energy information, and the second state quantity of the target resource attribute value after detrending, and input the first information quantity, the first potential energy information, the first kinetic energy information, the first state quantity, the second state quantity and the target variable into a preset first transfer entropy calculation model to obtain a first transfer entropy; the second state quantity is the state quantity of the first potential energy information and the first kinetic energy information together; the first transfer entropy is the transfer entropy of the target resource attribute value after detrending to the target variable;

[0026] A second calculation module is used to obtain the second potential energy information, the second kinetic energy information and the third state quantity of the detrended quantitative factor variable, and input the first information quantity, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state quantity, the second state quantity, the third state quantity and the target variable into a preset second transfer entropy calculation model to obtain a second transfer entropy; the third state quantity is the state quantity of the second potential energy information and the second kinetic energy information; the second transfer entropy is the transfer entropy of the target variable when the detrended quantitative factor variable and the detrended target resource attribute value act together;

[0027] The result acquisition module is used to determine the effective transfer entropy from the quantization factor variable to the target variable based on the second information amount, the first transfer entropy and the second transfer entropy; the second information amount is the amount of information about the target variable newly added by the quantization factor variable and the target resource attribute value under a random time series; the effective transfer entropy is used to evaluate the causal strength of the quantization factor variable on the target variable.

[0028] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0029] Obtain the quantitative factor variable and the target resource attribute value within a preset time series, and obtain the target variable according to the rate of return of the target resource attribute value after a preset period; perform trend decomposition on the quantitative factor variable and the target resource attribute value respectively to obtain the quantitative factor variable after detrending and the target resource attribute value after detrending; determine the first state quantity and the first information amount of the target variable according to the sorting quantile corresponding to each rate of return in the historical rate of return sequence; obtain the first potential energy information, the first kinetic energy information, and the second state quantity of the target resource attribute value after detrending, and input the first information amount, the first potential energy information, the first kinetic energy information, the first state quantity, the second state quantity and the target variable into a preset first transfer entropy calculation model to obtain the first transfer entropy; the second state quantity is the common state quantity of the first potential energy information and the first kinetic energy information; the first transfer entropy is the transfer entropy of the target resource attribute value after detrending to the target variable; obtain the detrended The second potential energy information, the second kinetic energy information and the third state quantity of the quantitative factor variable after trending, the first information quantity, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state quantity, the second state quantity, the third state quantity and the target variable are input into the preset second transfer entropy calculation model to obtain the second transfer entropy; the third state quantity is the state quantity of the second potential energy information and the second kinetic energy information; the second transfer entropy is the transfer entropy of the target variable when the quantitative factor variable after detrending and the target resource attribute value after detrending act together; according to the second information quantity, the first transfer entropy and the second transfer entropy, the effective transfer entropy from the quantitative factor variable to the target variable is determined; the second information quantity is the amount of information about the target variable newly added by the quantitative factor variable and the target resource attribute value under a random time series; the effective transfer entropy is used to evaluate the causal strength of the quantitative factor variable on the target variable.

[0030] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0031] Obtain the quantitative factor variable and the target resource attribute value within a preset time series, and obtain the target variable according to the rate of return of the target resource attribute value after a preset period; perform trend decomposition on the quantitative factor variable and the target resource attribute value respectively to obtain the quantitative factor variable after detrending and the target resource attribute value after detrending; determine the first state quantity and the first information amount of the target variable according to the sorting quantile corresponding to each rate of return in the historical rate of return sequence; obtain the first potential energy information, the first kinetic energy information, and the second state quantity of the target resource attribute value after detrending, and input the first information amount, the first potential energy information, the first kinetic energy information, the first state quantity, the second state quantity and the target variable into a preset first transfer entropy calculation model to obtain the first transfer entropy; the second state quantity is the common state quantity of the first potential energy information and the first kinetic energy information; the first transfer entropy is the transfer entropy of the target resource attribute value after detrending to the target variable; obtain the detrended The second potential energy information, the second kinetic energy information and the third state quantity of the quantitative factor variable after trending, the first information quantity, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state quantity, the second state quantity, the third state quantity and the target variable are input into the preset second transfer entropy calculation model to obtain the second transfer entropy; the third state quantity is the state quantity of the second potential energy information and the second kinetic energy information; the second transfer entropy is the transfer entropy of the target variable when the quantitative factor variable after detrending and the target resource attribute value after detrending act together; according to the second information quantity, the first transfer entropy and the second transfer entropy, the effective transfer entropy from the quantitative factor variable to the target variable is determined; the second information quantity is the amount of information about the target variable newly added by the quantitative factor variable and the target resource attribute value under a random time series; the effective transfer entropy is used to evaluate the causal strength of the quantitative factor variable on the target variable.

[0032] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0033] Obtain the quantitative factor variable and the target resource attribute value within a preset time series, and obtain the target variable according to the rate of return of the target resource attribute value after a preset period; perform trend decomposition on the quantitative factor variable and the target resource attribute value respectively to obtain the quantitative factor variable after detrending and the target resource attribute value after detrending; determine the first state quantity and the first information amount of the target variable according to the sorting quantile corresponding to each rate of return in the historical rate of return sequence; obtain the first potential energy information, the first kinetic energy information, and the second state quantity of the target resource attribute value after detrending, and input the first information amount, the first potential energy information, the first kinetic energy information, the first state quantity, the second state quantity and the target variable into a preset first transfer entropy calculation model to obtain the first transfer entropy; the second state quantity is the common state quantity of the first potential energy information and the first kinetic energy information; the first transfer entropy is the transfer entropy of the target resource attribute value after detrending to the target variable; obtain the detrended The second potential energy information, the second kinetic energy information and the third state quantity of the quantitative factor variable after trending, the first information quantity, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state quantity, the second state quantity, the third state quantity and the target variable are input into the preset second transfer entropy calculation model to obtain the second transfer entropy; the third state quantity is the state quantity of the second potential energy information and the second kinetic energy information; the second transfer entropy is the transfer entropy of the target variable when the quantitative factor variable after detrending and the target resource attribute value after detrending act together; according to the second information quantity, the first transfer entropy and the second transfer entropy, the effective transfer entropy from the quantitative factor variable to the target variable is determined; the second information quantity is the amount of information about the target variable newly added by the quantitative factor variable and the target resource attribute value under a random time series; the effective transfer entropy is used to evaluate the causal strength of the quantitative factor variable on the target variable.

[0034] The above-mentioned evaluation method, device, computer equipment, storage medium and computer program product for the causal strength of quantitative factor variables in the field of financial quantification first determine the forecast period of the target variable according to the business needs in the field of financial quantification; then decompose the quantitative factor variables and the target resource attribute values ​​into trend items and non-trend items; then use the detrended quantitative factor variables and target resource attribute values ​​to calculate the transfer entropy, thereby reducing the influence of the trend item on the potential energy information of the quantitative factor variables and the target resource attribute values, so as to effectively measure the causal strength of the transfer entropy on the target variable. In addition, this scheme takes into account the potential energy information and kinetic energy information of the quantitative factor variables at the same time, so as to more accurately calculate the value of the effective transfer entropy and reduce the errors in the evaluation results of the causal strength of the quantitative factor variables, which is helpful to more fully and comprehensively evaluate the causal strength of the quantitative factor variables and the target resource attribute values ​​on the target variable. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is an application environment diagram of an evaluation method of causal strength of quantitative factor variables in the field of financial quantification in one embodiment;

[0036] Figure 2 It is a flowchart of a method for evaluating the causal strength of quantitative factor variables in the field of financial quantification in one embodiment;

[0037] Figure 3 is a schematic flow chart of a second information amount calculation step in one embodiment;

[0038] Figure 4 A flowchart of a method for evaluating the causal strength of quantitative factor variables in the field of financial quantification in an application embodiment;

[0039] Figure 5 A schematic diagram of the causal intensity relationship of realized volatility in one embodiment;

[0040] Figure 6 is a schematic diagram of the causal strength relationship of fuzziness in one embodiment;

[0041] Figure 7 is a schematic diagram of the causal strength relationship of random numbers in one embodiment;

[0042] Figure 8 It is a structural block diagram of an evaluation device for the causal strength of quantitative factor variables in the field of financial quantification in one embodiment;

[0043] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application 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 application and are not used to limit the present application.

[0045] It should be noted that the customer information (including but not limited to customer device information, customer personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the customer or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0046] The evaluation method of the causal strength of quantitative factor variables in the field of financial quantification provided by the embodiment of the present application can be applied to Figure 1In the application environment shown, the terminal 101 communicates with the server 102 via a network. The data storage system can store data that the server 102 needs to process. The data storage system can be integrated on the server 102, or placed on the cloud or other network servers.

[0047] Specifically, the method for processing the recommended item pool provided in the embodiment of the present application can be executed by the server 102.

[0048] Exemplarily, the server 102 obtains the quantitative factor variable and the target resource attribute value within a preset time series, and obtains the target variable according to the rate of return of the target resource attribute value after a preset period; performs trend decomposition on the quantitative factor variable and the target resource attribute value respectively to obtain the detrended quantitative factor variable and the detrended target resource attribute value; determines the first state quantity and the first information quantity of the target variable according to the sorted quantiles corresponding to each rate of return in the historical rate of return sequence; the server 102 obtains the first potential energy information, the first kinetic energy information, and the second state quantity of the detrended target resource attribute value, and inputs the first information quantity, the first potential energy information, the first kinetic energy information, the first state quantity, the second state quantity and the target variable into a preset first transfer entropy calculation model to obtain the first transfer entropy; the second state quantity is the common state quantity of the first potential energy information and the first kinetic energy information; the first transfer entropy is the transfer of the target variable by the detrended target resource attribute value Transfer entropy; the server 102 obtains the second potential energy information, the second kinetic energy information and the third state quantity of the detrended quantitative factor variable, and inputs the first information quantity, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state quantity, the second state quantity, the third state quantity and the target variable into a preset second transfer entropy calculation model to obtain the second transfer entropy; the third state quantity is the state quantity of the second potential energy information and the second kinetic energy information; the second transfer entropy is the transfer entropy of the target variable when the detrended quantitative factor variable and the detrended target resource attribute value act together; the server 102 determines the effective transfer entropy from the quantitative factor variable to the target variable based on the second information quantity, the first transfer entropy and the second transfer entropy; the second information quantity is the amount of information about the target variable newly added by the quantitative factor variable and the target resource attribute value under a random time series; the effective transfer entropy is used to evaluate the causal strength of the quantitative factor variable on the target variable.

[0049] In such Figure 1 In the application environment shown, the terminal 101 can be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers. The server 102 can be implemented as an independent server or a server cluster consisting of multiple servers.

[0050] Step S201, obtaining a quantitative factor variable and a target resource attribute value within a preset time series, and obtaining a target variable according to the rate of return of the target resource attribute value after a preset period.

[0051] Among them, quantitative factor variables refer to the input variables used in quantitative models. These variables are usually calculated or evaluated based on mathematical models, statistical indicators or empirical rules. They are constructed to help explain and predict asset prices, market performance or investment returns. Quantitative factor variables can be a single factor or a combination of multiple factors, used to represent the measurement of different influencing factors.

[0052] Among them, the target resource attribute value within the preset time series can be an asset price time series, which is a sequence formed by arranging the price data of a specific asset (such as stocks, commodities, currencies, etc.) over a period of time in chronological order; it records the price level of the asset at different time points and can be used to analyze and predict the trend and volatility of asset prices.

[0053] The preset period may be 1 day, 1 week, 1 month or other periods.

[0054] Specifically, the server 102 responds to an evaluation request for the causal strength of quantitative factor variables in the field of financial quantification, obtains the quantitative factor variables and target resource attribute values ​​within a preset time series, and defines the yield of the target resource attribute value after a preset period as the target variable.

[0055] Step S202 , performing trend decomposition on the quantitative factor variables and the target resource attribute values ​​respectively, to obtain detrended quantitative factor variables and detrended target resource attribute values.

[0056] Among them, trend decomposition is a statistical method that decomposes time series data into trend, seasonal and residual components; it is used to analyze and understand the long-term trend, seasonal changes and random fluctuations in time series data.

[0057] Detrending refers to subtracting the long-term trend in time series data from the data in order to better analyze short-term fluctuations and seasonal changes in the data.

[0058] Specifically, the server 102 performs trend decomposition on the quantitative factor variables and the target resource attribute values ​​respectively to obtain the detrended quantitative factor variables and the detrended target resource attribute values.

[0059] Step S203, determining the first state quantity and the first information amount of the target variable according to the ranking quantile corresponding to each yield in the historical yield sequence.

[0060] The states of the target variable include but are not limited to rising, oscillating, and falling, and the number of first states is three.

[0061] The amount of information may be uncertainty, which refers to a measure of the degree of uncertainty or credibility of a measurement or estimation result.

[0062] Specifically, the server 102 determines the first state quantity of the target variable according to the ranking quantile corresponding to each yield in the historical yield sequence, and then obtains the first information quantity according to the first state quantity.

[0063] Step S204, obtain the first potential energy information, the first kinetic energy information and the second state quantity of the target resource attribute value after detrending, input the first information quantity, the first potential energy information, the first kinetic energy information, the first state quantity, the second state quantity and the target variable into a preset first transfer entropy calculation model to obtain the first transfer entropy; the second state quantity is the common state quantity of the first potential energy information and the first kinetic energy information; the first transfer entropy is the transfer entropy of the target resource attribute value to the target variable after detrending.

[0064] Among them, the information amount of the target resource attribute value after detrending is divided into two parts: the first potential energy information and the first kinetic energy information.

[0065] The first transfer entropy calculation model may be:

[0066]

[0067] Specifically, the server 102 obtains the first potential energy information, the first kinetic energy information, and the second state quantity of the target resource attribute value after detrending, and inputs the first information quantity, the first potential energy information, the first kinetic energy information, the first state quantity, the second state quantity, and the target variable into a preset first transfer entropy calculation model to obtain the first transfer entropy output by the first transfer entropy calculation model.

[0068] For example, calculate the transfer information entropy of the detrended asset price series Z to the target variable Y (That is, the reduction in uncertainty of Y when Z is known): . We divide the information of Z after detrending into two parts: potential information Zk and kinetic information Zp, which correspond to the size of Z value and the size of Z momentum, namely: Zk=Z, Zp=Z(t)-Z(tp), p is the parameter for momentum calculation, and the range of p is 1 to 10. Sort Zk and Zp, and divide the Zk and Zp values ​​into Zbin states according to the quantiles. The probability of each state is 1 / Zbin, and the value range of Zbin is 3 to 10. Therefore, The calculation method is as follows:

[0069]

[0070] Step S205, obtain the second potential energy information, the second kinetic energy information and the third state quantity of the detrended quantitative factor variable, input the first information quantity, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state quantity, the second state quantity, the third state quantity and the target variable into a preset second transfer entropy calculation model to obtain the second transfer entropy; the third state quantity is the common state quantity of the second potential energy information and the second kinetic energy information; the second transfer entropy is the transfer entropy of the target variable when the detrended quantitative factor variable and the detrended target resource attribute value act together.

[0071] Among them, the amount of information of the detrended quantitative factor variable is divided into two parts: the second potential information and the second kinetic information.

[0072] The second transfer entropy calculation model may be:

[0073]

[0074] Specifically, the server 102 obtains the second potential energy information, the second kinetic energy information and the third state quantity of the detrended quantitative factor variable, and inputs the first information quantity, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state quantity, the second state quantity, the third state quantity and the target variable into a preset second transfer entropy calculation model to obtain the second transfer entropy output by the second transfer entropy calculation model.

[0075] For example, the transfer entropy of the detrended quantitative factor X to the target variable Y is . We divide the information of X after detrending into two parts: potential information Xk and kinetic information Xp, which correspond to the size of X value and the size of X momentum respectively. Xk=X, Xp=X(t)-X(tp), p is the parameter for momentum calculation. Sort Xk and Xp, and divide the Xk and Xp values ​​into Zbin states according to the quantiles. The probability of each state is 1 / Xbin, and the value range of Xbin is 3 to 10. Therefore, when the asset price Z and the quantitative factor X work together, the transfer entropy of the target variable Y is:

[0076]

[0077] Step S206, determining the effective transfer entropy from the quantization factor variable to the target variable based on the second information amount, the first transfer entropy and the second transfer entropy; the second information amount is the amount of information about the target variable added by the quantization factor variable and the target resource attribute value under a random time series; the effective transfer entropy is used to evaluate the causal strength of the quantization factor variable on the target variable.

[0078] Specifically, the server 102 obtains a third amount of information based on the first transfer entropy and the second transfer entropy; the third amount of information is the amount of information about the target variable newly added by the quantization factor variables and resource attribute values ​​under a preset time series; based on the second amount of information and the third amount of information, the corresponding information amount difference is obtained as the effective transfer entropy.

[0079] In the above-mentioned evaluation method of the causal strength of quantitative factor variables in the field of financial quantification, the prediction period of the target variable is first determined according to the business needs in the field of financial quantification; then the quantitative factor variables and target resource attribute values ​​are decomposed into trend items and non-trend items; and then the transfer entropy is calculated using the detrended quantitative factor variables and target resource attribute values, thereby reducing the influence of the trend item on the potential energy information of the quantitative factor variables and the target resource attribute values, so that the causal strength of the transfer entropy on the target variable can be effectively measured. In addition, this scheme takes into account the potential energy information and kinetic energy information of the quantitative factor variables at the same time, so as to more accurately calculate the value of the effective transfer entropy and reduce the errors in the evaluation results of the causal strength of the quantitative factor variables, which is helpful to more fully and comprehensively evaluate the causal strength of the quantitative factor variables and the target resource attribute values ​​on the target variable.

[0080] In one of the embodiments, in the above step S202, the quantitative factor variables and the target resource attribute values ​​are respectively trend decomposed to obtain the detrended quantitative factor variables and the detrended target resource attribute values, which specifically includes the following steps: obtaining a first simple moving average of the quantitative factor variables and a second simple moving average of the target resource attribute values ​​within a preset time window; obtaining the detrended quantitative factor variables based on the quantitative factor variables and the first simple moving average, and obtaining the detrended target resource attribute values ​​based on the resource attribute values ​​and the second simple moving average.

[0081] Among them, the simple moving average is a common technical analysis tool used to smooth the fluctuations in asset prices in order to better observe price trends and changes; it is achieved by calculating the average price over a period of time.

[0082] Specifically, server 102 calculates a first simple moving average of the quantitative factor variable and a second simple moving average of the target resource attribute value within a preset time window; obtains the detrended quantitative factor variable based on the quantitative factor variable and the first simple moving average, and obtains the detrended target resource attribute value based on the resource attribute value and the second simple moving average.

[0083] For example, the simple moving average of the quantitative factor variable X is calculated. The window length used in the calculation of the simple moving average is between 10T and 50T. The difference between the quantitative factor variable X and its simple moving average is defined as the detrended factor variable X. Using the same method, the detrended asset price series Z is calculated. ， The detrended X and Z contain information about the predicted value of the target variable Y.

[0084] In this embodiment, by using a simple moving average, the quantitative factor variables after detrending and the target resource attribute values ​​after detrending are accurately calculated, so as to better observe the trends and changes of the quantitative factor variables and the resource attribute values.

[0085] In one of the embodiments, in the above step S203, the first state quantity and the first information amount of the target variable are determined according to the ranking quantile corresponding to each yield in the historical yield sequence, which specifically includes the following steps: according to the ranking quantile corresponding to each yield in the historical yield sequence, the target variable is divided into states to obtain the first state quantity; the first state quantity is input into the first information amount calculation model to obtain the first information amount of the target variable.

[0086] The first information amount calculation model may be:

[0087]

[0088] Specifically, the server 102 divides the target variable into states according to the ranking quantiles corresponding to each yield in the historical yield sequence to obtain a first state quantity; inputs the first state quantity into a first information quantity calculation model to obtain a first information quantity of the target variable output by the information quantity calculation model.

[0089] For example, sort the historical data values ​​of the target variable Y, and calculate the sorting quantile of each target variable Y value in the historical data. According to the quantile, divide the Y value into Ybin states, and the probability of each state is 1 / Ybin. The value range of Ybin is 3 to 10. When Ybin is equal to 3, it means that Y is divided into three states: rising, oscillating, and falling, and the probability of each state is 1 / 3. When Ybin is equal to 10, it means that Y is divided into 10 states, and the probability of each state is 1 / 10. At this time, the uncertainty (amount of information) of the target variable Y is:

[0090]

[0091] In this embodiment, the target variable is divided into states according to the ranking quantiles corresponding to each yield in the historical yield sequence to obtain the first state quantity; thus, the first information amount of the target variable is accurately calculated using the information amount calculation model with reference to the data indicator of the first state quantity.

[0092] In one embodiment, if Figure 3 As shown, before determining the effective transfer entropy from the quantization factor variable to the target variable according to the second information amount, the first transfer entropy and the second transfer entropy, the following steps are also included:

[0093] Step S301, rearrange the preset time sequence to generate a random time sequence;

[0094] Step S302, determining a third transfer entropy and a fourth transfer entropy under a random time series based on the first transfer entropy calculation model and the second transfer entropy calculation model;

[0095] Step S303: input the third transfer entropy and the fourth transfer entropy into a second information amount calculation model to obtain the second information amount.

[0096] The random time series may be a new time series formed by randomly shuffling and rearranging a preset time series.

[0097] Specifically, the server 102 rearranges the preset time series to generate a random time series; determines the third transfer entropy and the fourth transfer entropy under the random time series based on the first transfer entropy calculation model and the second transfer entropy calculation model; inputs the third transfer entropy and the fourth transfer entropy into the second information amount calculation model to obtain the second information amount output by the information amount calculation model.

[0098] In this embodiment, by generating a random time series, the third transfer entropy and the fourth transfer entropy under the random time series are determined with the help of the first transfer entropy calculation model and the second transfer entropy calculation model; thereby accurately calculating the second information amount, which helps to more fully and comprehensively evaluate the causal strength of the quantitative factor variables and the target resource attribute values ​​on the target variables.

[0099] In one of the embodiments, in the above step S206, the effective transfer entropy from the quantization factor variable to the target variable is determined based on the second information amount, the first transfer entropy and the second transfer entropy, which specifically includes the following steps: inputting the first transfer entropy and the second transfer entropy into the second information amount calculation model to obtain the third information amount; the third information amount is the amount of information about the target variable newly added by the quantization factor variable and the resource attribute value under a preset time series; and obtaining the corresponding information amount difference based on the second information amount and the third information amount as the effective transfer entropy.

[0100] The second information amount calculation model may be:

[0101]

[0102] Specifically, the server 102 inputs the first transfer entropy and the second transfer entropy into the second information amount calculation model to obtain the third information amount output by the second information amount calculation model; and obtains the corresponding information amount difference according to the second information amount and the third information amount as the effective transfer entropy.

[0103] For example, given the asset price Z, the amount of information added by the quantitative factor X about the target variable Y is: , the calculation formula of the effective transfer entropy from X to Y is as follows: ,in It represents a new time series formed by randomly shuffling and rearranging the time series X, which eliminates the inherent or potential statistical association or correlation between X and Y.

[0104] In this embodiment, the third information amount is obtained by inputting the first transfer entropy and the second transfer entropy into the second information amount calculation model, and the corresponding information amount difference is obtained according to the second information amount and the third information amount as the effective transfer entropy; thereby reducing the error in the causal strength evaluation results of the quantitative factor variables.

[0105] In one of the embodiments, the following steps are also included: when an adjustment instruction for a determined preset period is received, the acquisition process of the effective transfer entropy is stopped, and an adjustment amount for the preset period is obtained according to the adjustment instruction; the preset period is adjusted according to the adjustment amount; and according to the adjusted preset period, the acquisition process of the effective transfer entropy is re-executed.

[0106] The adjustment amount of the preset period may be a specific amount of time added or subtracted based on the preset period.

[0107] Specifically, when the server 102 receives an adjustment instruction for a determined preset period, it stops the acquisition process of the effective transfer entropy, and obtains the adjustment amount for the preset period according to the adjustment instruction; adjusts the preset period according to the adjustment amount; and re-executes the acquisition process of the effective transfer entropy according to the adjusted preset period.

[0108] In this embodiment, when an adjustment instruction for a determined preset period is received, the acquisition process of the effective transfer entropy is stopped, and the acquisition process of the effective transfer entropy is re-executed according to the adjusted preset period; thereby, the corresponding processing operations can be flexibly performed according to the actual needs of the user, which is conducive to providing the user with more comprehensive effective transfer entropy data.

[0109] In one of the embodiments, the following steps are also included: providing a recalculation entry for effective transfer entropy; in response to a trigger operation on the recalculation entry, obtaining the current quantization factor variable, and re-obtaining the effective transfer entropy from the current quantization factor variable to the target variable based on the current quantization factor variable, the target resource attribute value and the target variable.

[0110] Specifically, the server 102 provides a recalculation entry for effective transfer entropy; in response to a trigger operation on the recalculation entry, the current quantization factor variable is obtained, and the effective transfer entropy from the current quantization factor variable to the target variable is re-obtained according to the current quantization factor variable, the target resource attribute value and the target variable.

[0111] In this embodiment, by providing a recalculation entry for the effective transfer entropy, the effective transfer entropy from the current quantization factor variable to the target variable is re-obtained according to the current quantization factor variable, the target resource attribute value and the target variable; thereby, corresponding processing operations can be provided in a targeted manner according to the actual needs of the user, which is conducive to providing the user with effective transfer entropy data corresponding to different types of quantization factor variables.

[0112] In order to more clearly illustrate the evaluation method of the causal strength of quantitative factor variables in the field of financial quantification provided by the embodiment of the present application, the evaluation method of the causal strength of quantitative factor variables in the field of financial quantification is specifically described below with a specific embodiment. In one embodiment, Figure 4 As shown in FIG. 1 , a method for evaluating the causal strength of quantitative factor variables in the field of financial quantification in an application example is provided, which specifically includes the following steps:

[0113] Step S401, the financial asset used is the HSA00 index, the frequency is daily, and the target variable for prediction is the yield of the HSA00 index in the next 10 days.

[0114] Step S402, the target variable to be predicted has three states, and the probability of each state is equal, that is, Ybin=3: state 1 represents a decline, state 2 represents an oscillation, and state 3 represents an increase; when there is no prior information, the amount of information (uncertainty) of the target state is =1.5XX bits.

[0115] Step S403, calculate the simple moving average of the quantitative factor variable and the asset price, the window length used is 20T days, that is, 20*5=100 days; when calculating the first kinetic energy information Zp and the second kinetic energy information Xp, p takes the value of 5. Considering the limited amount of data, the first potential energy information Zk, the first kinetic energy information Zp, the second potential energy information Xk, and the second kinetic energy information Xp are discretized into 5 states according to quantiles, that is, Xbin=Zbin=5.

[0116] Step S404, three quantitative factors are selected, namely realized volatility, fuzziness and random number. The relationship between the three factors and the HSA00 index is as follows: Figure 5 , Figure 6 and Figure 7 As shown, the calculated transfer entropies are 0.08XX, 0.06XX and 0.05XX respectively, and the effective transfer entropies are 0.017XX, 0.004XX and -0.014XX respectively, as shown in Table 1. That is, the transfer entropy and effective transfer entropy of the realized volatility and ambiguity for the future 10-day return of the HSA00 index are higher than those of random numbers.

[0117] Table 1 The transfer entropy and effective transfer entropy of the three quantitative factors of fuzziness, realized volatility and random number on the return of HSA00 index in the next 10 days

[0118]

[0119] The beneficial effects brought by the above embodiments are as follows:

[0120] (1) Before calculating the effective transfer entropy, the quantitative factor variables X and asset prices Z are first decomposed into trend terms and non-trend terms according to the forecast period (T) of the target variable Y. The transfer entropy is calculated using the detrended quantitative factor variables X and asset prices Z to reduce the impact of the trend terms on the potential information of X and Z (Xk and Zp), thereby effectively measuring the causal strength of the transfer entropy on the target variable Y.

[0121] (2) This scheme takes into account both the amplitude (potential information) and momentum (kinetic information) of the quantitative factor, and more fully explores the amount of information (transfer entropy) that the quantitative factor variable X and asset price Z have on the target variable Y.

[0122] 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 is not strictly limited in order, 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 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.

[0123] Based on the same inventive concept, the embodiment of the present application also provides a device for evaluating the causal strength of quantitative factor variables in the financial quantification field for implementing the above-mentioned method for evaluating the causal strength of quantitative factor variables in the financial quantification field. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of the device for evaluating the causal strength of quantitative factor variables in the financial quantification field provided below can be referred to the limitations of the method for evaluating the causal strength of quantitative factor variables in the financial quantification field above, and will not be repeated here.

[0124] In one embodiment, Figure 8 As shown, a device for evaluating the causal strength of quantitative factor variables in the field of financial quantification is provided, comprising:

[0125] The information acquisition module 801 is used to acquire the quantitative factor variables and the target resource attribute values ​​within a preset time series, and obtain the target variable according to the yield of the target resource attribute values ​​after a preset period;

[0126] A trend decomposition module 802 is used to perform trend decomposition on the quantitative factor variables and the target resource attribute values ​​to obtain the detrended quantitative factor variables and the detrended target resource attribute values;

[0127] An information processing module 803 is used to determine the first state quantity and the first information amount of the target variable according to the ranking quantile corresponding to each yield in the historical yield sequence;

[0128] The first calculation module 804 is used to obtain the first potential energy information, the first kinetic energy information and the second state quantity of the target resource attribute value after detrending, and input the first information quantity, the first potential energy information, the first kinetic energy information, the first state quantity, the second state quantity and the target variable into a preset first transfer entropy calculation model to obtain the first transfer entropy; the second state quantity is the state quantity of the first potential energy information and the first kinetic energy information; the first transfer entropy is the transfer entropy of the target resource attribute value after detrending to the target variable;

[0129] The second calculation module 805 is used to obtain the second potential energy information, the second kinetic energy information and the third state quantity of the quantitative factor variable after detrending, and input the first information quantity, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state quantity, the second state quantity, the third state quantity and the target variable into a preset second transfer entropy calculation model to obtain the second transfer entropy; the third state quantity is the state quantity of the second potential energy information and the second kinetic energy information; the second transfer entropy is the transfer entropy of the target variable when the quantitative factor variable after detrending and the target resource attribute value after detrending act together;

[0130] The result acquisition module 806 is used to determine the effective transfer entropy from the quantitative factor variable to the target variable based on the second information amount, the first transfer entropy and the second transfer entropy; the second information amount is the amount of information about the target variable newly added by the quantitative factor variable and the target resource attribute value under a random time series; the effective transfer entropy is used to evaluate the causal strength of the quantitative factor variable on the target variable.

[0131] In one embodiment, the trend decomposition module 802 is also used to obtain a first simple moving average of the quantitative factor variable and a second simple moving average of the target resource attribute value within a preset time window; obtain the detrended quantitative factor variable based on the quantitative factor variable and the first simple moving average, and obtain the detrended target resource attribute value based on the target resource attribute value and the second simple moving average.

[0132] In one embodiment, the information processing module 803 is also used to divide the target variable into states according to the ranking quantiles corresponding to each yield in the historical yield sequence to obtain a first state quantity; input the first state quantity into the first information quantity calculation model to obtain the first information quantity of the target variable.

[0133] In one embodiment, the evaluation device for the causal strength of quantitative factor variables in the field of financial quantification also includes an information calculation module, which is used to rearrange the preset time series to generate a random time series; based on the first transfer entropy calculation model and the second transfer entropy calculation model, determine the third transfer entropy and the fourth transfer entropy under the random time series; input the third transfer entropy and the fourth transfer entropy into the second information quantity calculation model to obtain the second information quantity.

[0134] In one embodiment, the result acquisition module 806 is also used to input the first transfer entropy and the second transfer entropy into the second information quantity calculation model to obtain a third amount of information; the third amount of information is the amount of information about the target variable newly added by the quantitative factor variable and the resource attribute value under a preset time series; according to the second amount of information and the third amount of information, the corresponding information amount difference is obtained as the effective transfer entropy.

[0135] In one embodiment, the evaluation device for the causal strength of quantitative factor variables in the field of financial quantification also includes a period adjustment module, which is used to stop the acquisition process of the effective transfer entropy when receiving an adjustment instruction for a determined preset period, and obtain an adjustment amount for the preset period according to the adjustment instruction; adjust the preset period according to the adjustment amount; and re-execute the acquisition process of the effective transfer entropy according to the adjusted preset period.

[0136] In one embodiment, the evaluation device for the causal strength of quantitative factor variables in the field of financial quantification also includes a result recalculation module, which is used to provide a recalculation entry for effective transfer entropy; in response to a trigger operation on the recalculation entry, the current quantitative factor variable is obtained, and according to the current quantitative factor variable, the target resource attribute value and the target variable, the effective transfer entropy from the current quantitative factor variable to the target variable is re-obtained.

[0137] Each module in the above-mentioned evaluation device for the causal strength of quantitative factor variables in the field of financial quantification can be implemented in whole or in part by software, hardware, and a combination thereof. Each of the above-mentioned modules 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 the operations corresponding to each of the above modules.

[0138] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. 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 input / output interface of the computer device is used to exchange information between the processor and an external device. The communication 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, a method for evaluating the causal strength of quantitative factor variables in the field of financial quantification is implemented.

[0139] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application 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.

[0140] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0141] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0142] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0143] 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 in this application 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 in this application 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 to this. The processor involved in each embodiment provided in this application 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 to this.

[0144] 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.

[0145] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for evaluating the causal strength of quantitative factor variables in the field of financial quantification, characterized in that: The method comprises: Obtaining the quantitative factor variable and the target resource attribute value within a preset time series, and obtaining the target variable according to the rate of return of the target resource attribute value after a preset period; Performing trend decomposition on the quantitative factor variables and the target resource attribute values ​​respectively to obtain detrended quantitative factor variables and detrended target resource attribute values; Determine the first state quantity and the first information amount of the target variable according to the ranking quantile corresponding to each yield in the historical yield sequence; Obtaining first potential energy information, first kinetic energy information, and second state quantity of the target resource attribute value after detrending, inputting the first information quantity, first potential energy information, first kinetic energy information, first state quantity, second state quantity, and target variable into a preset first transfer entropy calculation model to obtain a first transfer entropy; the second state quantity is the common state quantity of the first potential energy information and the first kinetic energy information; the first transfer entropy is the transfer entropy of the target resource attribute value after detrending to the target variable; The second potential energy information, the second kinetic energy information and the third state quantity of the detrended quantitative factor variable are obtained, and the first information quantity, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state quantity, the second state quantity, the third state quantity and the target variable are input into a preset second transfer entropy calculation model to obtain a second transfer entropy; the third state quantity is the state quantity of the second potential energy information and the second kinetic energy information together; the second transfer entropy is the transfer entropy of the target variable when the detrended quantitative factor variable and the detrended target resource attribute value act together; The effective transfer entropy from the quantization factor variable to the target variable is determined based on the second information amount, the first transfer entropy and the second transfer entropy; the second information amount is the amount of information about the target variable newly added by the quantization factor variable and the target resource attribute value under a random time series; the effective transfer entropy is used to evaluate the causal strength of the quantization factor variable on the target variable.

2. The method according to claim 1, characterized in that The step of performing trend decomposition on the quantitative factor variables and the target resource attribute values ​​to obtain detrended quantitative factor variables and detrended target resource attribute values ​​includes: Acquire a first simple moving average of the quantitative factor variable and a second simple moving average of the target resource attribute value within a preset time window; The detrended quantification factor variable is obtained according to the quantification factor variable and the first simple moving average, and the detrended target resource attribute value is obtained according to the target resource attribute value and the second simple moving average.

3. The method according to claim 1, characterized in that The determining of the first state quantity and the first information amount of the target variable according to the ranking quantile corresponding to each yield in the historical yield sequence includes: According to the ranking quantile corresponding to each yield in the historical yield sequence, the target variable is divided into states to obtain the first state quantity; The first state quantity is input into a first information quantity calculation model to obtain the first information quantity of the target variable.

4. The method according to claim 1, characterized in that Before determining the effective transfer entropy from the quantization factor variable to the target variable according to the second information amount, the first transfer entropy and the second transfer entropy, the method further includes: Rearranging the preset time series to generate the random time series; Determine a third transfer entropy and a fourth transfer entropy under the random time series based on the first transfer entropy calculation model and the second transfer entropy calculation model; The third transfer entropy and the fourth transfer entropy are input into a second information amount calculation model to obtain the second information amount.

5. The method according to claim 4, characterized in that The determining, according to the second information amount, the first transfer entropy and the second transfer entropy, the effective transfer entropy from the quantization factor variable to the target variable comprises: Inputting the first transfer entropy and the second transfer entropy into the second information amount calculation model to obtain a third amount of information; the third amount of information is the amount of information about the target variable newly added by the quantization factor variable and the resource attribute value under the preset time series; According to the second amount of information and the third amount of information, a corresponding information amount difference is obtained as the effective transfer entropy.

6. The method according to claim 1, characterized in that The method further comprises: When receiving an adjustment instruction for a determined preset period, stopping the acquisition process of the effective transfer entropy, and obtaining an adjustment amount for the preset period according to the adjustment instruction; adjusting the preset period according to the adjustment amount; According to the adjusted preset period, the process of acquiring the effective transfer entropy is re-executed.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Providing a recalculation entry for the effective transfer entropy; In response to the triggering operation on the recalculation entry, a current quantization factor variable is obtained, and according to the current quantization factor variable, a target resource attribute value and a target variable, an effective transfer entropy from the current quantization factor variable to the target variable is re-obtained.

8. An evaluation device for the causal strength of quantitative factor variables in the field of financial quantification, characterized in that: The device comprises: An information acquisition module is used to acquire the quantitative factor variable and the target resource attribute value within a preset time series, and obtain the target variable according to the yield of the target resource attribute value after a preset period; A trend decomposition module, used to perform trend decomposition on the quantitative factor variables and the target resource attribute values, respectively, to obtain the detrended quantitative factor variables and the detrended target resource attribute values; An information processing module, used for determining the first state quantity and the first information quantity of the target variable according to the ranking quantile corresponding to each yield in the historical yield sequence; A first calculation module is used to obtain the first potential energy information, the first kinetic energy information, and the second state quantity of the target resource attribute value after detrending, and input the first information quantity, the first potential energy information, the first kinetic energy information, the first state quantity, the second state quantity and the target variable into a preset first transfer entropy calculation model to obtain a first transfer entropy; the second state quantity is the state quantity of the first potential energy information and the first kinetic energy information together; the first transfer entropy is the transfer entropy of the target resource attribute value after detrending to the target variable; A second calculation module is used to obtain the second potential energy information, the second kinetic energy information and the third state quantity of the detrended quantitative factor variable, and input the first information quantity, the first potential energy information, the first kinetic energy information, the second potential energy information, the second kinetic energy information, the first state quantity, the second state quantity, the third state quantity and the target variable into a preset second transfer entropy calculation model to obtain a second transfer entropy; the third state quantity is the state quantity of the second potential energy information and the second kinetic energy information; the second transfer entropy is the transfer entropy of the target variable when the detrended quantitative factor variable and the detrended target resource attribute value act together; The result acquisition module is used to determine the effective transfer entropy from the quantization factor variable to the target variable based on the second information amount, the first transfer entropy and the second transfer entropy; the second information amount is the amount of information about the target variable newly added by the quantization factor variable and the target resource attribute value under a random time series; the effective transfer entropy is used to evaluate the causal strength of the quantization factor variable on the target variable.

9. 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 7 are implemented.

10. 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 7 are implemented.

Images