Financial time series data feature engineering variable dimension raising method

Abstract

The invention provides a financial time series data feature engineering variable dimension raising method, which comprises the following steps: acquiring to-be-processed financial market time series data, and preprocessing the to-be-processed financial market time series data to obtain preprocessed data; wherein the financial market time series data to be processed comprises day data and month data; dividing the preprocessed data according to a preset time scale to obtain grouped data; performing linear regression parameter calculation on the grouped data to obtain linear regression parameters; according to the linear regression parameters, features are constructed according to a preset dimension raising ratio, dimension raising data are obtained, and the data are selected. According to the method, an efficient data preprocessing and feature engineering method can be introduced, the data processing flow is optimized, and it is ensured that information with actual value can be recognized and obtained from mass market data. The depth and the accuracy of data analysis are improved, and a reliable basis can be provided for strategic decision making, so that the competitiveness and the flexible strain capacity in a dynamic market environment are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of financial data processing, and in particular to a method for increasing the dimension of financial time series data feature engineering variables. Background Art

[0002] Financial data is complex and high-dimensional, but in actual operations, the potential information is often not mined in depth due to unreasonable feature selection, insufficient data preprocessing, and improper feature engineering methods.

[0003] In traditional financial data processing, financial statistical analysis methods are relatively simple and mainly rely on simple statistical analysis indicators, resulting in poor data comparability. The lack of scientific data selection leads to inaccurate prediction results, which sometimes even deviate from the development direction of things. At the same time, there is also the problem of insufficient depth and breadth of data mining, resulting in a significant bottleneck in improving prediction accuracy. Summary of the invention

[0004] Based on this, it is necessary to provide a method for increasing the dimension of feature engineering variables of financial time series data in response to the above technical problems.

[0005] A method for increasing the dimension of feature engineering variables of financial time series data, comprising the following steps:

[0006] Acquire the financial market time series data to be processed, and preprocess the financial market time series data to be processed to obtain preprocessed data; wherein the financial market time series data to be processed includes daily data and monthly data;

[0007] Dividing the preprocessed data according to a preset time scale to obtain grouped data;

[0008] Calculating linear regression parameters for the grouped data to obtain linear regression parameters; wherein the linear regression parameters include: mean value, standard deviation and slope;

[0009] According to the linear regression parameters, features are constructed according to preset dimensionality increase ratios to obtain dimensionality increase data, and the data are selected.

[0010] In one embodiment, obtaining the financial market time series data to be processed includes:

[0011] Get ready-to-process financial market time series data through a real-time API.

[0012] In one embodiment, preprocessing the to-be-processed financial market time series data to obtain preprocessed data includes:

[0013] Performing missing value processing on the daily data to obtain missing value compensation data;

[0014] Performing monthly index conversion on the monthly data to obtain monthly conversion data;

[0015] The missing compensation data and the monthly conversion data constitute the pre-processing data.

[0016] In one embodiment, performing missing value processing on the daily data to obtain missing value compensation data includes:

[0017] Unify the time length of the financial market time series data to be processed, remove the data with inconsistent time periods for obtaining the financial market time series data to be processed, and obtain unified data;

[0018] Taking the trading day as the standard, the missing values ​​in the daily unified data are filled by linear interpolation to obtain the first filled data;

[0019] For the futures data in the daily unified data, adjust its price according to the expiration time to obtain the second filling data;

[0020] The first filling data and the second filling data constitute the missing filling data.

[0021] In one embodiment, the monthly data is converted into monthly indicators to obtain monthly converted data including:

[0022] Filling the monthly data to the entire release month to obtain monthly filled data;

[0023] The release lag time of the monthly data is obtained, and the monthly filling data is postponed according to the release lag time to obtain the monthly conversion data.

[0024] In one embodiment, dividing the preprocessed data according to a preset time scale to obtain grouped data includes:

[0025] The preset time scales are: 10 working days, 20 working days, 40 working days, 60 working days and 120 working days.

[0026] In one embodiment, constructing features according to the linear regression parameters according to a preset dimension-upgrading ratio to obtain dimension-upgrading data, and selecting the data includes:

[0027] The preset dimension-upgrading ratio is:

[0028] 1Mstd / 1Mmean, 1Msteep / 1Mmean, 2Mstd / 2Mmean, 2Msteep

[0029] / 2Mmean, 2Wmean / 1Mmean, 2Wmean

[0030] / 2Mmean, 2Wmean / 3Mmean, 2Wmean / 6Mmean, 2Wstd

[0031] / 2Wmean, 2Wsteep

[0032] / 2Wmean,

[0033] Among them, std represents standard deviation, steep represents slope, mean represents mean, M represents monthly data, and W represents weekly data.

[0034] A system for upgrading the dimension of financial time series data feature engineering variables, used to implement the method for upgrading the dimension of financial time series data feature engineering variables as described above, comprising:

[0035] A data acquisition module, used to acquire the financial market time series data to be processed, and preprocess the financial market time series data to be processed to obtain preprocessed data; wherein the financial market time series data to be processed includes daily data and monthly data;

[0036] A region division module, used for dividing the pre-processed data according to a preset time scale to obtain grouped data;

[0037] A parameter calculation module, used to perform linear regression parameter calculation on the grouped data to obtain linear regression parameters; wherein the linear regression parameters include: mean value, standard deviation and slope;

[0038] The feature dimension-increasing module is used to construct features according to the linear regression parameters according to the preset dimension-increasing ratio, obtain dimension-increasing data, and select the data.

[0039] A device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of a method for variable dimension enhancement of feature engineering of financial time series data described in the above-mentioned embodiments are implemented.

[0040] A storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for increasing the dimension of a variable in feature engineering of financial time series data described in each of the above embodiments.

[0041] Compared with the prior art, the advantages and beneficial effects of the present invention are: the present invention can introduce efficient data preprocessing and feature engineering methods, optimize the data processing process, and ensure that information with practical value can be identified and obtained from massive market data. It improves the depth and accuracy of data analysis and can provide a reliable basis for strategic decision-making, thereby enhancing competitiveness and flexibility in a dynamic market environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of a flow chart of a method for increasing the dimension of a feature engineering variable of financial time series data in one embodiment;

[0043] Figure 2 A schematic diagram of the structure of a system for upgrading the dimension of financial time series data feature engineering variables in one embodiment;

[0044] Figure 3 Schematic diagram of the internal structure of a device in one embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0046] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of this specification should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in one or more embodiments of this specification do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0047] In one embodiment, Figure 1 As shown, a method for increasing the dimension of feature engineering variables of financial time series data is provided, including the following steps:

[0048] Step S101, obtaining financial market time series data to be processed, and preprocessing the financial market time series data to be processed to obtain preprocessed data; wherein the financial market time series data to be processed includes daily data and monthly data.

[0049] On this basis, obtaining the time series data of financial markets to be processed includes:

[0050] Get ready-to-process financial market time series data through a real-time API.

[0051] Specifically, determine the unprocessed financial market time series data that needs to be processed. Access the real-time API data interface, and use different interfaces for different regions. The unprocessed financial market time series data includes daily data obtained in units of days and monthly data obtained in units of months. Preprocess the obtained unprocessed financial market time series data to obtain preprocessed data.

[0052] On this basis, the financial market time series data to be processed is preprocessed to obtain preprocessed data including:

[0053] Performing missing value processing on the daily data to obtain missing value compensation data;

[0054] Performing monthly index conversion on the monthly data to obtain monthly conversion data;

[0055] The missing compensation data and the monthly conversion data constitute the pre-processing data.

[0056] Specifically, missing value processing is performed on daily data obtained in units of days, and monthly data obtained in units of months are converted into monthly indicators to obtain preprocessed data.

[0057] On this basis, the daily data is processed for missing values, and the missing value compensation data obtained include:

[0058] Unify the time length of the financial market time series data to be processed, remove the daily data with inconsistent time periods for obtaining the financial market time series data to be processed, and obtain unified data;

[0059] Taking the trading day as the standard, the missing values ​​in the daily unified data are filled by linear interpolation to obtain the first filled data;

[0060] For the futures data in the daily unified data, adjust its price according to the expiration time to obtain the second filling data;

[0061] The first filling data and the second filling data constitute the missing filling data.

[0062] Specifically, first unify the time length of the data, remove the daily data with inconsistent data acquisition time periods, take the trading day as the standard, and do not consider the difference in statutory holidays. For the missing values ​​in each daily data, use linear interpolation to fill in. For futures data, adjust its price according to the expiration date.

[0063] In order to unify domestic and foreign data (different countries have different holidays), the working days in the daily data are Monday to Friday, and holidays are also considered working days (for example, National Day on October 1st is Wednesday, which is also considered a working day), and the daily data of holidays are linearly filled.

[0064] On this basis, the monthly data is converted into monthly indicators, and the monthly conversion data obtained includes:

[0065] Filling the monthly data to the entire release month to obtain monthly filled data;

[0066] The release lag time of the monthly data is obtained, and the monthly filling data is postponed according to the release lag time to obtain the monthly conversion data.

[0067] Specifically, due to the existence of monthly data (monthly release) and usually a release lag of 1 to 2 months, when converted to daily data, the same value will fill the entire release month, and the data will be postponed by 1 to 2 months based on the lag to ensure the consistency of the timeline and the logic of the data.

[0068] Step S102, dividing the pre-processed data according to a preset time scale to obtain grouped data.

[0069] Specifically, the preprocessed data is divided according to a preset time scale.

[0070] On this basis, the pre-processed data is divided according to a preset time scale to obtain grouped data including:

[0071] The preset time scales are: 10 working days, 20 working days, 40 working days, 60 working days and 120 working days.

[0072] Specifically, the original preprocessed data is divided into 5 dimensions, namely 2 weeks (2W), i.e. 10 working days, 1 month (1M), i.e. 20 working days, 2 months (2M), i.e. 40 working days, 3 months (3M), i.e. 60 working days, and 6 months (6M), i.e. 120 working days.

[0073] The purpose of dividing data from different time scales is to better capture the regularity and changing trends of data in the time dimension. Short-term data (such as 2 weeks, 1 month) can capture high-frequency fluctuations in the market and short-term sentiment changes. Long-term data (such as March, June) can be used to analyze trends such as economic cycles and long-term changes in supply and demand.

[0074] Step S103, performing linear regression parameter calculation on the grouped data to obtain linear regression parameters; wherein the linear regression parameters include: mean value, standard deviation and slope.

[0075] Specifically, the grouped data divided by the time dimension is subjected to linear regression, and the mean, standard deviation, and slope of different time dimensions are calculated, for a total of 5*3=15 data dimensions. The mean represents the typical value of the period, that is, the current price benchmark, the standard deviation represents the degree of dispersion of the data, and represents the market sentiment, and the slope represents the overall trend of the market.

[0076] Step S104, constructing features according to the linear regression parameters and the preset dimension-increasing ratio, obtaining dimension-increasing data, and selecting the data.

[0077] Specifically, features are constructed through ratios to upgrade data dimensions, obtain upgraded data, obtain upgraded data from the data, and select the data.

[0078] On this basis, according to the linear regression parameters, features are constructed according to the preset dimension-upgrading ratio to obtain dimension-upgrading data, and the data is selected including:

[0079] The preset dimension-upgrading ratio is:

[0080] 1Mstd / 1Mmean, 1Msteep / 1Mmean, 2Mstd / 2Mmean, 2Msteep

[0081] / 2Mmean, 2Wmean / 1Mmean, 2Wmean

[0082] / 2Mmean, 2Wmean / 3Mmean, 2Wmean / 6Mmean, 2Wstd

[0083] / 2Wmean, 2Wsteep

[0084] / 2Wmean,

[0085] Among them, std represents standard deviation, steep represents slope, mean represents mean, M represents monthly data, and W represents weekly data.

[0086] Specifically, by constructing features through ratios, 14 feature dimension-enhancing methods were finally selected. The specific dimension-enhancing methods (feature engineering) are shown in Table 1:

[0087] Table 1 Schematic diagram of feature dimension upgrading method

[0088]

[0089] The present invention can introduce efficient data preprocessing and feature engineering methods, optimize the data processing process, and ensure that information with practical value can be identified and obtained from massive market data. The depth and accuracy of data analysis are improved, and a reliable basis can be provided for strategic decision-making, thereby enhancing its competitiveness and flexibility in a dynamic market environment. The feature engineering improves the mining ability of financial data, can effectively process diversified financial data, and improve the mining ability of hidden information. Dimensional processing can not only enhance its ability to capture nonlinear relationships, convert the nonlinear characteristics of data into an easily analyzable form in linear space, but also increase the dimension of data, reveal potential structures, and capture the complex relationships behind them. For high-dimensional data in financial markets, such as global economic indicators, market sentiment, changes in supply and demand, etc., new feature combinations are constructed through feature engineering, which can better reveal potential driving factors. Ultimately, data using this processing method can improve the prediction accuracy of the model, effectively enhance sensitivity to market dynamics, and help companies optimize decision-making.

[0090] It should be noted that the method of the embodiment of the present invention can be performed by a single device, such as a computer or a server. The method of this embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present invention, and the multiple devices will interact with each other to complete the described method.

[0091] It should be noted that some embodiments of the present invention are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present invention also provides a system for upgrading the dimension of feature engineering variables of financial time series data.

[0093] refer to Figure 2 The system for upgrading the dimension of financial time series data feature engineering variables comprises:

[0094] A data acquisition module, used to acquire the financial market time series data to be processed, and preprocess the financial market time series data to be processed to obtain preprocessed data; wherein the financial market time series data to be processed includes daily data and monthly data;

[0095] A region division module 201 is used to divide the pre-processed data according to a preset time scale to obtain grouped data;

[0096] The parameter calculation module 202 is used to perform linear regression parameter calculation on the grouped data to obtain linear regression parameters; wherein the linear regression parameters include: mean value, standard deviation and slope;

[0097] The feature dimension-increasing module 203 is used to construct features according to the linear regression parameters according to a preset dimension-increasing ratio, obtain dimension-increasing data, and select the data.

[0098] For the convenience of description, the above system is described by dividing it into various modules according to its functions. Of course, when implementing the present invention, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0099] The system of the above embodiment is used to implement a method for increasing the dimension of a feature engineering variable of financial time series data corresponding to any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0100] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for variable dimensionality increase of feature engineering of financial time series data as described in any of the above embodiments is implemented.

[0101] Figure 3 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0102] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0103] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0104] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0105] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0106] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0107] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0108] The electronic device of the above embodiment is used to implement a method for increasing the dimension of a feature engineering variable of financial time series data corresponding to any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0109] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present invention also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute a method for upgrading the dimension of feature engineering variables of financial time series data as described in any of the above embodiments.

[0110] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0111] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute a method for upgrading the dimension of feature engineering variables of financial time series data as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0112] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention (including the claims) is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0113] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0114] In addition, when specific details are set forth to describe exemplary embodiments of the present invention, it will be apparent to those skilled in the art that embodiments of the present invention may be implemented without these specific details or when these specific details are varied. Therefore, these descriptions should be considered illustrative rather than restrictive. Although the present invention has been described in conjunction with specific embodiments of the present invention, many replacements, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description.

[0115] The embodiments of the present invention are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for increasing the dimension of feature engineering variables of financial time series data, characterized in that: include: Acquire the financial market time series data to be processed, and preprocess the financial market time series data to be processed to obtain preprocessed data; wherein the financial market time series data to be processed includes daily data and monthly data; Dividing the preprocessed data according to a preset time scale to obtain grouped data; Calculating linear regression parameters for the grouped data to obtain linear regression parameters; wherein the linear regression parameters include: mean value, standard deviation and slope; According to the linear regression parameters, features are constructed according to preset dimensionality increase ratios to obtain dimensionality increase data, and the data are selected.

2. According to claim 1, a method for increasing the dimension of financial time series data feature engineering variables, characterized in that: The obtaining of the to-be-processed financial market time series data comprises: Get ready-to-process financial market time series data through a real-time API.

3. According to claim 1, a method for increasing the dimension of financial time series data feature engineering variables, characterized in that: The preprocessing of the to-be-processed financial market time series data to obtain preprocessed data comprises: Performing missing value processing on the daily data to obtain missing value compensation data; Performing monthly index conversion on the monthly data to obtain monthly conversion data; The missing compensation data and the monthly conversion data constitute the pre-processing data.

4. According to claim 3, a method for increasing the dimension of financial time series data feature engineering variables is characterized in that: The performing missing value processing on the daily data to obtain missing value compensation data comprises: Unify the time length of the financial market time series data to be processed, remove the daily data with inconsistent time periods for obtaining the financial market time series data to be processed, and obtain unified data; Taking the trading day as the standard, the missing values ​​in the daily unified data are filled by linear interpolation to obtain the first filled data; For the futures data in the daily unified data, adjust its price according to the expiration time to obtain the second filling data; The first filling data and the second filling data constitute the missing filling data.

5. According to claim 3, a method for increasing the dimension of financial time series data feature engineering variables, characterized in that: The monthly data is converted into monthly indicators to obtain monthly conversion data including: Filling the monthly data to the entire release month to obtain monthly filled data; The release lag time of the monthly data is obtained, and the monthly filling data is postponed according to the release lag time to obtain the monthly conversion data.

6. According to claim 1, a method for increasing the dimension of financial time series data feature engineering variables, characterized in that: The dividing the pre-processed data according to a preset time scale to obtain grouped data comprises: The preset time scales are: 10 working days, 20 working days, 40 working days, 60 working days and 120 working days.

7. According to claim 1, a method for increasing the dimension of financial time series data feature engineering variables, characterized in that: The step of constructing features according to the linear regression parameters and the preset dimension-upgrading ratio to obtain dimension-upgrading data includes: The preset dimension-upgrading ratio is: 1Mstd / 1Mmean, 1Msteep / 1Mmean, 2Mstd / 2Mmean, 2Msteep / 2Mmean, 2Wmean / 1Mmean, 2Wmean / 2Mmean, 2Wmean / 3Mmean, 2Wmean / 6Mmean, 2Wstd / 2Wmean, 2Wsteep / 2Wmean、3Mstd / 3Mmean、3Msteep / 3Mmean、6Mstd / 6Mmean、6Msteep / 6Mmean Among them, std represents standard deviation, steep represents slope, mean represents mean, M represents monthly data, and W represents weekly data.

8. A system for increasing the dimension of feature engineering variables of financial time series data, characterized in that: A method for implementing a variable dimension upgrade for feature engineering of financial time series data as described in any one of claims 1 to 7, comprising: A data acquisition module, used to acquire the financial market time series data to be processed, and preprocess the financial market time series data to be processed to obtain preprocessed data; wherein the financial market time series data to be processed includes daily data and monthly data; A region division module, used for dividing the pre-processed data according to a preset time scale to obtain grouped data; A parameter calculation module, used to perform linear regression parameter calculation on the grouped data to obtain linear regression parameters; wherein the linear regression parameters include: mean value, standard deviation and slope; The feature dimension-increasing module is used to construct features according to the linear regression parameters according to the preset dimension-increasing ratio, obtain dimension-increasing data, and select the data.

9. A device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: 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 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