Abnormal financial data prediction method and device based on time series and electronic equipment

Through the time series-based anomaly financial data prediction method, using deep learning models to process the complexity and nonlinear characteristics of financial data, the problems of low efficiency and large error in financial data analysis are solved, and efficient and accurate finance are achieved Data prediction.

CN119025578AInactive Publication Date: 2024-11-26EASY CREDIT (XIAMEN) CREDIT SERVICE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411495813.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-25
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional financial data analysis methods are difficult to deal with the complexity, nonlinearity and dynamic variability of financial data, and rely on manual intervention, resulting in low efficiency and large errors.

Method used

Using an abnormal financial data prediction method based on time series, the abnormal financial data is obtained and preprocessed, and the abnormal financial data prediction model is used, combined with the deep learning model of unsupervised learning, to process the complexity and nonlinear characteristics of financial data to reduce manual intervention. Improve the efficiency and accuracy of data processing.

Benefits of technology

It significantly improves the accuracy of financial data prediction, is suitable for efficient processing of massive financial data, reduces manual intervention and error, and can effectively capture nonlinear and dynamic changes of data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119025578A_ABST
    Figure CN119025578A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of financial data analysis, and discloses an abnormal financial data prediction method and device based on a time series and electronic equipment, and the method comprises the steps: obtaining financial data based on the time series, and carrying out the preprocessing of the financial data, and obtaining the preprocessed financial data; and inputting the preprocessed financial data into an abnormal financial data prediction model, respectively obtaining a prediction result at the current moment and a prediction result at the previous moment of the current moment, and determining abnormal financial data based on the prediction result at the current moment and the prediction result at the previous moment. The complexity, nonlinearity and dynamic variability of financial data can be processed, the efficiency and accuracy of data processing are improved, manual intervention is reduced, and errors are reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of financial data analysis, and in particular to a method, device and electronic device for predicting abnormal financial data based on time series. Background Art

[0002] With the rapid development of financial markets and the explosive growth of data volume, traditional financial data analysis methods face major challenges. The complexity, nonlinearity and dynamic variability of financial data require analytical tools to not only be able to handle large-scale data sets, but also be able to capture subtle changes and potential patterns in the data. Traditional financial analysis methods usually rely on statistical principles, such as mean regression, variance analysis, cointegration analysis, etc. These methods perform well when dealing with relatively simple linear relationships, but their limitations become apparent in the face of the nonlinearity and complexity of financial markets. In addition, traditional methods often require human intervention and expertise to interpret the results, which is not only time-consuming but may also introduce subjective biases. Time series analysis is another important tool in the financial field for predicting anomalies in financial data. It includes techniques such as ARIMA models and seasonal decomposition, which can capture the time dependence and periodicity of data. However, time series analysis usually assumes that the data has a certain degree of stationarity, which is often not true in the rapid changes of financial data.

[0003] In view of this, this application is filed. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a method, device, electronic device and storage medium for predicting abnormal financial data based on time series, which can handle the complexity, nonlinearity and dynamic variability of financial data, improve the efficiency and accuracy of data processing, reduce human intervention, and reduce errors.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for predicting abnormal financial data based on time series, the method comprising: Acquiring financial data based on time series, and preprocessing the financial data to obtain preprocessed financial data; Inputting the preprocessed financial data into the abnormal financial data prediction model to obtain the prediction result at the current moment and the prediction result at the moment before the current moment, respectively, wherein the preprocessed financial data includes the preprocessed financial data at the current moment and the preprocessed financial data at the moment before the current moment; Abnormal financial data is determined based on the prediction result at the current moment and the prediction result at a moment before the current moment.

[0006] In a second aspect, the embodiments of the present disclosure further provide a device for predicting abnormal financial data based on time series, the device comprising: A first acquisition module, used to acquire financial data based on time series, and preprocess the financial data to obtain preprocessed financial data; A second acquisition module is used to input the preprocessed financial data into the abnormal financial data prediction model to obtain the prediction result at the current moment and the prediction result at the previous moment of the current moment, respectively, wherein the preprocessed financial data includes the preprocessed financial data at the current moment and the preprocessed financial data at the previous moment of the current moment; The third determination module is used to determine abnormal financial data based on the prediction result at the current moment and the prediction result at the previous moment of the current moment.

[0007] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the abnormal financial data prediction method based on time series as described above.

[0008] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the abnormal financial data prediction method based on time series as described above.

[0009] The abnormal financial data prediction method based on time series provided by the embodiment of the present disclosure pre-processes the financial data using the first formula to obtain pre-processed financial data, which can significantly improve the accuracy of abnormal financial data prediction while removing noise. Then, based on the abnormal financial data prediction model, the prediction results at different times are obtained, and the prediction results at different times are compared to determine the abnormal financial data. The abnormal financial data prediction model can handle the complexity, nonlinearity and dynamic variability of financial data, is suitable for efficient processing of massive financial data, improves the efficiency and accuracy of data processing, reduces manual intervention, and reduces errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0011] Figure 1 The present invention is a flowchart of a method for predicting abnormal financial data based on time series in an embodiment of the present invention.

[0012] Figure 2 Schematic diagram of the structure of an abnormal financial data prediction device based on time series in an embodiment of the present disclosure; Figure 3 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0014] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0015] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0016] Time series data is the core of financial data analysis. Although traditional time series prediction models, such as autoregressive moving average model and exponential smoothing method, can capture the trend and seasonality of data to a certain extent, they often show limitations when facing high-dimensional, nonlinear and noisy data, and are difficult to meet the needs of practical applications. Financial data often contains noise, which may affect the accuracy of the analysis results.

[0017] Secondly, traditional financial analysis methods, such as statistical prediction models and expert systems, often rely on the linear relationship and static characteristics of historical data, which makes it difficult for traditional analysis methods to effectively process these data. Financial data has nonlinear characteristics, and traditional linear models cannot accurately capture these characteristics. In this context, the introduction of unsupervised learning deep learning models provides a new path for the processing and analysis of financial data.

[0018] In response to the above problems, the embodiments of the present disclosure provide an abnormal financial data prediction method based on time series, which can handle the complexity, nonlinearity and dynamic variability of financial data, improve the efficiency and accuracy of data processing, reduce human intervention, and reduce errors.

[0019] Figure 11 is a flowchart of a method for predicting abnormal financial data based on time series in an embodiment of the present disclosure. The method can be executed by a device for predicting abnormal financial data based on time series, which can be implemented in software and / or hardware, and can be configured in an electronic device. Figure 1 As shown, the method may specifically include the following steps: S110: Acquire financial data based on time series, and preprocess the financial data to obtain preprocessed financial data.

[0020] Specifically, time series refers to various financial data with time sequence. For example, time series can be expressed from 0, 1...t time, and financial data based on time series, that is, various financial data corresponding to time 0, various financial data corresponding to time 1, until various financial data corresponding to time t. Among them, various time series financial data of the financial market can be collected through public financial market databases, exchanges, financial news websites and other channels.

[0021] In one embodiment, preprocessing the financial data to obtain preprocessed financial data includes: preprocessing the financial data using a first formula to obtain preprocessed financial data, wherein the first formula is expressed as: in, Indicates the current moment, Indicates the previous moment of the current moment. express Preprocess financial data at each moment, Represents the adjustable filter factor, Representing financial data The weight factor of represents the amount of preprocessed financial data, express Financial data at all times, express The standard deviation of financial data at a given moment, represents the probability density distribution function, Indicates the multiplication symbol.

[0022] In this embodiment, the weight factor can be used to give different importance to data at different time points, so that the data at certain key time points can make a greater contribution to the final result; the probability density distribution can be used to adjust the distribution characteristics of the data, which may be used to emphasize the kurtosis and skewness of the data; the standard deviation can be used to standardize the data, which helps to eliminate the influence of different dimensions and magnitudes; the adjustable filter factor can capture the cumulative effect of time series data, reflect the influence of historical data on current data, and at the same time reduce the impact of changes in financial data, improve data stability, and ensure the quality of financial data.

[0023] S120. Input the preprocessed financial data into an abnormal financial data prediction model to obtain a prediction result at the current moment and a prediction result at a moment before the current moment, respectively, wherein the preprocessed financial data includes the preprocessed financial data at the current moment and the preprocessed financial data at a moment before the current moment.

[0024] Specifically, based on the above embodiments, it can be known that the preprocessed financial data is also preprocessed financial data based on the time series, for example, it can be The preprocessed financial data corresponding to the time Taking the current moment as an example, we can know the preprocessed financial data at the current moment and the preprocessed financial data at the previous moment, that is, Preprocessed financial data at each moment and Preprocess financial data at each moment.

[0025] Among them, the expression of the abnormal financial data prediction model is:

[0026] in, express The prediction results at the time, represents the first hyperparameter of the abnormal financial data prediction model, represents the second hyperparameter of the abnormal financial data prediction model, represents the kernel function of the abnormal financial data prediction model, Indicates that the abnormal financial data prediction model is The weight parameter at the moment, Indicates that the abnormal financial data prediction model is The bias parameter at time, express Preprocessing financial data at the moment The hyperbolic tangent function of express Preprocessing financial data at the moment The radial basis function.

[0027] It can be understood that the abnormal financial data prediction model consists of an integral encoder model and a kernel function integral model. Among them, the integral encoder model can be expressed as: , the kernel function integral model can be expressed as: .

[0028] Then, Preprocessed financial data at each moment and The pre-processed financial data at each time point are input into the abnormal financial data prediction model, and we can get The prediction results at the time and The prediction results at time, where The expression of the prediction result at time is:

[0029] The expression of the prediction result at time is:

[0030] in, express The prediction results at the time, represents the first hyperparameter of the abnormal financial data prediction model, represents the second hyperparameter of the abnormal financial data prediction model, represents the kernel function of the abnormal financial data prediction model, Indicates that the abnormal financial data prediction model is The weight parameter at the moment, Indicates that the abnormal financial data prediction model is The bias parameter at time, express Preprocessing financial data at the moment The hyperbolic tangent function of express Preprocessing financial data at the moment The radial basis function, express The prediction results at the moment, express Preprocess financial data at each moment, Indicates that the abnormal financial data prediction model is The weight parameter at the moment, Indicates that the abnormal financial data prediction model is The bias parameter at time, express Preprocessing financial data at the moment The hyperbolic tangent function of express Preprocessing financial data at the moment The radial basis function.

[0031] The embodiment of the present invention can capture the nonlinear characteristics of data through the kernel function model, and the hyperparameters and weight parameters of the model provide flexibility in adjusting the model to adapt to different data characteristics. Through the integral encoder, it has the ability to predict multi-step time series to predict abnormal financial data trends.

[0032] It should be noted that the abnormal financial data prediction model is a model trained using the pre-processed financial data of different periods obtained in the above manner as samples.

[0033] S130. Determine abnormal financial data based on the prediction result at the current moment and the prediction result at the previous moment before the current moment.

[0034] In one implementation, the determining abnormal financial data based on the prediction result at the current moment and the prediction result at the previous moment of the current moment includes: Calculating the prediction result at the current moment and the prediction result at the previous moment of the current moment to obtain the difference of the prediction results; Based on the prediction result difference, abnormal financial data is determined.

[0035] Exemplarily, based on the above embodiment, Preprocessed financial data at each moment and The difference between the preprocessed financial data at each moment is taken as the prediction result difference, and its expression is:

[0036] in, Represents the difference in prediction results, express Preprocess financial data at each moment, express The prediction results at the time, express Preprocessing financial data at the moment The hyperbolic tangent function of Indicates that the abnormal financial data prediction model is The weight parameter at the moment, express Preprocessing financial data at the moment The radial basis function.

[0037] After obtaining the difference in the prediction results, the difference in the prediction results is input into the second formula to determine the abnormal financial data, wherein the expression of the second formula is:

[0038] in, Indicates abnormal financial data, express The standard deviation of the preprocessed financial data at time instant.

[0039] Abnormal financial data is determined by the second formula, and abnormal financial data usually refers to those financial data points that are significantly different from expected patterns or historical trends. In financial data analysis, abnormal data analysis helps regulators and financial institutions to better use financial data, and provide more accurate references for subsequent financial data operations by removing the impact of abnormal points.

[0040] This embodiment calculates The prediction results at time The difference in prediction results at different moments can identify the difference in predictions at adjacent time points, and further identify possible abnormal or sudden data in financial data.

[0041] The abnormal financial data prediction method based on time series provided by the present invention pre-processes financial data by adopting the first formula to obtain pre-processed financial data, which can significantly improve the accuracy of abnormal financial data prediction while removing noise. Then, based on the abnormal financial data prediction model, the prediction results at different times are obtained, and the prediction results at different times are compared to determine the abnormal financial data. The abnormal financial data prediction model can handle the complexity, nonlinearity and dynamic variability of financial data, is suitable for efficient processing of massive financial data, improves the efficiency and accuracy of data processing, reduces manual intervention, and reduces errors.

[0042] Figure 2 FIG. 1 is a schematic diagram of the structure of the abnormal financial data prediction device based on time series in the embodiment of the present disclosure. Figure 2 As shown: the device includes: a first acquisition module 210, a second acquisition module 220 and a third determination module 230.

[0043] The first acquisition module 210 is used to acquire financial data based on time series, and preprocess the financial data to obtain preprocessed financial data.

[0044] The second acquisition module 220 is used to input the preprocessed financial data into the abnormal financial data prediction model to obtain the prediction result at the current moment and the prediction result at the previous moment, respectively, wherein the preprocessed financial data includes the preprocessed financial data at the current moment and the preprocessed financial data at the previous moment.

[0045] The third determination module 230 is used to determine abnormal financial data based on the prediction result at the current moment and the prediction result at the previous moment before the current moment.

[0046] Optionally, the financial data is preprocessed to obtain preprocessed financial data, including: The financial data is preprocessed using a first formula to obtain preprocessed financial data, wherein the first formula is expressed as: in, Indicates the current moment, Indicates the previous moment of the current moment. express Preprocess financial data at each moment, Represents the adjustable filter factor, Representing financial data The weight factor of represents the number of preprocessed financial data, express Financial data at all times, express The standard deviation of financial data at a given moment, represents the probability density distribution function, Indicates the multiplication symbol.

[0047] Optionally, the expression of the abnormal financial data prediction model is:

[0048] in, express The prediction results at the moment, represents the first hyperparameter of the abnormal financial data prediction model, represents the second hyperparameter of the abnormal financial data prediction model, represents the kernel function of the abnormal financial data prediction model, Indicates that the abnormal financial data prediction model is The weight parameter at the moment, Indicates that the abnormal financial data prediction model is The bias parameter at time, express Preprocessing financial data at the moment The hyperbolic tangent function of express Preprocessing financial data at the moment The radial basis function.

[0049] Optionally, the determining abnormal financial data based on the prediction result at the current moment and the prediction result at a moment before the current moment includes: Calculating the prediction result at the current moment and the prediction result at the previous moment of the current moment to obtain the difference of the prediction results; Based on the prediction result difference, abnormal financial data is determined.

[0050] The expression of the prediction result difference is:

[0051] in, Represents the difference in prediction results, express Preprocess financial data at each moment, express The prediction results at the time, express Preprocessing financial data at the moment The hyperbolic tangent function of Indicates that the abnormal financial data prediction model is The weight parameter at the moment, express Preprocessing financial data at the moment The radial basis function.

[0052] Optionally, determining abnormal financial data based on the prediction result difference includes: The prediction result difference is input into the second formula to determine abnormal financial data, wherein the expression of the second formula is: ; in, Indicates abnormal financial data, express The standard deviation of the preprocessed financial data at time instant.

[0053] The abnormal financial data prediction device based on time series provided in the embodiment of the present disclosure can execute the steps in the abnormal financial data prediction method based on time series provided in the method embodiment of the present disclosure, and the execution steps and beneficial effects are no longer repeated here.

[0054] Figure 3 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 3 , which shows a structural schematic diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0055] like Figure 3As shown, the electronic device 500 may include a processing device 501, a ROM 502, a RAM 503, a bus 504, an input / output (I / O) interface 505, an input device 506, an output device 507, a storage device 508, and a communication device 509. The processing device (e.g., a central processing unit, a graphics processor, etc.) 501 can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage device 508 to the random access memory (RAM) 503 to implement the abnormal financial data prediction method based on time series as described in the embodiment of the present disclosure. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0056] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the abnormal financial data prediction method based on time series as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above functions defined in the method of the embodiment of the present disclosure are executed.

[0057] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0058] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains financial data based on time series, and preprocesses the financial data to obtain preprocessed financial data; inputs the preprocessed financial data into the abnormal financial data prediction model to obtain the prediction result at the current moment and the prediction result at the previous moment, respectively, wherein the preprocessed financial data includes the preprocessed financial data at the current moment and the preprocessed financial data at the previous moment; and determines the abnormal financial data based on the prediction result at the current moment and the prediction result at the previous moment.

[0059] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0060] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0061] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

Claims

1. The abnormal financial data prediction method based on time series is characterized by: The method comprises: Acquiring financial data based on time series, and preprocessing the financial data to obtain preprocessed financial data; Inputting the preprocessed financial data into the abnormal financial data prediction model to obtain the prediction result at the current moment and the prediction result at the moment before the current moment, respectively, wherein the preprocessed financial data includes the preprocessed financial data at the current moment and the preprocessed financial data at the moment before the current moment; Based on the prediction result at the current moment and the prediction result at the previous moment before the current moment, determining abnormal financial data, The preprocessing of the financial data to obtain preprocessed financial data includes: The financial data is preprocessed using a first formula to obtain preprocessed financial data, wherein the expression of the first formula is: in, Indicates the current moment, Indicates the previous moment of the current moment. express Preprocess financial data at each moment, Represents the adjustable filter factor, Representing financial data The weight factor of represents the amount of preprocessed financial data, express Financial data at all times, express The standard deviation of financial data at a given moment, represents the probability density distribution function, Indicates the multiplication symbol.

2. The method according to claim 1, characterized in that The expression of the abnormal financial data prediction model is: ; in, express The prediction results at the moment, represents the first hyperparameter of the abnormal financial data prediction model, represents the second hyperparameter of the abnormal financial data prediction model, represents the kernel function of the abnormal financial data prediction model, Indicates that the abnormal financial data prediction model is The weight parameter at the moment, Indicates that the abnormal financial data prediction model is The bias parameter at time, express Preprocessing financial data at the moment The hyperbolic tangent function of express Preprocessing financial data at the moment The radial basis function.

3. The method according to claim 2, characterized in that Determining abnormal financial data based on the prediction result at the current moment and the prediction result at the previous moment before the current moment includes: Calculating the prediction result at the current moment and the prediction result at the previous moment of the current moment to obtain the difference of the prediction results; Based on the prediction result difference, abnormal financial data is determined.

4. The method according to claim 3, characterized in that The expression of the difference in the prediction result is: ; in, Represents the difference in prediction results, express Preprocess financial data at each moment, express The prediction results at the moment, express Preprocessing financial data at the moment The hyperbolic tangent function of Indicates that the abnormal financial data prediction model is The weight parameter at the moment, express Preprocessing financial data at the moment The radial basis function.

5. The method according to claim 4, characterized in that Based on the prediction result difference, determining abnormal financial data includes: The prediction result difference is input into the second formula to determine abnormal financial data, wherein the expression of the second formula is: ; in, Indicates abnormal financial data, express The standard deviation of the preprocessed financial data at time instant.

6. The abnormal financial data prediction device based on time series is characterized by: The device comprises: A first acquisition module, used to acquire financial data based on time series, and preprocess the financial data to obtain preprocessed financial data; A second acquisition module is used to input the preprocessed financial data into the abnormal financial data prediction model to obtain the prediction result at the current moment and the prediction result at the previous moment of the current moment, respectively, wherein the preprocessed financial data includes the preprocessed financial data at the current moment and the preprocessed financial data at the previous moment of the current moment; The third determination module is used to determine abnormal financial data based on the prediction result at the current moment and the prediction result at the previous moment of the current moment.

7. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.