Fund fixed investment strategy determination method and device

Abstract

The invention relates to a fund fixed investment strategy determination method and device, and the method comprises the steps: screening funds invested in a first section, calculating the investment proportion of each fund in the first section, and screening sample funds representing the first section based on the investment proportion; the fixed investment yield and multiple quantitative indexes of each sample fund under different fixed investment frequencies are calculated, and the overall fixed investment yield and multiple quantitative indexes of the first plate under different fixed investment frequencies are calculated; obtaining a time sequence of multiple quantitative indexes of the first plate and a time sequence of fixed investment yield within the time T; a LightGBM training model is used, and the relation between historical data under the time window t and the fixed investment yield is obtained based on the time sequence; and according to the trained model, predicting the fixed investment yield of the first plate at the T + 1 moment based on historical data at the T-t + 1 moment. By screening sample funds, a model for more accurately predicting the fixed investment yield is trained according to multiple quantitative indexes, so that investors can more clearly know the profitable investment direction.

Description

Technical Field

[0001] The present invention relates to the field of machine learning technology, and in particular to a method and device for determining a fund fixed investment strategy. Background Art

[0002] A method and device for determining a fixed investment strategy for a fund (publication number CN116645217A) has been disclosed in the prior art, which can be applied to the fields of artificial intelligence and finance. By obtaining fixed investment strategy information, the combination data of fixed investment indicators and returns is determined according to the fixed investment strategy information; the prediction model is trained using GA and stacking according to the combination data; the return value set corresponding to the first product under different fixed investment strategies is predicted by combining the prediction model and the mean difference of similar products: the fixed investment strategy with the highest return value in the return value set is confirmed as the recommended strategy. Therefore, based on a large amount of historical fund transaction data in the system, GA and stacking integrated learning are integrated to efficiently recommend fund fixed investment strategies, and combined with the user's own risk-bearing capacity, the investment plan with the default optimal return is recommended to the user, and the investment plan is echoed to the front-end page, and the user can select the default setting with one click or adjust it according to his or her own preferences.

[0003] However, the independent variables used in training models in existing technologies are not diverse enough, the formulated fixed investment plans do not focus on areas of concern to investors, and the plans do not include recommendations on investment directions and portfolio adjustments. Summary of the invention

[0004] In order to address the deficiencies of the prior art, the present invention provides a method and device for determining a fund fixed investment strategy to help investors formulate a fund fixed investment strategy that is more focused on the areas of concern to investors, has a clearer investment direction, and is more suitable for the needs of investors.

[0005] To achieve the above objectives, the technical solutions adopted by the present invention include:

[0006] A method for determining a fixed investment strategy for a fund, characterized by comprising:

[0007] S1. Filter the investment fund set in the first section as {A1,…,A n}, calculate the investment proportion of each fund in the first sector as {P1,…,P n}, based on the investment ratio, select sample funds representing the first sector, and each sample fund is recorded as A i , where n is the number of funds invested in the first section and i is the fund index;

[0008] S2. Calculate the fixed investment rate of return {Y i,1 ,…,Y i,m}, m is the subscript of fixed investment frequency, set the weight ratio, and calculate the overall fixed investment yield of the first sector under different fixed investment frequencies {Y1,…,Y m};

[0009] S3. Calculate multiple quantitative indicators {X i,m,1 ,…,X i,m,k}, set the weight ratio, and calculate multiple quantitative indicators of the first sector {X m,1 ,…,X m,k}, where k is the subscript of the quantitative index;

[0010] S4. Add the time dimension to obtain the time series of multiple quantitative indicators of the first sector within time T as {X m,1,T ,…,X m,k,T}, the time series of the fixed investment yield of the first sector is {Y m,1,T ,…,Y m,k,T};

[0011] S5. Use LightGBM to train the model, use the Bayesian optimization algorithm to adjust the parameters, get the trained model, and obtain the historical data {X m,1,T-t ,…,X m,k,T-t} and fixed investment rate of return {Y m,1,T ,…,Y m,k,T}relationship;

[0012] S6. According to the trained model, based on the historical data {X 1,T-t+1 ,…,X m,T-t+1}For the fixed investment yield of the first sector at time T+1 {Y 1,T+1 ,…,Y m,T+1} Make predictions and obtain prediction data.

[0013] Furthermore, the screening of the funds invested in the first section includes:

[0014] Based on the industry classification standards, a penetration analysis is performed on the fund holdings, and the industries corresponding to the stocks held by the fund are mapped to the first sector, wherein the first sector includes one or more industries.

[0015] Furthermore, the screening of sample funds representing the first sector based on the investment ratio includes:

[0016] An investment ratio threshold is set, and funds whose investment ratio exceeds the investment ratio threshold are taken as sample funds. The sample funds can be used to represent the first sector.

[0017] Furthermore, the fixed investment frequency includes weekly, biweekly, monthly and quarterly, and the quantitative indicators include the fund's interval rate of return, standard deviation and Sharpe ratio.

[0018] Furthermore, the LightGBM training model further includes:

[0019] The Huber loss function is used as the loss function of the LightGBM model.

[0020] Furthermore, the method further comprises:

[0021] Make fixed investments based on the forecast data and historical data, and increase or decrease positions according to demand.

[0022] The present invention also relates to a device for determining a fund fixed investment strategy, which is characterized by comprising:

[0023] Fund screening module, used to screen the fund set invested in the first section as {A1,…,A n}, calculate the investment proportion of each fund in the first sector as {P1,…,P n}, based on the investment ratio, select sample funds representing the first sector, and each sample fund is recorded as A i , where n is the number of funds invested in the first section and i is the fund index;

[0024] The yield calculation module is used to calculate the fixed investment yield {Y i,1 ,…,Y i,m}, m is the subscript of fixed investment frequency, set the weight ratio, and calculate the overall fixed investment yield of the first sector under different fixed investment frequencies {Y1,…,Y m};

[0025] The quantitative index calculation module is used to calculate multiple quantitative indexes {X i,m,1 ,…,X i,m,k}, set the weight ratio, and calculate multiple quantitative indicators of the first sector {X m,1 ,…,X m,k}, where k is the subscript of the quantitative index;

[0026] The time series acquisition module is used to add a time dimension and obtain the time series of multiple quantitative indicators of the first sector within time T as {X m,1,T ,…,X m,k,T}, the time series of the fixed investment yield of the first sector is {Y m,1,T ,…,Y m,k,T};

[0027] The model training module is used to train the model using LightGBM, adjust the parameters using the Bayesian optimization algorithm, obtain the trained model, and obtain historical data {X m,1,T-t ,…,X m,k,T-t} and fixed investment rate of return {Y m,1,T ,…,Y m,k,T}relationship;

[0028] The model using module is used to use the trained model based on the historical data {X 1,T-t+1 ,…,X m,T-t+1}For the fixed investment yield of the first sector at time T+1 {Y 1,T+1 ,…,Y m,T+1} Make predictions and obtain prediction data.

[0029] The present invention also relates to a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and the computer program implements the above method when executed by a processor.

[0030] The present invention also relates to an electronic device, characterized in that it comprises a processor and a memory;

[0031] The memory is used to store program instructions;

[0032] The processor is used to execute the above method by calling program instructions.

[0033] The present invention also relates to a computer program product, comprising a computer program and / or instructions, characterized in that the computer program and / or instructions implement the steps of the above method when executed by a processor.

[0034] The beneficial effects of the present invention are:

[0035] The method and device for determining a fixed investment strategy for a fund described in the present invention are used to screen representative fund samples of industries or sectors, construct multiple quantitative indicators of industries or sectors, and improve the accuracy of model prediction. The present invention provides a complete mechanism for determining a fixed investment strategy for a fund through demand analysis, fund screening, quantitative indicator calculation, LightGBM model training, Bayesian optimization parameter adjustment, etc., to help users focus on areas of concern to investors, clarify profitable investment directions, and facilitate users to further adjust fixed investment positions in a timely manner in combination with other market indicators. Based on historical data and with reference to forecast data, users can choose sectors with higher fixed investment yields for investment, and adjust positions in a timely manner according to the market to meet investor needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0037] Figure 1 A schematic diagram of a method for determining a fixed investment strategy for a fund according to the present invention;

[0038] Figure 2 This is a schematic diagram of the structure of a device for determining a fixed investment strategy for a fund according to the present invention;

[0039] Figure 3 The figure is a schematic structural diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. It should be understood that the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments, and these embodiments are only used to illustrate the present application and are not used to limit the scope of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0041] like Figure 1 As shown, the embodiment of the present invention discloses a method for determining a fixed investment strategy for a fund, and the steps of the method include:

[0042] S1. Filter the investment fund set in the first section as {A1,…,A n}, calculate the investment proportion of each fund in the first sector as {P1,…,P n}, based on the investment ratio, select sample funds representing the first sector, and each sample fund is recorded as A i , where n is the number of funds invested in the first section and i is the fund index.

[0043] Specifically, the funds invested in the first section are screened, including:

[0044] Based on the industry classification standards, a penetration analysis is performed on the fund holdings, and the industries corresponding to the stocks held by the fund are mapped to the first sector, wherein the first sector includes one or more industries.

[0045] Based on the investment ratio, sample funds representing the first sector are selected, including:

[0046] An investment ratio threshold is set, and funds whose investment ratio exceeds the investment ratio threshold are taken as sample funds. The sample funds can be used to represent the first sector.

[0047] S2. Calculate the fixed investment rate of return {Y i,1 ,…,Y i,m}, m is the subscript of fixed investment frequency, set the weight ratio, and calculate the overall fixed investment yield of the first sector under different fixed investment frequencies {Y1,…,Y m}.

[0048] Specifically, the fixed investment frequency may include weekly, biweekly, monthly, and quarterly.

[0049] S3. Calculate multiple quantitative indicators {X i,m,1 ,…,X i,m,k}, set the weight ratio, and calculate multiple quantitative indicators of the first sector {X m,1 ,…,X m,k}, where k is the subscript of the quantitative index.

[0050] Specifically, quantitative indicators may include the fund's interval return, standard deviation, and Sharpe ratio.

[0051] S4. Add the time dimension to obtain the time series of multiple quantitative indicators of the first sector within time T as {X m,1,T ,…,X m,k,T}, the time series of the fixed investment yield of the first sector is {Y m,1,T ,…,Y m,k,T}.

[0052] S5. Use LightGBM to train the model, use the Bayesian optimization algorithm to adjust the parameters, get the trained model, and obtain the historical data {X m,1,T-t ,…,X m,k,T-t} and fixed investment rate of return {Y m,1,T ,…,Y m,k,T}relationship.

[0053] Preferably, the LightGBM training model is used, further comprising:

[0054] The Huber loss function is used as the loss function of the LightGBM model. The formula of the Huber loss function is as follows:

[0055]

[0056] Huber loss is essentially an absolute error, and only when the error is small does it become a square error. The critical value of the judgment error is controlled by the hyperparameter δ. The selection of this parameter is very critical and determines how the model determines anomalies. This way of calculating the error effectively avoids the problem that the MSE loss function is sensitive to abnormal data and the MAE loss function derivative has a low discontinuous solution rate, so it is also called the smoothed mean absolute error. In addition, the volatility of the financial market is high, and there are many factors affecting the market. Therefore, the independent variable indicators in the model cannot cover all factors that will affect the market. In this case, it is very necessary to eliminate data that is too abnormal. In the fixed investment plan, investors disperse the risk of concentrated investment by investing in fixed amounts in installments, so it does not need to be very precise. Therefore, the prediction model for the fixed investment rate of return can bring greater benefits to investors as long as it can accurately predict the rate of return in most cases. In the fund fixed investment strategy determination plan, there is no need to pay too much attention to abnormal data. Excessive attention to abnormal data may affect the model's judgment of most cases. However, when using the Huber loss function to train the model, it is still necessary to continuously adjust the hyperparameter δ to train a model that is more in line with the fixed investment rate of return prediction scenario.

[0057] S6. According to the trained model, based on the historical data {X 1,T-t+1 ,…,X m,T-t+1}For the fixed investment yield of the first sector at time T+1 {Y 1,T+1 ,…,Y m,T+1} Make predictions and obtain prediction data.

[0058] Specifically, the method further includes:

[0059] Make fixed investments based on the forecast data and historical data, and increase or decrease positions according to demand.

[0060] In particular, the present invention can predict the fixed investment yield of other sectors according to the above steps. Investors analyze the predicted data based on historical data and can choose sectors with higher fixed investment yields for investment in combination with their own investment needs. At the same time, investors can further refer to the market heat index and make fixed investment increases and decreases in the selected investment direction according to demand. Generally, when the market heat is high, the position can be appropriately reduced, and when the market heat is low, the position can be appropriately increased. An embodiment of the present invention provides a method for determining a fund fixed investment strategy, which uses a model to help investors formulate a fund fixed investment strategy that focuses more on the areas of concern of investors, clarifies the investment direction, and is more suitable for the needs of investors.

[0061] Embodiment 1

[0062] Step 1. According to the current market analysis needs, determine the sectors or industries that need to be studied. Assuming that sector A is the focus of this analysis, based on the Shenwan first-level industry classification standards, select funds that invest in sector A from equity-oriented funds. This screening process requires a penetrating analysis of the fund holdings, and maps the Shenwan first-level industries corresponding to the stocks held to the corresponding sectors. Sectors usually include one or more industries. Assume that the set of all funds that have investments in sector A is {A1,…,A n}, calculate the investment proportion of each fund in sector A as {P1,…,P n}, where n represents the number of funds invested in sector A.

[0063] The investment ratio threshold is set to 50%, and the funds with investment ratio P ≥ 50% are used as sample funds for sector A. In order to simplify the embodiment for easier understanding, it is assumed in this embodiment that three funds are selected as sample funds representing sector A, namely A1, A2, and A3.

[0064] Step 2: Calculate the fixed investment yields {Y i,1 ,…,Y i,m}, where i is the fund index and m is the fixed investment frequency index. In this embodiment, equal weights are used to further calculate the overall fixed investment yield of sector A at different fixed investment frequencies {Y1,…,Y m}, as shown in Table 1.

[0065] Table 1

[0066]

[0067]

[0068] Step 3: The quantitative indicators used as independent variables can be the interval rate of return, standard deviation, and Sharpe ratio of the fund. In order to simplify the embodiment for easy understanding, in this embodiment, only the standard deviation is selected as the independent variable for this model training, and the standard deviation of the sample funds A1, A2, and A3 under the fixed investment frequency m (weekly, biweekly, monthly, and quarterly) is calculated. In this embodiment, equal weights are used to further calculate the standard deviation of the A sector in the week, biweekly, monthly, and quarter, as shown in Table 2.

[0069] Table 2

[0070]

[0071] Step 4: Add the time dimension to steps 3 and 4. At time T, the time series of the standard deviation of plate A {X 周,stddev,T ,X 双周,stddev,T ,X 月,stddev,T ,X 季,stddev,T} and the time series of fixed investment yield of sector A {Y 周,stddev,T ,Y 双周,stddev,T ,Y 月,stddev,T ,Y 季,stddev,T}.

[0072] Step 5: Use LightGBM to train the model and explore the historical data of the independent variable {X m,1,T-t ,…,X m,k,T-t} and fixed investment rate of return {Y m,1,T ,…,Y m,k,T}relationship.

[0073] During training, the Huber loss function is selected as the loss function of the LightGBM model. The formula of the Huber loss function is as follows:

[0074]

[0075] When training the model, you can use δ=1.35 as the starting parameter. At this time, the loss function satisfies the Gaussian distribution, and the time window can start from t=1 to find the t with the best prediction effect. Use the Bayesian optimization algorithm to efficiently find the parameter combination with excellent performance.

[0076] Step 6: Based on the trained model, the historical data of the independent variable indicator {X 1,T-t+1 ,…,X m,T-t+1}For the fixed investment yield of the first sector at time T+1 {Y 1,T+1 ,…,Y m,T+1} to make predictions.

[0077] Step 7: Repeat steps 1-7 for sectors B and C to obtain a training model suitable for each sector, and predict the fixed investment yield of each sector at time T+1. Investors can determine the sector with higher yields based on historical data and predicted fixed investment yields of each sector and investment needs.

[0078] Additionally, investors can further refer to the market heat index and increase or decrease their positions according to their needs. If the market heat index is high, the current fixed investment can be appropriately reduced, and when the market heat is low, the current fixed investment can be appropriately increased. For example, in this embodiment, when the market temperature is greater than 50 degrees, the position is reduced by 20%, and when the market temperature is less than 50 degrees, the position is increased by 10%.

[0079] like Figure 2 As shown, the embodiment of the present invention discloses a device for determining a fixed investment strategy for a fund, and its structure includes:

[0080] Fund screening module, used to screen the fund set invested in the first section as {A1,…,A n}, calculate the investment proportion of each fund in the first sector as {P1,…,P n}, based on the investment ratio, select sample funds representing the first sector, and each sample fund is recorded as A i , where n is the number of funds invested in the first section and i is the fund index;

[0081] The yield calculation module is used to calculate the fixed investment yield {Y i,1 ,…,Y i,m}, m is the subscript of fixed investment frequency, set the weight ratio, and calculate the overall fixed investment yield of the first sector under different fixed investment frequencies {Y1,…,Y m};

[0082] The quantitative index calculation module is used to calculate multiple quantitative indexes {X i,m,1 ,…,X i,m,k}, set the weight ratio, and calculate multiple quantitative indicators of the first sector {X m,1 ,…,X m,k}, where k is the subscript of the quantitative index;

[0083] The time series acquisition module is used to add a time dimension and obtain the time series of multiple quantitative indicators of the first sector within time T as {X m,1,T ,…,X m,k,T}, the time series of the fixed investment yield of the first sector is {Y m,1,T ,…,Y m,k,T};

[0084] The model training module is used to train the model using LightGBM, adjust the parameters using the Bayesian optimization algorithm, obtain the trained model, and obtain historical data {X m,1,T-t ,…,X m,k,T-t} and fixed investment rate of return {Y m,1,T ,…,Y m,k,T}relationship;

[0085] The model using module is used to use the trained model based on the historical data {X 1,T-t+1 ,…,X m,T-t+1}For the fixed investment yield of the first sector at time T+1 {Y 1,T+1 ,…,Y m,T+1} Make predictions and obtain prediction data.

[0086] By using this device, the above-mentioned calculation processing method can be executed and the corresponding technical effects can be achieved.

[0087] An embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the method in the above embodiment, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps in the method in the above embodiment are implemented.

[0088] The embodiment of the present invention further provides an electronic device for executing the above method, as a device for implementing the method, and its structure is as follows: Figure 3 As shown, the electronic device 300 includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one. It is understandable that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the specific structure of the electronic device 300. In other embodiments of the present application, the electronic device 300 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware. Optionally, the electronic device may also include a display screen 305 for displaying images, or receiving user operation instructions when necessary.

[0089] The processor 301 is applied in the embodiment of the present application to implement the method shown in the above method embodiment. The transceiver 304 may include a receiver and a transmitter. The transceiver 304 is applied in the embodiment of the present application to implement the function of the electronic device of the embodiment of the present application communicating with other devices when executed.

[0090] Processor 301 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0091] The processor 301 may also include one or more processing units, for example, the processor 301 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processor (NPU). Among them, different processing units may be independent devices or integrated into one or more processors. Among them, the controller may be the nerve center and command center of the electronic device 300. The controller may generate an operation control signal according to the instruction opcode and the timing signal to complete the control of fetching and executing instructions. A memory may also be set in the processor 301 for storing instructions and data. In some embodiments, the memory in the processor 301 is a high-speed cache memory. The memory may store instructions or data that the processor 301 has just used or circulated. If the processor 301 needs to use the instruction or data again, it may be directly called from the memory. Repeated access is avoided, the waiting time of the processor 301 is reduced, and the efficiency of the system is improved.

[0092] The processor 301 can run the method provided in the embodiment of the present application. The processor 301 can include different devices. For example, when a CPU and a GPU are integrated, the CPU and the GPU can cooperate to execute the method provided in the embodiment of the present application, for example, part of the algorithm in the method is executed by the CPU, and another part of the algorithm is executed by the GPU to obtain faster processing efficiency.

[0093] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0094] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or may include a high-speed random access memory, or may include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0095] Optionally, the memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the method provided in any embodiment of the present application.

[0096] The memory 303 can be used to store computer executable program codes, which include instructions. The processor 301 executes various functional applications and data processing of the electronic device 300 by running the instructions stored in the memory 303. The memory 303 may include a program storage area and a data storage area. Among them, the program storage area may store the code of the operating system, application program, etc. The data storage area may store data created during the use of the electronic device 300 (such as images, videos, etc. collected by the camera application), etc.

[0097] The memory 303 may also store one or more computer programs corresponding to the method provided in the embodiment of the present application. The one or more computer programs are stored in the above-mentioned memory 303 and are configured to be executed by the one or more processors 301. The one or more computer programs include instructions, and the above-mentioned instructions can be used to execute each step in the above-mentioned corresponding embodiment.

[0098] Of course, the code of the method provided in the embodiment of the present application can also be stored in an external memory. In this case, the processor 301 can run the code of the method stored in the external memory through the external memory interface, and the processor 301 can control the running process.

[0099] The display screen 305 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 300 may include 1 or N display screens 305, where N is a positive integer greater than 1. The display screen 305 can be used to display information input by a user or information provided to a user and various graphical user interfaces (GUI). For example, the display screen 305 can display photos, videos, web pages, or files.

[0100] The electronic device provided in the embodiment of the present application is applicable to any embodiment of the above method. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, which will not be repeated here.

[0101] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0103] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0105] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for determining a fixed investment strategy for a fund, characterized in that: include: S1. Filter the investment fund set in the first section as {A1,…,A n }, calculate the investment proportion of each fund in the first sector as {P1,…,P n }, based on the investment ratio, select sample funds representing the first sector, and each sample fund is recorded as A i , where n is the number of funds invested in the first section and i is the fund index; S2. Calculate the fixed investment rate of return {Y i,1 ,…,Y i,m }, m is the subscript of fixed investment frequency, set the weight ratio, and calculate the overall fixed investment yield of the first sector under different fixed investment frequencies {Y1,…,Y m }; S3. Calculate multiple quantitative indicators {X i,m,1 ,…,X i,m,k }, set the weight ratio, and calculate multiple quantitative indicators of the first sector {X m,1 ,…,X m,k }, where k is the subscript of the quantitative index; S4. Add the time dimension to obtain the time series of multiple quantitative indicators of the first sector within time T as {X m,1,T ,…,X m,k,T }, the time series of the fixed investment yield of the first sector is {Y m,1,T ,…,Y m,k,T }; S5. Use LightGBM to train the model, use the Bayesian optimization algorithm to adjust the parameters, get the trained model, and obtain the historical data {X m,1,T-t ,…,X m,k,T-t } and fixed investment rate of return {Y m,1,T ,…,Y m,k,T }relationship; S6. According to the trained model, based on the historical data {X 1,T-t+1 ,…,X m,T-t+1 }For the fixed investment yield of the first sector at time T+1 {Y 1,T+1 ,…,Y m,T+1 } Make predictions and obtain prediction data.

2. The method according to claim 1, characterized in that The funds invested in the first section of the screening include: Based on the industry classification standards, a penetration analysis is performed on the fund holdings, and the industries corresponding to the stocks held by the fund are mapped to the first sector, where the first sector includes one or more industries.

3. The method according to claim 1, characterized in that The screening of sample funds representing the first sector based on the investment ratio includes: An investment ratio threshold is set, and funds whose investment ratio exceeds the investment ratio threshold are taken as sample funds. The sample funds can be used to represent the first sector.

4. The method according to claim 1, characterized in that The fixed investment frequency includes weekly, biweekly, monthly and quarterly, and the quantitative indicators include the fund's interval rate of return, standard deviation and Sharpe ratio.

5. The method according to claim 1, characterized in that The LightGBM training model also includes: The Huber loss function is used as the loss function of the LightGBM model.

6. The method according to claim 1, characterized in that The method further comprises: Make fixed investments based on the forecast data and historical data, and increase or decrease positions according to demand.

7. A device for determining a fixed investment strategy for a fund, characterized in that: include: Fund screening module, used to screen the fund set invested in the first section as {A1,…,A n }, calculate the investment proportion of each fund in the first sector as {P1,…,P n }, based on the investment ratio, select sample funds representing the first sector, and each sample fund is recorded as A i , where n is the number of funds invested in the first section and i is the fund index; The yield calculation module is used to calculate the fixed investment yield {Y i,1 ,…,Y i,m }, m is the subscript of fixed investment frequency, set the weight ratio, and calculate the overall fixed investment yield of the first sector under different fixed investment frequencies {Y1,…,Y m }; The quantitative index calculation module is used to calculate multiple quantitative indexes {X i,m,1 ,…,X i,m,k }, set the weight ratio, and calculate multiple quantitative indicators of the first sector {X m,1 ,…,X m,k }, where k is the subscript of the quantitative index; The time series acquisition module is used to add a time dimension and obtain the time series of multiple quantitative indicators of the first sector within time T as {X m,1,T ,…,X m,k,T }, the time series of the fixed investment yield of the first sector is {Y m,1,T ,…,Y m,k,T }; The model training module is used to train the model using LightGBM, adjust the parameters using the Bayesian optimization algorithm, obtain the trained model, and obtain historical data {X m,1,T-t ,…,X m,k,T-t } and fixed investment rate of return {Y m,1,T ,…,Y m,k,T }relationship; The model using module is used to use the trained model based on the historical data {X 1,T-t+1 ,…,X m,T-t+1 }For the fixed investment yield of the first sector at time T+1 {Y 1,T+1 ,…,Y m,T+1 } Make predictions and obtain prediction data.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store program instructions; The processor is configured to execute the method according to any one of claims 1 to 6 by calling program instructions.

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

Images