WO2019205384A1

WO2019205384A1 - Electronic device, machine learning-based stock trade timing method and storage medium

Info

Publication number: WO2019205384A1
Application number: PCT/CN2018/102224
Authority: WO
Inventors: 李正洋; 周璟
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-04-26
Filing date: 2018-08-24
Publication date: 2019-10-31
Also published as: CN108764291A

Abstract

Disclosed by the present application are an electronic device, a machine learning-based stock trade timing method and a storage medium, the method comprising: first, acquiring a preset type of index factor corresponding to a predetermined stock market index on each trading day within a preset time period; next, analyzing the acquired preset type of index factor of each trading day respectively according to a completely pre-trained timing strategy analysis model so as to output a trend factor value corresponding to each trading day; then, performing clustering analysis on the trend factor value corresponding to each trading day according to a predetermined clustering algorithm so as to obtain a trend type corresponding to the trend factor value for each trading day; and finally, according to the obtained trend type corresponding to the trend factor value of each trading day, determining a trade timing strategy. Thus, the efficiency and accuracy of stock trade timing are improved.

Description

Electronic device, machine learning-based stock timing method and storage medium

This application claims the priority of the Chinese Patent Application entitled "Electronic Device, Machine Learning-Based Stock Timing Method and Storage Medium" submitted by the Chinese Patent Office on April 26, 2018, with the application number 2018103871394. This is incorporated herein by reference.

Technical field

The present application relates to the field of financial market analysis, and in particular, to an electronic device, a machine learning-based stock timing method, and a storage medium.

Background technique

With the continuous improvement and development of financial markets and financial theory, stock quantitative investment has become a favorable factor for many financial institutions to attract stock investors. At present, the research on stock quantitative investment is mainly based on timing trading. The timing trading refers to using some method to judge the investment target, such as stocks, futures, foreign exchange, etc., within a predetermined period of time, and according to the trend A means of trading that determines the point of sale. Usually, the analysis of stock timing trading requires professionals to study the corresponding trend timing indicators, such as stock trend timing indicators including MA (double moving average), DMA (average line difference), TRIX (triple index smooth movement). Such changes, and the timing of buying and selling transactions based on changes in timing indicators, there are problems of inefficiency and low accuracy.

Summary of the invention

In view of this, the present application proposes an electronic device, a machine learning-based stock timing method and a storage medium, which can improve the efficiency and accuracy of stock timing transaction analysis.

First, the present application provides an electronic device including a memory and a processor coupled to the memory, the processor for executing a machine learning based stock timing program stored on the memory, The machine learning-based stock timing program is executed by the processor to implement the following steps:

A10. Obtain a preset type indicator factor corresponding to each trading day of the predetermined stock market index within a preset time period;

A20. The preset type index factors of each acquired trading day are respectively analyzed according to the timing analysis strategy model completed by the pre-training, so as to output the trend factor values corresponding to each trading day;

A30. Perform cluster analysis on the trend factor values corresponding to each trading day according to a predetermined clustering algorithm to obtain a trend category corresponding to the trend factor value of each trading day;

A40. Determine a timing trading strategy according to the trend category corresponding to the obtained trend factor value of each trading day.

In addition, the present application also proposes a machine learning-based stock timing method, the method comprising the following steps:

S100. Obtain a preset type indicator factor corresponding to each trading day of the predetermined stock market index within a preset time period;

S200: analyzing, according to the timing analysis strategy model completed by the pre-training, respectively, the preset type index factors of each acquired trading day are analyzed, so as to output the trend factor values corresponding to each trading day;

S300, performing cluster analysis on the trend factor values corresponding to each trading day according to a predetermined clustering algorithm, to obtain a trend category corresponding to the trend factor value of each trading day;

S400: Determine a timing trading strategy according to the trend category corresponding to the obtained trend factor value of each trading day.

Furthermore, the present application further provides a computer readable storage medium storing a machine learning based stock timing program, the machine learning based stock timing program being executable by at least one processor, Taking the at least one processor to perform the following steps:

Obtaining a preset type index factor corresponding to each trading day of the predetermined stock market index within a preset time period;

According to the timing analysis strategy model completed by the pre-training, the preset type index factors of each acquired trading day are respectively analyzed to output the trend factor values corresponding to each trading day;

Perform cluster analysis on the trend factor values corresponding to each trading day according to a predetermined clustering algorithm to obtain a trend category corresponding to the trend factor value of each trading day;

The timing trading strategy is determined according to the trend category corresponding to the trend factor value of each trading day obtained.

Compared with the prior art, the electronic device, the machine learning-based stock timing method and the storage medium proposed by the present application firstly obtain a preset corresponding to each trading day of the predetermined stock market index within a preset time period. Type indicator factor; then, according to the pre-trained timing analysis model, the preset type index factors of each transaction day are analyzed to output the trend factor values corresponding to each trading day; and then according to a predetermined clustering algorithm The trend factor values corresponding to each trading day are clustered to obtain the trend category corresponding to the trend factor value of each trading day; finally, the timing trading strategy is determined according to the trend category corresponding to the trend factor value of each trading day. Improve the efficiency and accuracy of stock timing trading analysis.

DRAWINGS

1 is a schematic diagram of an optional hardware architecture of an electronic device proposed by the present application;

2 is a schematic diagram of a stock timing program module based on machine learning in an embodiment of an electronic device of the present application;

3 is a flow chart of an implementation of a preferred embodiment of a machine learning based stock timing method of the present application.

The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings.

detailed description

In order to make the objects, technical solutions, and advantages of the present application more comprehensible, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

It should be noted that the descriptions of "first", "second" and the like in the present application are for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. . Thus, features defining "first" or "second" may include at least one of the features, either explicitly or implicitly. In addition, the technical solutions between the various embodiments may be combined with each other, but must be based on the realization of those skilled in the art, and when the combination of the technical solutions is contradictory or impossible to implement, it should be considered that the combination of the technical solutions does not exist. Nor is it within the scope of protection required by this application.

Referring to FIG. 1 , it is an optional hardware architecture diagram of the electronic device proposed by the present application. In this embodiment, the electronic device 10 may include, but is not limited to, a memory 11, a processor 12, and a network interface 13 communicably connected to each other through a communication bus 14. It should be noted that FIG. 1 only shows the electronic device 10 having the components 11-14, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.

The memory 11 includes at least one type of computer readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (for example, SD or DX memory, etc.), a random access memory (RAM), and a static memory. Random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 10, such as a hard disk or memory of the electronic device 10. In other embodiments, the memory 11 may also be an outsourced storage device of the electronic device 10, such as a plug-in hard disk equipped on the electronic device 10, a smart memory card (SMC), and a secure digital (Secure Digital, SD) ) cards, flash cards, etc. Of course, the memory 11 can also include both an internal storage unit of the electronic device 10 and an external storage device thereof. In this embodiment, the memory 11 is generally used to store an operating system installed on the electronic device 10 and various types of application software, such as a stock learning time-based program based on machine learning. Further, the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.

Processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 12 is typically used to control the overall operation of the electronic device 10. In this embodiment, the processor 12 is configured to run program code or processing data stored in the memory 11, such as a running machine learning based stock timing program.

Network interface 13 may include a wireless network interface or a wired network interface, which is typically used to establish a communication connection between electronic device 10 and other electronic devices.

Communication bus 14 is used to implement a communication connection between components 11-13.

Figure 1 shows only the electronic device 10 with components 11-14 and a machine learning based stock timing program, but it should be understood that not all illustrated components may be implemented, alternative implementations may be more or less s component.

Optionally, the electronic device 10 may further include a user interface (not shown in FIG. 1), and the user interface may include a display, an input unit such as a keyboard, wherein the user interface may further include a standard wired interface, a wireless interface, and the like.

Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED touch device, or the like. Further, the display may also be referred to as a display screen or display unit for displaying information processed in the electronic device 10 and a user interface for displaying visualizations.

In an embodiment, when the machine learning based stock timing program stored in the memory 11 is executed by the processor 12, the following operations are implemented:

A10. Obtain a preset type indicator factor corresponding to each trading day of the predetermined stock market index in a preset time period;

Specifically, the pre-determined stock market index refers to stock market reference data that has strong liquidity, large scale, can represent the stock price comprehensive change, and can provide investors with an authoritative investment direction, such as SSE 50, Shanghai and Shenzhen. 300, or commonly used reference data such as CSI 500. Among them, SSE 50 corresponds to 50 large-cap stocks in Shanghai stock market, and CSI 300 corresponds to 300 blue-chip stocks outside the market value of 30 cities, of which only a few are coincident with SSE 50, such as Pufa, Unicom, etc. 500 corresponds to 500 stocks with moderate market capitalization in the two cities, many of which coincide with the Shanghai and Shenzhen 300. Specifically, the preset type index factor is a macro indicator that affects a predetermined stock market index. For example, in the embodiment, taking the CSI 300 as an example, the corresponding preset type index factors include, but are not limited to, the medium debt. Treasury yield to maturity - China Bond Corporate Bond Yield to maturity, risk premium, dividend yield, SlowD, MACD Histogram, Bollinger Bands, MA of RSI (14) [M=22], 4-period MA of 4-week MA of Modified OBV-(MA4*4), CR indicator, ratio of size and turnover, RSRS indicator, CSI 300 premium rate, and CSI 300 active purchase amount and other 13-dimensional indicators.

Among them, the debt yield of China Bond (AAA) is 10 years - the 10-year period of China Bond National Debt can be seen from the general trend. When the spread is rising, the market will also start to rise and the small market will go down. Conversely, when the spread falls, the indicator goes down and the small market goes up. From the chart, the spread of the spread has recently declined, indicating that the market is starting to decline and the small-cap style is dominant.

The risk premium and the dividend yield are inversely related. When the stock market's yield is higher than the bond market, the funds will flow from the bond market to the stock market. Conversely, when the stock index yield is lower than the bond market, the funds will flow from the stock market to the bond market. (Smooth channel is average plus or minus 1std)

The dividend yield, the CSI 300 dividend yield and the closing price of the CSI 300 were negatively correlated. (Smooth channel is average plus or minus 1std)

SlowD, when slowD<10 oversold signal appears, do more index; when slowD>10 oversold signal disappears, short index.

MACD Histogram When the MACD Histogram turns from negative to positive, the multi-signal appears, the MACD changes from positive to negative, and the short signal appears;

Bollinger Bands, when the stock price < lower trajectory BN, the buy signal appears.

MA of RSI (14) [M = 22], when 22-day MA of RSI (14) < 40, the buy signal appears, the investment period is 22 trading days.

4-period MA of 4-week MA of modified OBV-(MA4*4), when the stock price trend is consistent with MA4*4, the buy signal appears, and when it deviates, the sell signal appears.

CR indicator, CR <260, low energy, jiacang signal appears.

Size change ratio

When the turnover rate is <=0.1, and the amplitude is <=-10%, the market changes from small to large style; when the turnover rate is >=0.3, and the amplitude is >=10%, the market turns from the market to the small market.

RSRS indicator, when zscore>0.7 and the closing price of MA(20) on the same day > the closing price of MA(20) in the past three days, buy signal; when zscore<-0.7 and the closing price of MA(20) on the same day < the past three days MA (20) When the closing price is sold, the signal is sold.

The CSI 300 premium rate, premium rate >0, market optimism; premium rate <0, market pessimism; historically, the premium rate hits 5 o'clock, is a sell signal; when the premium rate hits -1, it is a buy signal.

The Shanghai and Shenzhen 300 actively buy the amount, the premium rate is >0, the market is optimistic; the premium rate is <0, the market is pessimistic; historically, the premium rate hits 5 o'clock, it is a sell signal; when the premium rate hits -1, it is a buy signal.

Generally, according to the number of trading days included in the preset time period, the preset time period may be classified into ultra short-term, short-term, medium-term, long-term, and ultra-long-term, etc., for example, in this embodiment, the predefined ultra-short-term included transaction The number of days is less than or equal to 5, and the number of trading days included in the short-term is greater than 5 and less than or equal to 10. The number of trading days included in the medium-term is greater than 10 and less than or equal to 15, and the number of trading days included in the long-term is greater than 15 days and less than one year. The number of trading days included in the long term is greater than one year. In general, in practical applications, time series data in ultra-short-term and short-term time periods have a good fitting effect, but contain less information and can be used for ultra-short-line timing reference; the data of medium- and long-term time series contains There is more information, but the dependence of data between time series is not obvious in the short term, so the fitting effect is not super short-term and short-term, so the macroeconomic situation and economic trend are usually described by ultra-long-term data, and combined with medium and long-term data, Long-term timing reference.

Specifically, the pre-trained timing strategy model adopts the idea of machine learning, and uses a preset type index factor of each trading day in a preset time period as an input of a machine learning model, and outputs corresponding to each trading day through machine learning prediction. Trend factor value.

Preferably, in the present embodiment, the pre-trained completion timing strategy model is a cyclic neural network (RNN), and the cyclic neural network is used as a machine learning algorithm. Specifically, the cyclic neural network includes an input layer, a hidden layer (state learning layer), and an output layer; in this embodiment, the output layer is configured to output a relative profit rate within a preset time period, specifically, a relative profit rate The rate of return associated with the total return of the stock market over a predetermined period of time; in this embodiment, the relative rate of return is used to train the inverse update gradient of the machine learning model, and the different factors corresponding to each trading day of the hidden layer output The value is the trend factor value corresponding to each trading day output by the timing strategy model.

It should be noted that the hidden layer of the cyclic neural network (RNN) includes multiple nodes, and the interconnection between the nodes acts as a key layer of the entire machine learning model. Usually the characteristics of the input layer input pass through the hidden layer training learning transformation and reach the output layer. In the hidden layer, which contains multiple layers of neurons, it can be regarded as a neural network transmitted in time. Its depth is the length of time. Usually, as the depth deepens, the phenomenon of “gradient disappearance” will appear. At time t, the gradient it produces disappears after several layers of history on the time axis. Therefore, in the process of training, it is necessary to train the inverse update gradient of the machine learning model by means of the data output from the output layer, and hide The neural network of the layer performs training learning corresponding to the preset type indicators of each trading day input by the input layer, and obtains the factor values corresponding to each trading day, and outputs the respective factor values at the corresponding nodes.

According to the above analysis, the timing strategy model used in this scheme is not used for the prediction of the rate of return, and is closer to a generation model in thought. The output of the timing strategy model involved in this scenario is a classification of hidden layer values corresponding to each trading day, which is equivalent to generating a label for each trading day.

Specifically, the predetermined clustering algorithm is a k-means clustering algorithm, and the k-means clustering algorithm is one of the more classical clustering algorithms in the partitioning method. Because of its high efficiency, the algorithm is widely used in clustering large-scale data. At present, many algorithms are extended and improved around the algorithm.

The k-means algorithm uses k as a parameter to divide n objects into k clusters, so that the clusters have higher similarity and the similarity between clusters is lower. In this embodiment, the processing of the k-means algorithm is as follows: First, assuming that there are n trading days, the trend factor values corresponding to k transaction days are randomly selected as objects, where n>k, and n,k are Is a positive integer; each object initially represents the average or center of a cluster; for each of the remaining objects, it is assigned to the nearest cluster based on its distance from the center of each cluster; then each cluster is recalculated average value. This process is repeated until the criterion function converges. In general, the criterion function uses a squared error criterion, which is defined as follows:

Where E is the sum of the squared errors of all objects consisting of the trend factor values corresponding to n trading days, and p is the point in the space that needs to be clustered. In this embodiment, p is the trend factor of n trading days, mi Is the average of the cluster Ci. The objective function makes the generated cluster as compact and independent as possible, and the distance metric used is the Euclidean distance, although other distance metrics can be used. The algorithm flow of the k-means clustering algorithm is as follows: input the database containing n objects and the number k of clusters. In this embodiment, the trend factor values corresponding to n transaction days are taken as the above n objects, and the preset k The class trend category is used as the number of clusters; k clusters are output to minimize the square error criterion. In this embodiment, the method specifically includes: selecting a trend factor value of k transaction days as an initial cluster center; assigning each object (re) to the most similar cluster according to the average value of the objects in the cluster; updating the average of the clusters The value, which is the average of the objects in each cluster; until the calculation no longer changes, the cluster ends.

Further, the common trend categories can be visually represented in different K-line patterns. For example, the common K-line form has a "V" shape, a reverse cross type, a "W" type, a low position five-yang line, and an arc bottom type. The rise of the bow line in the middle of the rise, the jump of the sword line in the middle of the rise, the jump line of the jump, and so on, and the trend factor value corresponds to one of the various K-line forms.

Specifically, in an embodiment of the present embodiment, taking the CSI 300 as an example, it is assumed that the trend factor values corresponding to each trading day in a year are clustered and analyzed, and k types corresponding to the trend factor values of each trading day are obtained. Market trend category. The position points corresponding to the corresponding K-line patterns are respectively analyzed on each trading day, and the subsequent K-line variation pattern of the corresponding position points is further determined, specifically, in the historical time period (in this embodiment, the hypothesis analysis period is 1) Years) There are market trend categories similar to the K-line pattern. For example, statistical analysis of the trend pattern of the Shanghai and Shenzhen 300 in a week, assuming that the trend factor corresponding to each trading day in the week has a "w" in the trend category. After the K-line change pattern, and the K-line change pattern of the "w" bottom appears in the past week, in the subsequent preset time, it is assumed that the corresponding K-line change pattern is more likely to be close to another determined trend category within one week. Assuming a rising bow line in the middle of the rise, it is determined that the next-day trading strategy for the next week is determined according to the rising midline high bow line.

It can be seen from the above embodiments that the electronic device proposed by the present application firstly obtains a preset type index factor corresponding to each trading day of a predetermined stock market index within a preset time period; and then performs a timing strategy based on pre-training. The analysis model separately analyzes the preset type index factors of each acquired trading day to output the trend factor values corresponding to each trading day; and then clusters the trend factor values corresponding to each trading day according to a predetermined clustering algorithm. In order to obtain the trend category corresponding to the trend factor value of each trading day; finally, the timing trading strategy is determined according to the trend category corresponding to the trend factor value of each trading day obtained. Improve the efficiency and accuracy of stock timing transactions.

It should be further noted that the machine learning-based stock timing program of the present application may be described by a program module having the same function according to different functions implemented by the respective parts. Please refer to FIG. 2 , which is a schematic diagram of a program module of a machine-based stock timing program according to an embodiment of the electronic device of the present application. In this embodiment, the machine timing program based on machine learning may be divided into an obtaining module 201, an analyzing module 202, a clustering module 203, and a determining module 204 according to different functions implemented by the respective parts. As can be seen from the above description, the program module referred to in the present application refers to a series of computer program instruction segments capable of performing a specific function, and is more suitable than the program to describe the execution process of the machine learning-based stock timing program in the electronic device 10. The functions or operational steps implemented by the modules 201-204 are similar to the above, and are not described in detail herein, by way of example, for example:

The obtaining module 201 is configured to obtain a preset type indicator factor corresponding to each trading day of the predetermined stock market index within a preset time period;

The analyzing module 202 is configured to analyze the preset type index factors of each acquired trading day according to the timing analysis strategy model completed by the pre-training, so as to output the trend factor values corresponding to each trading day;

The clustering module 203 is configured to perform cluster analysis on the trend factor values corresponding to each trading day according to a predetermined clustering algorithm, to obtain a trend category corresponding to the trend factor value of each trading day;

The determining module 204 is configured to determine a timing trading strategy according to the obtained trend category corresponding to the trend factor value of each trading day.

In addition, the present application also proposes a machine learning-based stock timing method. Referring to FIG. 3, the machine learning-based stock timing method includes the following steps:

Specifically, the pre-determined stock market index refers to stock market reference data that has strong liquidity, large scale, can represent the stock price comprehensive change, and can provide investors with an authoritative investment direction, such as SSE 50, Shanghai and Shenzhen. 300, or commonly used reference data such as CSI 500. Among them, SSE 50 corresponds to 50 large-cap stocks in Shanghai stock market, and CSI 300 corresponds to 300 blue-chip stocks outside the market value of 30 cities, of which only a few are coincident with SSE 50, such as Pufa, Unicom, etc. 500 corresponds to 500 stocks with moderate market capitalization in the two cities, many of which coincide with the Shanghai and Shenzhen 300. Specifically, the preset type index factor is a macro indicator that affects a predetermined stock market index. For example, in the embodiment, taking the CSI 300 as an example, the corresponding preset type index factors include, but are not limited to, the medium debt. Treasury yield to maturity - China Bond Corporate Bond Yield to maturity, risk premium, dividend yield, SlowD, MACD Histogram, Bollinger Bands, MA of RSI (14) [M=22], 4-period MA of 4-week MA of Modified OBV-(MA4*4), CR indicator, ratio of size to disk, RSRS indicator, CSI 300 premium rate, CSI 300 active purchase amount and other 13-dimensional indicators.

CR indicator, CR <260, low energy, jiacang signal appears.

Size change ratio

The Shanghai-Shenzhen 300 premium rate, premium rate >0, market optimism; premium rate <0, market pessimism; historically, the premium rate hits 5 o'clock, is a sell signal; when the premium rate hits -1, it is a buy signal.

It should be noted that there is an interconnection between hidden layer nodes of the cyclic neural network (RNN), which is a key layer of the entire machine learning model. Usually the input layer input features pass through the hidden layer training learning transformation and reach the output layer. In the hidden layer, which contains multiple layers of neurons, it can be regarded as a neural network transmitted in time. Its depth is the length of time. Usually, as the depth deepens, the phenomenon of “gradient disappearance” will appear. At time t, the gradient it produces disappears after several layers of history on the time axis. Therefore, in the process of training, it is necessary to train the inverse update gradient of the machine learning model by means of the data output from the output layer, and hide The neural network of the layer performs training learning corresponding to the preset type indicators of each trading day input by the input layer, and obtains the factor values corresponding to each trading day, and outputs the respective factor values at the corresponding nodes.

Where E is the sum of the squared errors of all objects consisting of the trend factor values corresponding to n trading days, p is the point in space, and mi is the average of the cluster Ci. The objective function makes the generated cluster as compact and independent as possible, and the distance metric used is the Euclidean distance, although other distance metrics can be used. The algorithm flow of the k-means clustering algorithm is as follows: input the database containing n objects and the number k of clusters. In this embodiment, the trend factor values corresponding to n transaction days are taken as the above n objects, and the preset k The class trend category is used as the number of clusters; k clusters are output to minimize the square error criterion. In this embodiment, the method specifically includes: selecting a trend factor value of k transaction days as an initial cluster center; assigning each object (re) to the most similar cluster according to the average value of the objects in the cluster; updating the average of the clusters The value, which is the average of the objects in each cluster; until the calculation no longer changes, the cluster ends.

It can be seen from the above embodiments that the machine learning-based stock timing method proposed by the present application firstly obtains a preset type index factor corresponding to each trading day of a predetermined stock market index within a preset time period; The training completion timing analysis model separately analyzes the preset type index factors of each transaction day to output the trend factor values corresponding to each trading day; and then according to the predetermined clustering algorithm, the corresponding trend of each trading day The factor value is clustered to obtain the trend category corresponding to the trend factor value of each trading day; finally, the timing trading strategy is determined according to the trend category corresponding to the trend factor value of each trading day. Improve the efficiency and accuracy of stock timing transactions.

In addition, the present application further provides a computer readable storage medium on which a machine learning based stock timing program is stored, and the machine learning based stock timing program is executed by a processor as follows: operating:

The specific embodiment of the computer readable storage medium of the present application is substantially the same as the above embodiments of the electronic device and the machine learning based stock method, and will not be described herein.

The serial numbers of the embodiments of the present application are merely for the description, and do not represent the advantages and disadvantages of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better. Implementation. Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk, The optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

The above is only a preferred embodiment of the present application, and is not intended to limit the scope of the patent application, and the equivalent structure or equivalent process transformations made by the specification and the drawings of the present application, or directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of this application.

Claims

An electronic device, comprising: a memory, and a processor coupled to the memory, the processor configured to execute a machine learning based stock timing program stored on the memory, the based The machine learning stock timing program is executed by the processor to implement the following steps:

A10. Obtain a preset type indicator factor corresponding to each trading day of the predetermined stock market index in a preset time period;

A20. The preset type index factors of each acquired trading day are respectively analyzed according to the timing analysis strategy model completed by the pre-training, so as to output the trend factor values corresponding to each trading day;

A30. Perform cluster analysis on the trend factor values corresponding to each trading day according to a predetermined clustering algorithm to obtain a trend category corresponding to the trend factor value of each trading day;

A40. Determine a timing trading strategy according to the trend category corresponding to the obtained trend factor value of each trading day.
The electronic device according to claim 1, wherein the pre-trained timing analysis strategy analysis model is a cyclic neural network model;

The looping neural network includes an input layer, a hidden layer, and an output layer; the input layer is configured to input a preset type index factor corresponding to each trading day in a preset time period; and the output layer is configured to output a preset time period The relative yield within the layer; the hidden layer comprises a plurality of layers of neurons, and an interconnection function exists between each node of each neuron, and the preset type index factor input by the input layer is trained through neuron training After the transformation, the trend factor value corresponding to each trading day is generated.
The electronic device according to claim 2, wherein the predetermined clustering algorithm is a k-means clustering algorithm; and the step A30 comprises the following steps:

E1, respectively, assuming n objects and a number of clusters, wherein the n objects are trend factor values corresponding to the acquired respective transaction days, and the number of the clusters is a predefined k-type trend category, wherein n≥k, and both Is a positive integer;

F1, arbitrarily selecting k objects from the n objects as pre-defined initial clusters, and k objects are respectively average values of pre-defined initial clusters;

G1, respectively calculating a Euclidean distance between the average values of the n objects and each initial cluster, and according to the calculation result, respectively assigning the n objects to the cluster corresponding to the smallest Euclidean distance;

H1, recalculate the average value of each cluster, and repeat the above step G1 until the predefined criterion function converges, then the cluster ends.
The electronic device of claim 3 wherein said predefined criterion function is a squared error criterion function, said squared error criterion function is:

Where E is the sum of the squared errors of all objects consisting of the trend factor values corresponding to n trading days, p is the trend factor of n trading days, and mi is the average of the cluster Ci.
The electronic device according to claim 1, wherein the trend factor value corresponds to a point in a different K-line form, and the trend category corresponding to the trend factor value comprises a different K-line form.
The electronic device according to claim 2, wherein the trend factor value corresponds to a point in a different K-line form, and the trend category corresponding to the trend factor value comprises a different K-line form.
The electronic device according to claim 3, wherein the trend factor value corresponds to a point in a different K-line form, and the trend category corresponding to the trend factor value comprises a different K-line form.
The electronic device according to claim 4, wherein the trend factor value corresponds to a point in a different K-line form, and the trend category corresponding to the trend factor value comprises a different K-line form.
A machine learning-based stock timing method, characterized in that the method comprises the following steps:

S100. Obtain a preset type indicator factor corresponding to each trading day of the predetermined stock market index within a preset time period;

S200: analyzing, according to the timing analysis strategy model completed by the pre-training, respectively, the preset type index factors of each acquired trading day are analyzed, so as to output the trend factor values corresponding to each trading day;

S300, performing cluster analysis on the trend factor values corresponding to each trading day according to a predetermined clustering algorithm, to obtain a trend category corresponding to the trend factor value of each trading day;

S400: Determine a timing transaction strategy according to the trend category corresponding to the obtained trend factor value of each trading day.
The machine learning-based stock timing method according to claim 9, wherein the pre-trained completion timing analysis model is a cyclic neural network model;

The looping neural network includes an input layer, a hidden layer, and an output layer; the input layer is configured to input a preset type index factor corresponding to each trading day in a preset time period; and the output layer is configured to output a preset time period The relative yield within the layer; the hidden layer comprises a plurality of layers of neurons, and an interconnection function exists between each node of each neuron, and the preset type index factor input by the input layer is trained through neuron training After the transformation, the trend factor value corresponding to each trading day is generated.
The machine learning-based stock timing method according to claim 10, wherein the predetermined clustering algorithm is a k-means clustering algorithm; and the step S300 comprises the following steps:

E2, respectively, assuming n objects and a number of clusters, wherein the n objects are trend factor values corresponding to the acquired respective trading days, and the number of the clusters is a predefined k-category trend category, wherein n≥k, and both Is a positive integer;

F2, arbitrarily selecting k objects from the n objects as pre-defined initial clusters, and k objects are respectively average values of pre-defined initial clusters;

G2, respectively calculating a Euclidean distance between the average values of the n objects and each of the initial clusters, and according to the calculation result, respectively assigning the n objects to the cluster corresponding to the smallest Euclidean distance;

H2, recalculate the average value of each cluster, and repeat step G2 above until the predefined criterion function converges, then the cluster ends.
The machine learning-based stock timing method according to claim 11, wherein the predefined criterion function is a square error criterion function, and the square error criterion function is:

Where E is the sum of the squared errors of all objects consisting of the trend factor values corresponding to n trading days, p is the trend factor of n trading days, and mi is the average of the cluster Ci.
The machine learning-based stock timing method according to claim 9, wherein the trend factor value corresponds to a point in a different K-line form, and the trend category corresponding to the trend category includes different K-line forms. .
The machine learning-based stock timing method according to claim 10, wherein the trend factor value corresponds to a point in a different K-line form, and the trend factor value corresponding to the trend category includes different K-line forms. .
The machine learning-based stock timing method according to claim 11, wherein the trend factor value corresponds to a point in a different K-line form, and the trend factor value corresponding to the trend category includes different K-line forms. .
The machine learning-based stock timing method according to claim 12, wherein the trend factor value corresponds to a point in a different K-line form, and the trend factor value corresponding to the trend category includes different K-line forms. .
A computer readable storage medium storing a machine learning based stock timing program, the machine learning based stock timing program being executable by at least one processor to cause the at least one The processor performs the following steps:

Obtaining a preset type index factor corresponding to each trading day of the predetermined stock market index within a preset time period;

According to the timing analysis strategy model completed by the pre-training, the preset type index factors of each acquired trading day are respectively analyzed to output the trend factor values corresponding to each trading day;

Perform cluster analysis on the trend factor values corresponding to each trading day according to a predetermined clustering algorithm to obtain a trend category corresponding to the trend factor value of each trading day;

The timing trading strategy is determined according to the trend category corresponding to the trend factor value of each trading day obtained.
The storage medium according to claim 17, wherein said pre-trained completion timing analysis model is a cyclic neural network model; said cyclic neural network comprises an input layer, a hidden layer, and an output layer; said input The layer is configured to input a preset type indicator factor corresponding to each trading day in the preset time period; the output layer is configured to output a relative rate of return in the preset time period; the hidden layer comprises a plurality of layers of neurons, and each nerve There is an interconnection function between the nodes of the element, and the preset type index factor input by the input layer is transformed by the neuron training learning, and the trend factor value corresponding to each trading day is generated.
The electronic device according to claim 2, wherein the predetermined clustering algorithm is a k-means clustering algorithm; and the clustering factor corresponding to each trading day is aggregated according to a predetermined clustering algorithm The steps of class analysis to obtain the trend category corresponding to the trend factor value of each trading day include:

E1, respectively, assuming n objects and a number of clusters, wherein the n objects are trend factor values corresponding to the acquired respective transaction days, and the number of the clusters is a predefined k-type trend category, wherein n≥k, and both Is a positive integer;

F1, arbitrarily selecting k objects from the n objects as pre-defined initial clusters, and k objects are respectively average values of pre-defined initial clusters;

G1, respectively calculating a Euclidean distance between the average values of the n objects and each initial cluster, and according to the calculation result, respectively assigning the n objects to the cluster corresponding to the smallest Euclidean distance;

H1, recalculate the average value of each cluster, and repeat the above step G1 until the predefined criterion function converges, then the cluster ends.
The storage medium of claim 19 wherein said predefined criterion function is a squared error criterion function, said squared error criterion function is:

Where E is the sum of the squared errors of all objects consisting of the trend factor values corresponding to n trading days, p is the trend factor of n trading days, and mi is the average of the cluster Ci.