CN107368925A  Stock trend forecasting method and system  Google Patents
Stock trend forecasting method and system Download PDFInfo
 Publication number
 CN107368925A CN107368925A CN201710620881.0A CN201710620881A CN107368925A CN 107368925 A CN107368925 A CN 107368925A CN 201710620881 A CN201710620881 A CN 201710620881A CN 107368925 A CN107368925 A CN 107368925A
 Authority
 CN
 China
 Prior art keywords
 mark point
 stock
 mrow
 tendency
 section
 Prior art date
 Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
 Pending
Links
Classifications

 G—PHYSICS
 G06—COMPUTING; CALCULATING OR COUNTING
 G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
 G06Q10/00—Administration; Management
 G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"

 G—PHYSICS
 G06—COMPUTING; CALCULATING OR COUNTING
 G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
 G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
 G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
 Business, Economics & Management (AREA)
 Engineering & Computer Science (AREA)
 Economics (AREA)
 Strategic Management (AREA)
 General Business, Economics & Management (AREA)
 Human Resources & Organizations (AREA)
 Marketing (AREA)
 Finance (AREA)
 Development Economics (AREA)
 Physics & Mathematics (AREA)
 Accounting & Taxation (AREA)
 General Physics & Mathematics (AREA)
 Theoretical Computer Science (AREA)
 Game Theory and Decision Science (AREA)
 Technology Law (AREA)
 Entrepreneurship & Innovation (AREA)
 Operations Research (AREA)
 Quality & Reliability (AREA)
 Tourism & Hospitality (AREA)
 Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides stock trend forecasting method and system, including the first market data are obtained, and the first market data are preprocessed to obtain the second market data；Share price observation Oe values and Forecasting of Stock Prices Pe values are calculated according to the second market data, and obtains linear regression model (LRM)；In linear regression model (LRM), tendency form and the section of stock are determined according to Forecasting of Stock Prices Pe values；Tendency form and section are applied in the K line charts of stock and obtain tangible Cartographic Technique index, and carry out strategy instruction.The present invention solves the technical problem of the method shortage accuracy of Prediction of Stock Index, can help user according to the tangible Cartographic Technique index on K line charts, it is easier to which ground judges the trend of stock, so as to scientifically be carried out policy development, it is ensured that user benefit.
Description
Technical field
The present invention relates to Computer Applied Technology field, more particularly, to stock trend forecasting method and system.
Background technology
Develop into people's today and carried out substantial amounts of research, including technical Analysis method, Fundamental Analysis method, valency in stock market
It is worth law of investment etc., as the development of science and technology, information revolution trend and conventional investment method are known, will to predict that stock is walked
Gesture needs more more accurately prediction analysis methods, but new Forecasting Methodology will be more complicated, and noneconomy and computer should
It is difficult to hold shares changing tendency and carry out technical Analysis with the people of technical field.
Existing technical indicator is for the people of noneconomy and Computer Applied Technology field, it is difficult to grasp market trend
And shares changing tendency；Prediction of the existing technical indicator to shares changing tendency is because the people used is excessive, and has certain hysteresis
Property and plus artificial subjective judgement, thus it is not accurate enough and stably.
In summary, the major defect of prior art is that the method for Prediction of Stock Index lacks accuracy, for amateur people
Application has larger difficulty for member.
The content of the invention
In view of this, it is an object of the invention to provide stock trend forecasting method and system, user can be helped according to K
Tangible Cartographic Technique index on line chart, it is easier to which ground judges the trend of stock, so as to scientifically be carried out policy development, really
Protect user benefit.
In a first aspect, the embodiments of the invention provide stock trend forecasting method, including：
The first market data are obtained, and the first market data are preprocessed to obtain the second market data；
Share price observation Oe values and Forecasting of Stock Prices Pe values are calculated according to the second market data, and obtains linear regression mould
Type；
In the linear regression model (LRM), tendency form and the area of the stock are determined according to the Forecasting of Stock Prices Pe values
Between；
The tendency form and the section are applied in the K line charts of the stock and obtain tangible Cartographic Technique index,
And carry out strategy instruction.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the first of first aspect, wherein, institute
Stating the second market data includes date, share price and exchange hand, and the Forecasting of Stock Prices Pe values include tendency classification value and values of intercept, institute
Stating tendency form includes going up, accelerates to go up, drop and accelerate drop, and the section includes sowing, germination, growth, harvest, winter
Tibetan, severe winter, severe cold and the return of spring.
With reference to the first possible embodiment of first aspect, the embodiments of the invention provide second of first aspect
Possible embodiment, wherein, it is described to calculate share price observation Oe values and Forecasting of Stock Prices Pe values according to the second market data, and
Obtaining linear regression model (LRM) includes：
The tendency classification value is calculated according to following formula：
Or；
The values of intercept is calculated according to following formula：
Or；
The linear regression model (LRM) is calculated according to following formula：
Y=a+bX
Wherein, x is the date, and y is the share price, and n is number of days, and a is the values of intercept, and b is the tendency classification value,
Y is predicting Stock Price, and X is forecast date.
With reference to the first possible embodiment of first aspect, the embodiments of the invention provide the third of first aspect
Possible embodiment, wherein, the tendency classification value includes the first numerical value, second value, third value and the 4th numerical value, institute
State in the linear regression model (LRM), determine that the tendency form of the stock and section include according to the Forecasting of Stock Prices Pe values：
Mark point corresponding with the tendency form in the linear regression model (LRM) is determined, and according to the mark point meter
Calculate the tendency classification value；
According to the tendency classification be worth to the tendency form, wherein, it is described go up, it is described accelerate go up, it is described under
Fall with it is described accelerate drop corresponding to the tendency classification value be respectively first numerical value, the second value, the described 3rd
Numerical value and the 4th numerical value；
Section is determined according to the mark point.
With reference to the first possible embodiment of first aspect, the embodiments of the invention provide the 4th of first aspect kind
Possible embodiment, wherein, the described tendency form and the section are applied in the K line charts of the stock is had
Shape Cartographic Technique index includes：
Using different colours by it is described go up, it is described accelerate go up, it is described drop, it is described acceleration drop, the sowing, institute
Germination, the growth, the harvest, winter Tibetan, the severe winter, the severe cold and the mark of rejuvenating are stated in the K line charts
On.
With reference to the third possible embodiment of first aspect, the embodiments of the invention provide the 5th of first aspect kind
Possible embodiment, wherein, it is described to determine mark point bag corresponding with the tendency form in the linear regression model (LRM)
Include：
First mark point is determined according to the share price and the exchange hand, wherein, the share price includes lowest price；
The worst error predicted value of every in the linear regression model (LRM) is calculated, and is sought according to the worst error predicted value
Look for the second mark point；
The minimal error predicted value of every between first mark point and second mark point is calculated, and determines the 3rd
Mark point.
With reference to the 5th kind of possible embodiment of first aspect, the embodiments of the invention provide the 6th of first aspect kind
Possible embodiment, wherein, it is described to determine mark point corresponding with the tendency form in the linear regression model (LRM) also
Including：
4th mark point is determined according to the share price, wherein, the share price includes highest price；
The tendency classification value is calculated using the 3rd mark point and the 4th mark point；
Definition values of intercept is the share price corresponding to second mark point, and calculates the stock from second mark point
The predicted value of valency.
According to the third possible embodiment of first aspect, the embodiments of the invention provide the 7th of first aspect kind
Possible embodiment, wherein, it is described to determine mark point corresponding with the tendency form in the linear regression model (LRM) also
Including：
5th mark point is determined according to the share price and the exchange hand, wherein, the share price includes highest price；
Calculate the worst error predicted value of every in the regression model, and the is found according to the worst error predicted value
Six mark points；
The minimal error predicted value of every between the 5th mark point and the 6th mark point is calculated, and determines the 7th
Mark point；
8th mark point is determined according to the share price, wherein, the share price includes lowest price；
The tendency classification value is calculated using the 7th mark point and the 8th mark point；
Definition values of intercept is the share price corresponding to the 6th mark point, and calculates the stock from the 6th mark point
The predicted value of valency.
With reference to the third possible embodiment of first aspect, the embodiments of the invention provide the 8th of first aspect kind
Possible embodiment, wherein, determine that section includes according to the mark point：
The second mark point is begun look for from the first mark point, and the section before second mark point is not determined is as institute
State sowing；
From first mark point to after determining second mark point, and the section before the 3rd mark point is not determined is made
For the germination；
To the section present node as the growth since the second mark point；
Same day closing price is less than the section of the share price corresponding to first mark point as the harvest；
The 6th mark point is begun look for from the 5th mark point, and the section before the 6th mark point is not determined is as institute
State winter Tibetan；
From the 5th mark point to after determining the 6th mark point, and the section before the 7th mark point is not determined is made
For the severe winter；
To the section present node as the severe cold since the 6th mark point；
Same day closing price is more than the section of the share price corresponding to the 5th mark point as the return of spring.
Second aspect, the embodiments of the invention provide stock trend predicting system, including：
Processing unit is obtained, for obtaining the first market data, and the first market data are preprocessed to obtain
Second market data；
First computing unit, for calculating share price observation Oe values and Forecasting of Stock Prices Pe values according to the second market data,
And obtain linear regression model (LRM)；
Second computing unit, in the linear regression model (LRM), the stock to be determined according to the Forecasting of Stock Prices Pe values
The tendency form of ticket and section；
Strategy instruction unit, obtained for the tendency form and the section to be applied in the K line charts of the stock
Tangible Cartographic Technique index, and carry out strategy instruction.
The invention provides stock trend forecasting method and system, first, obtains the first market data, and to the first market
Data are preprocessed to obtain the second market data；Then, share price observation Oe values are calculated according to the second market data and share price is pre
Pe values are surveyed, and obtain linear regression model (LRM)；Secondly, in linear regression model (LRM), walking for stock is determined according to Forecasting of Stock Prices Pe values
Gesture form and section；Finally, tendency form and section are applied in the K line charts of stock and obtain tangible Cartographic Technique index, and
Carry out strategy instruction.The present invention solves the technical problem of the method shortage accuracy of Prediction of Stock Index, can help user according to K
Tangible Cartographic Technique index on line chart, it is easier to which ground judges the trend of stock, so as to scientifically be carried out policy development, really
Protect user benefit.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages are in specification, claims
And specifically noted structure is realized and obtained in accompanying drawing.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art
The required accompanying drawing used is briefly described in embodiment or description of the prior art, it should be apparent that, in describing below
Accompanying drawing is some embodiments of the present invention, for those of ordinary skill in the art, before creative work is not paid
Put, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is stock trend forecasting method flow chart provided in an embodiment of the present invention；
Fig. 2 is step S103 method flow diagrams provided in an embodiment of the present invention；
Fig. 3 is step S201 method flow diagrams provided in an embodiment of the present invention；
Fig. 4 is another step S201 method flow diagrams provided in an embodiment of the present invention；
Fig. 5 is step S203 method flow diagrams provided in an embodiment of the present invention；
Fig. 6 is that rise tendency provided in an embodiment of the present invention defines method schematic diagram；
Fig. 7 defines method schematic diagram for acceleration rise tendency provided in an embodiment of the present invention；
Fig. 8 defines method schematic diagram for drop tendency provided in an embodiment of the present invention；
Fig. 9 accelerates drop tendency to define method schematic diagram to be provided in an embodiment of the present invention；
Figure 10 is four kinds of tendencies morphological relationship figure provided in an embodiment of the present invention；
Figure 11 is eight kinds of section graphs of a relation provided in an embodiment of the present invention；
Figure 12 is stock trend forecasting method schematic diagram provided in an embodiment of the present invention；
Figure 13 is stock trend predicting system schematic diagram provided in an embodiment of the present invention；
Figure 14 is the application scenario diagram of stock trend forecasting method provided in an embodiment of the present invention；
Figure 15 is another step S201 method flow diagrams provided in an embodiment of the present invention.
Icon：10 acquiring units；The computing units of 20 first；The computing units of 30 second；40 strategy instruction units.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with accompanying drawing to the present invention
Technical scheme be clearly and completely described, it is clear that described embodiment is part of the embodiment of the present invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
At present, the major defect of prior art is that the method for Prediction of Stock Index lacks accuracy, comes for layman
Say that application has larger difficulty, based on this, stock trend forecasting method provided in an embodiment of the present invention and system, can help
User is according to the tangible Cartographic Technique index on K line charts, it is easier to which ground judges the trend of stock, so as to scientifically be carried out plan
Slightly formulate, it is ensured that user benefit.
For ease of understanding the present embodiment, the stock trend forecasting method disclosed in the embodiment of the present invention is entered first
Row is discussed in detail, and the present invention can be applied in stock price index futures, commodity future and K line tendency types except applying in stock
On financial derivatives.
Fig. 1 is stock trend forecasting method flow chart provided in an embodiment of the present invention.
Reference picture 1, stock trend forecasting method include：
Step S101, the first market data are obtained, and the first market data are preprocessed to obtain the second market number
According to；
Specifically, the relevant historical trading data of stock is obtained daily, including it is opening price, closing price, highest price, minimum
Valency, activity data, and preprocessed.
Step S102, share price observation Oe (Observation example) values and stock are calculated according to the second market data of institute
Valency predicts Pe (Prediction example) value, and obtains linear regression model (LRM)；
Step S103, in linear regression model (LRM), tendency form and the section of stock are determined according to institute's Forecasting of Stock Prices Pe values；
Step S104, tendency form and section are applied in the K line charts of stock and obtain tangible Cartographic Technique index, gone forward side by side
Row strategy instruction.
Specifically, tendency form and section are applied in stock K line graphs, by using different colours continuously in K lines
Interval division and Form division are carried out on figure, one kind is formed and is named as " tangible map " technical indicator.The embodiment of the present invention provides
Tangible Cartographic Technique analysis indexes be directly applied on K line charts, user intuitively can see that tangible cartographic analysis refers in K line charts
Mark, form strategy instruction；As shown in figure 14, there are the form areas such as " germination " " growth " of different colours mark the middle and lower part of K line charts
Between mark, when it is " sowing " that user has found the section index of " tangible map " in K line charts, represents the stock and have just enter into
The trend of liter；When it is " germination " that user has found the section index of " tangible map " in K line charts, the stock ascendant trend has been represented
Through being formed；When it is " growth " that user has found the section index of " tangible map " in K line charts, the stock ascendant trend has been represented
Confirm and increasing degree is accelerated, when user has found that the section index of " tangible map " is " harvest " in K line charts, while on K line charts
The section is represented with " lower arrow ", the stock ascendant trend is represented and reaches peak, it will into downward tendency；When user is in K lines
When the section index that " tangible map " is found in figure is " winter Tibetan ", represents the stock and have just enter into downward tendency；When user is in K line charts
When the middle section index for finding " tangible map " is " severe winter ", represents the falling stock price trend and formed；When user is in K line charts
When the middle section index for finding " tangible map " is " severe cold ", represents the falling stock price trend and have confirmed that and drop range increase；When with
Family finds that the section index of " tangible map " is " return of spring " in K line charts, while represents the area with " upward arrow " on K line charts
Between, represent the falling stock price trend and reach peak, it will into ascendant trend.Here, in fig. 14 it can be seen that there is upper and lower arrow
The instruction of head.The falling stock price trend is represented with " upward arrow " reach bottomvalley in K line charts, it will into ascendant trend, with " under
Arrow " represents the stock ascendant trend and reaches peak, it will into downward trend, Forecasting Methodology provided in an embodiment of the present invention is led to
Crossing word, color, arrow etc. and be intuitively identified as user's presentation trend prediction result, auxiliary user is traded Analysis of Policy Making,
Greatly improve Consumer's Experience.
According to the exemplary embodiment of the present invention, the second market data are pretreated stock relevant historical number of deals
According to, including date, share price and exchange hand, Forecasting of Stock Prices Pe values include tendency classification value and values of intercept, tendency form includes going up,
Accelerate to go up, drop and accelerate drop, section includes sowing, germination, growth, harvest, winter Tibetan, severe winter, severe cold and the return of spring.
Specifically, share price observation Oe values are existing transaction data.
According to the exemplary embodiment of the present invention, share price observation Oe values and Forecasting of Stock Prices Pe are calculated according to the second market data
It is worth, and obtain linear regression model (LRM) to include：
Tendency classification value is calculated according to formula (1)：
Or；
Values of intercept is calculated according to formula (2)：
Or；
Linear regression model (LRM) is calculated according to formula (3)：
Y=a+bX (3)
Wherein, x is the date, and y is share price, and n is number of days, and a is values of intercept, and b is tendency classification value, and Y is predicting Stock Price, and X is
Forecast date.
Specifically, as shown in figure 12, share price observation Oe values are obtained by the second market data, be worth observing Oe according to share price
To Forecasting of Stock Prices Pe values, by linear regression model (LRM), prediction result is obtained.
According to the exemplary embodiment of the present invention, tendency classification value includes the first numerical value, second value, third value and the
Four numerical value, in linear regression model (LRM), determine that the tendency form of stock and section include according to Forecasting of Stock Prices Pe values：
Reference picture 2, step S201, mark point corresponding with tendency form in linear regression model (LRM) is determined, and according to mark
Note point calculates tendency classification value；
Step S202, tendency form is worth to according to tendency classification, wherein, go up, accelerate to go up, drop and accelerate drop
Corresponding tendency classification value is respectively the first numerical value, second value, third value and the 4th numerical value；
Specifically, tendency classification value corresponding to tendency classification value corresponding to rise is 1, acceleration goes up is 1.1, drop is corresponding
Tendency classification value be 2, to accelerate tendency classification value corresponding to drop be 2.1.
Step S203, section is determined according to mark point.
According to the present invention exemplary embodiment, tendency form and section are applied in the K line charts of stock obtain it is tangible
Cartographic Technique index includes：
It will be gone up using different colours, and accelerate to go up, drop, accelerate drop, sowing, germination, growth, harvest, winter hide, be cold
Winter, severe cold and return of spring mark are on K line charts.
According to the exemplary embodiment of the present invention, step S201 includes：
Reference picture 3, step S301, the first mark point is determined according to share price and exchange hand, wherein, share price includes lowest price；
Step S302, the worst error predicted value of every in linear regression model (LRM) is calculated, and according to worst error predicted value
Find the second mark point；
Step S303, the minimal error predicted value of every between the first mark point and the second mark point is calculated, and determine the
Three mark points.
Specifically, as shown in fig. 6, selected first mark point is 1.0a, 1.0a is that first stock is minimum in the section
Valency, and the same day (n) exchange hand>The average exchange hand of first n days, the lowest price of n days is recycled to substitute into formula (1) (2) respectively
(3).Judge which point is the predicted value of worst error using formula (4), the worst error predicted value when n days does not change, then
That point is just defined as to the second mark point 1.0b；Finally, after 1.0b is defined, the highest price generation between 1.0a and 1.0b is utilized
Enter and substitute into formula (1) (2) (3) respectively, and utilize formula (5) to find the predicted value of some minimal errors and be just defined as 1.0c.Need
It is noted that 1.0a and 1.0b is substituted into formula (1), tendency classification value b values should be greater than 0, i.e. 1.0b>1.0a.
Here, the calculation formula of worst error predicted value is：
Minimal error predicted value obtains calculation formula：
Wherein, Oe is that the share price observes Oe values, and Pe is the Forecasting of Stock Prices Pe values, L_{∞}(E) it is error prediction value, max
For maximum, min is minimum.
According to the exemplary embodiment of the present invention, step S201 also includes：
Reference picture 4, step S401, the 4th mark point is determined according to share price, wherein, share price includes highest price；
Step S402, tendency classification value is calculated using the 3rd mark point and the 4th mark point；
Step S403, definition values of intercept are share price corresponding to the second mark point, and calculate the pre of share price from the second mark point
Measured value.
Specifically, it is illustrated in figure 7 acceleration to go up, it is 1.0d to select the 4th mark point, and 1.0d is defined as into the same day most
At high price, and the highest price on the same day have to be larger than the 3rd mark point 1.0c；After 1.0d is defined, 1.0c and 1.0d highest price is utilized
Formula (1) is substituted into find tendency classification value b '.
It should be noted that above to go up and accelerating the definition method of rise, the definition for dropping and accelerating drop
Method can similarly obtain.
Reference picture 15, step S601, the 5th mark point is determined according to institute's share price and exchange hand, wherein, share price includes highest
Valency；
Step S602, the worst error predicted value of every in regression model is calculated, and found according to worst error predicted value
6th mark point；
Step S603, the minimal error predicted value of every between the 5th mark point and the 6th mark point is calculated, and determine the
Seven mark points；
Step S604, the 8th mark point is determined according to share price, wherein, share price includes lowest price；
Step S605, tendency classification value is calculated using the 7th mark point and the 8th mark point；
Step S606, definition values of intercept are share price corresponding to the 6th mark point, and calculate the pre of share price from the 6th mark point
Measured value.
Specifically, the 5th mark point is 2.0a, and the 6th mark point is 2.0b, and the 7th mark point is 2.0c, and the 8th
Mark point is 2.0d.Identified for drop, as shown in figure 8, be first highest price in section 2.0a, and the same day (n) into
Friendship amount is more than the average exchange hand of first n days；Then, formula (1) (2) (3) is substituted into using the highest price of n days.Utilize formula (4)
Judge which point be worst error predicted value, when the predicted value of n days worst errors does not change, then maximum error it is pre
Measured value point is just defined as 2.0b；After 2.0b is defined, formula (1) (2) is substituted into using the highest price between 2.0a and 2.0b
(3) predicted value of some minimal errors, is found using formula (5), and will change the time and define 2.0c.Here, 2.0a and 2.0b are utilized
Formula (1) is substituted into, b values are necessarily less than 0, are 2.0b<2.0a.For accelerating drop mark, as shown in figure 9,2.0d is defined as
The lowest price on the same day, and the lowest price on the same day is necessarily less than 2.0c；After 2.0d is defined, 2.0c and 2.0d lowest price generation is utilized
Enter formula (1), find b '.
Therefore deduce that, for formula (1), (" rise 1.0 " herein rising 1.0 and represent that tendency form to rise, is walked
Gesture classification value is the tendency classification value b that in the case of 1.0), obtains>0；In the tendency point in the case of 1.1, obtained of accelerating
Class value b '>b.The transformational relation of tendency form be can refer to shown in Figure 10, and the figure is shown by using arrow between various tendency forms
Transformational relation, carry out the tendency trend of auxiliary judgment next step.Figure 10 intactly presents shares changing tendency by rising → acceleration
The transformational relation flow of liter → drop → acceleration drop → rising is, it is necessary to which explanation, is the normal of stock due to rising and dropping
State, therefore in the figure, mantoman transformational relation is not only embodied, two pair one of transformational relation is also embodied, that is, is risen with
Drop state is transformed by other two states, and (rising → drop ← accelerates, and rises and accelerates as two kinds of conversions
To the mode passage of drop, drop → rising ← acceleration drop can similarly obtain), also embodyChange mutually
Situation, meet the realtime alteration trend of stock in reality, can effectively cover most of advance versus decline flow path switch, it is more smart
Really reliably user is helped to carry out Trend judgement.
According to the exemplary embodiment of the present invention, step S203 includes：
Reference picture 5, step S501, the second mark point is begun look for from the first mark point, and the second mark point is not determined
Preceding section is as sowing；
Step S502, from the first mark point to after determining the second mark point, and the section before the 3rd mark point is not determined
As germination；
Step S503, to the section present node as growth since the second mark point；
Step S504, same day closing price is less than the section of share price corresponding to first mark point as harvest, here,
The closing price on the same day is necessarily less than the opening price on the same day.
Specifically, there is definition method similarly for winter Tibetan, severe winter, severe cold and the return of spring.Begun look for from the 5th mark point
6th mark point, and the section before the 6th mark point is not determined is hidden as the winter；From the 5th mark point to the 6th mark point of determination
Afterwards, the section before and the 7th mark point is not determined is as severe winter；To the section present node since the 6th mark point
As severe cold；Same day closing price is more than the section of share price corresponding to the 5th mark point as the return of spring.Begun look for from 2.0a points
In 2.0b, and the section before 2.0b is not determined is hidden as the winter；After determining 2.0b from 2.0a Dian Dao Indeed, and the nonIndeed of 2.0c it is fixed before section
As severe winter；Since 2.0b points till now between section as severe cold；The closing price on the same day>The Y predictions of same day formula (3)
Value or the closing price on the same day>The section of 2.0a point share prices is as rejuvenating, and here, the closing price on the same day must Shall reopening after a cessation of business more than the same day
Valency.The transformational relation in section can refer to shown in Figure 11, and the figure shows the transformational relation between various sections by using arrow, come auxiliary
Help the section form for judging next step.It can be seen from fig. 11 that the figure intactly presents the form section of stock by sowing
The transfer process of → germination → growth → harvest → winter Tibetan → severe winter → severe cold → the return of spring → sowing is, it is necessary to explanation, section
Transformational relation not only include outer loop formula translative mode, the support transformational relation of internal greatleapforward is also covered, from figure
In as can be seen that sowing and germination can be converted directly into harvest section across growth, severe winter and winter hide can also be directly across
Severe cold is converted directly into return of spring section, movement in stock and share situation more in closer to reality, so that side provided in an embodiment of the present invention
Method more flexibility and reliability, provides the user more accurate help.
The embodiment of the present invention carries out the calculating of shares changing tendency by the methods of selecting predictors, formula calculating and artificial intelligence,
Show that four kinds of form tendencies of stock judge and define eight sections, four kinds of form tendencies be respectively go up, accelerate to go up, under
Fall and accelerate to drop, eight sections respectively sowing, germination, growth, harvest, winter Tibetan, severe winter, severe cold, the return of spring, most at last four kinds
Form and eight sections are applied on stock K line charts, form the stock technical Analysis index that one kind is named as " tangible map ".This
Formula and analysis, computational methods, four kinds of tendency forms and eight sections belong to innovation used by inventive embodiments, effectively carry
The accuracy of high forward prediction, realize user and objectively speaking arrive stock " tangible map " section index, help user directly perceived
Judgement trend, so as to scientifically be carried out policy development, it is ensured that user benefit.
Figure 13 is stock trend predicting system structural representation provided in an embodiment of the present invention.
Reference picture 13, stock trend predicting system include：
Processing unit 10 is obtained, for obtaining the first market data, and the first market data are preprocessed to obtain with the
Two market data；
First computing unit 20, for calculating share price observation Oe values and Forecasting of Stock Prices Pe values according to the second market data, and
Obtain linear regression model (LRM)；
Second computing unit 30, in linear regression model (LRM), the tendency shape of stock to be determined according to Forecasting of Stock Prices Pe values
State and section；
Strategy instruction unit 40, tangible map skill is obtained for tendency form and section being applied in the K line charts of stock
Art index, and carry out strategy instruction.
Specifically, the mark in state and section, generation are carried out by using different colours interval division on K line charts daily
Tangible Cartographic Technique index, the application example of the notation methods category embodiment of the present invention；The stock is calculated on the day of system
Tendency state value is 1.1, and section is growth section, and system continues on K line charts draws growth section, and generate the stock has
Shape Cartographic Technique analysis indexes；If systemcomputed show that same day tendency state value is 2, section is between winter Tibetan area, and system is in K lines
Continue on figure between drawing winter Tibetan area, and so on.
According to the exemplary embodiment of the present invention, the first computing unit 20 includes：
Tendency classification value is calculated according to formula (1)；
Values of intercept is calculated according to formula (2)；
Linear regression model (LRM) is calculated according to formula (3).
Stock trend predicting system provided in an embodiment of the present invention, the stock trend forecasting method provided with abovedescribed embodiment
With identical technical characteristic, so can also solve identical technical problem, reach identical technique effect.
The stock trend forecasting method and the computer program product of system that the embodiment of the present invention is provided, including store
The computerreadable recording medium of program code, the instruction that described program code includes can be used for performing in previous methods embodiment
Described method, specific implementation can be found in embodiment of the method, will not be repeated here.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
With the specific work process of device, the corresponding process in preceding method embodiment is may be referred to, will not be repeated here.
In addition, in the description of the embodiment of the present invention, unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or be integrally connected；Can
To be mechanical connection or electrical connection；Can be joined directly together, can also be indirectly connected by intermediary, Ke Yishi
The connection of two element internals.For the ordinary skill in the art, with concrete condition abovementioned term can be understood at this
Concrete meaning in invention.
If the function is realized in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention.
And foregoing storage medium includes：USB flash disk, mobile hard disk, readonly storage (ROM, ReadOnly Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
In addition, term " first ", " second ", " the 3rd " are only used for describing purpose, and it is not intended that instruction or implying phase
To importance.
Finally it should be noted that：Embodiment described above, it is only the embodiment of the present invention, to illustrate the present invention
Technical scheme, rather than its limitations, protection scope of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, it will be understood by those within the art that：Any one skilled in the art
The invention discloses technical scope in, it can still modify to the technical scheme described in previous embodiment or can be light
Change is readily conceivable that, or equivalent substitution is carried out to which part technical characteristic；And these modifications, change or replacement, do not make
The essence of appropriate technical solution departs from the spirit and scope of technical scheme of the embodiment of the present invention, should all cover the protection in the present invention
Within the scope of.Therefore, protection scope of the present invention described should be defined by scope of the claims.
Claims (10)
 A 1. B shareB trend forecasting method, it is characterised in that including：The first market data are obtained, and the first market data are preprocessed to obtain the second market data；Share price observation Oe values and Forecasting of Stock Prices Pe values are calculated according to the second market data, and obtains linear regression model (LRM)；In the linear regression model (LRM), tendency form and the section of the stock are determined according to the Forecasting of Stock Prices Pe values；The tendency form and the section are applied in the K line charts of the stock and obtain tangible Cartographic Technique index, is gone forward side by side Row strategy instruction.
 2. stock trend forecasting method according to claim 1, it is characterised in that the second market data include day Phase, share price and exchange hand, the Forecasting of Stock Prices Pe values include tendency classification value and values of intercept, the tendency form includes going up, Accelerate to go up, drop and accelerate drop, the section includes sowing, germination, growth, harvest, winter Tibetan, severe winter, severe cold and the return of spring.
 3. stock trend forecasting method according to claim 2, it is characterised in that described according to the second market data Share price observation Oe values and Forecasting of Stock Prices Pe values are calculated, and obtain linear regression model (LRM) to include：The tendency classification value is calculated according to following formula：<mrow> <mi>b</mi> <mo>=</mo> <mfrac> <mrow> <mi>n</mi> <mrow> <mo>(</mo> <mo>&Sigma;</mo> <mi>x</mi> <mi>y</mi> <mo>)</mo> </mrow> <mo></mo> <mrow> <mo>(</mo> <mo>&Sigma;</mo> <mi>x</mi> <mo>)</mo> </mrow> <mrow> <mo>(</mo> <mo>&Sigma;</mo> <mi>y</mi> <mo>)</mo> </mrow> </mrow> <mrow> <mi>n</mi> <mrow> <mo>(</mo> <mo>&Sigma;</mo> <msup> <mi>x</mi> <mn>2</mn> </msup> <mo>)</mo> </mrow> <mo></mo> <msup> <mrow> <mo>(</mo> <mo>&Sigma;</mo> <mi>x</mi> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> </mfrac> </mrow>Or；The values of intercept is calculated according to following formula：<mrow> <mi>a</mi> <mo>=</mo> <mfrac> <mrow> <mo>(</mo> <mo>&Sigma;</mo> <mi>y</mi> <mo>)</mo> <mo>(</mo> <mo>&Sigma;</mo> <msup> <mi>x</mi> <mn>2</mn> </msup> <mo>)</mo> <mo></mo> <mo>(</mo> <mo>&Sigma;</mo> <mi>x</mi> <mo>)</mo> <mo>(</mo> <mo>&Sigma;</mo> <mi>x</mi> <mi>y</mi> <mo>)</mo> </mrow> <mrow> <mi>n</mi> <mrow> <mo>(</mo> <mo>&Sigma;</mo> <msup> <mi>x</mi> <mn>2</mn> </msup> <mo>)</mo> </mrow> <mo></mo> <msup> <mrow> <mo>(</mo> <mo>&Sigma;</mo> <mi>x</mi> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> </mfrac> </mrow>Or；The linear regression model (LRM) is calculated according to following formula：Y=a+bXWherein, x is the date, and y is the share price, and n is number of days, and a is the values of intercept, and b is the tendency classification value, and Y is Predicting Stock Price, X are forecast date.
 4. stock trend forecasting method according to claim 2, it is characterised in that the tendency classification value includes the first number Value, second value, third value and the 4th numerical value, it is described in the linear regression model (LRM), according to the Forecasting of Stock Prices Pe values The tendency form and section for determining the stock include：Mark point corresponding with the tendency form in the linear regression model (LRM) is determined, and institute is calculated according to the mark point State tendency classification value；According to the tendency classification be worth to the tendency form, wherein, it is described go up, it is described accelerate go up, it is described drop and The tendency classification value corresponding to the acceleration drop is respectively first numerical value, the second value, the third value With the 4th numerical value；Section is determined according to the mark point.
 5. stock trend forecasting method according to claim 2, it is characterised in that described by the tendency form and described Section, which is applied in the K line charts of the stock, to be obtained tangible Cartographic Technique index and includes：Using different colours by it is described go up, it is described accelerate go up, it is described drop, it is described accelerate drop, it is described sowing, the hair Bud, the growth, the harvest, winter Tibetan, the severe winter, the severe cold and the mark of rejuvenating are on the K line charts.
 6. stock trend forecasting method according to claim 4, it is characterised in that described to determine the linear regression model (LRM) In the mark point corresponding with the tendency form include：First mark point is determined according to the share price and the exchange hand, wherein, the share price includes lowest price；Calculate the worst error predicted value of every in the linear regression model (LRM), and the is found according to the worst error predicted value Two mark points；The minimal error predicted value of every between first mark point and second mark point is calculated, and determines the 3rd mark Point.
 7. stock trend forecasting method according to claim 6, it is characterised in that also include：4th mark point is determined according to the share price, wherein, the share price includes highest price；The tendency classification value is calculated using the 3rd mark point and the 4th mark point；Definition values of intercept is the share price corresponding to second mark point, and calculates the share price from second mark point Predicted value.
 8. stock trend forecasting method according to claim 4, it is characterised in that described to determine the linear regression model (LRM) In the mark point corresponding with the tendency form also include：5th mark point is determined according to the share price and the exchange hand, wherein, the share price includes highest price；The worst error predicted value of every in the regression model is calculated, and the 6th mark is found according to the worst error predicted value Note point；The minimal error predicted value of every between the 5th mark point and the 6th mark point is calculated, and determines the 7th mark Point；8th mark point is determined according to the share price, wherein, the share price includes lowest price；The tendency classification value is calculated using the 7th mark point and the 8th mark point；Definition values of intercept is the share price corresponding to the 6th mark point, and calculates the share price from the 6th mark point Predicted value.
 9. stock trend forecasting method according to claim 4, it is characterised in that determine that section is wrapped according to the mark point Include：The second mark point is begun look for from the first mark point, and the section before second mark point is not determined is broadcast as described in Kind；From first mark point to after determining second mark point, and the section before the 3rd mark point is not determined is as institute State germination；To the section present node as the growth since the second mark point；Same day closing price is less than the section of the share price corresponding to first mark point as the harvest；The 6th mark point is begun look for from the 5th mark point, and the section before the 6th mark point is not determined is as the winter Hide；From the 5th mark point to after determining the 6th mark point, and the section before the 7th mark point is not determined is as institute State severe winter；To the section present node as the severe cold since the 6th mark point；Same day closing price is more than the section of the share price corresponding to the 5th mark point as the return of spring.
 A 10. B shareB trend predicting system, it is characterised in that including：Processing unit is obtained, for obtaining the first market data, and the first market data are preprocessed to obtain second Market data；First computing unit, for calculating share price observation Oe values and Forecasting of Stock Prices Pe values according to the second market data, and obtain To linear regression model (LRM)；Second computing unit, in the linear regression model (LRM), the stock to be determined according to the Forecasting of Stock Prices Pe values Tendency form and section；Strategy instruction unit, for the tendency form and the section are applied in the K line charts of the stock obtain it is tangible Cartographic Technique index, and carry out strategy instruction.
Priority Applications (1)
Application Number  Priority Date  Filing Date  Title 

CN201710620881.0A CN107368925A (en)  20170726  20170726  Stock trend forecasting method and system 
Applications Claiming Priority (1)
Application Number  Priority Date  Filing Date  Title 

CN201710620881.0A CN107368925A (en)  20170726  20170726  Stock trend forecasting method and system 
Publications (1)
Publication Number  Publication Date 

CN107368925A true CN107368925A (en)  20171121 
Family
ID=60307232
Family Applications (1)
Application Number  Title  Priority Date  Filing Date 

CN201710620881.0A Pending CN107368925A (en)  20170726  20170726  Stock trend forecasting method and system 
Country Status (1)
Country  Link 

CN (1)  CN107368925A (en) 
Cited By (5)
Publication number  Priority date  Publication date  Assignee  Title 

CN108090625A (en) *  20171231  20180529  广州金十信息科技有限公司  A kind of Forecasting Methodology, terminal device and the storage medium of finance market 
CN109408531A (en) *  20180925  20190301  平安科技（深圳）有限公司  The detection method and device of slow drop type data, electronic equipment, storage medium 
CN109859039A (en) *  20181228  20190607  北京邮电大学  A kind of prediction technique and device 
CN110263843A (en) *  20190618  20190920  苏州梧桐汇智软件科技有限责任公司  Stock K line recognition methods based on deep neural network 
CN112732236A (en) *  20210122  20210430  上海鎏量科技有限公司  Trend device implementation method for transaction investment and transaction investment method 

2017
 20170726 CN CN201710620881.0A patent/CN107368925A/en active Pending
Cited By (6)
Publication number  Priority date  Publication date  Assignee  Title 

CN108090625A (en) *  20171231  20180529  广州金十信息科技有限公司  A kind of Forecasting Methodology, terminal device and the storage medium of finance market 
CN109408531A (en) *  20180925  20190301  平安科技（深圳）有限公司  The detection method and device of slow drop type data, electronic equipment, storage medium 
CN109408531B (en) *  20180925  20230418  平安科技（深圳）有限公司  Method and device for detecting slowfalling data, electronic equipment and storage medium 
CN109859039A (en) *  20181228  20190607  北京邮电大学  A kind of prediction technique and device 
CN110263843A (en) *  20190618  20190920  苏州梧桐汇智软件科技有限责任公司  Stock K line recognition methods based on deep neural network 
CN112732236A (en) *  20210122  20210430  上海鎏量科技有限公司  Trend device implementation method for transaction investment and transaction investment method 
Similar Documents
Publication  Publication Date  Title 

Degasperi et al.  The global transmission of us monetary policy  
Md et al.  Novel optimization approach for stock price forecasting using multilayered sequential LSTM  
CN107368925A (en)  Stock trend forecasting method and system  
Choudhury et al.  A real time clustering and SVM based pricevolatility prediction for optimal trading strategy  
Hahn et al.  Valuebased performance and risk management in supply chains: A robust optimization approach  
Norouzi et al.  Black gold falls, black plague ariseAn Opec crude oil price forecast using a gray prediction model  
Liao et al.  Investment project valuation based on a fuzzy binomial approach  
Lim et al.  Dynamic portfolio rebalancing through reinforcement learning  
CN107679987A (en)  Asset Allocation strategy acquisition methods, device, computer equipment and storage medium  
Li et al.  Take Bitcoin into your portfolio: a novel ensemble portfolio optimization framework for broad commodity assets  
McAleer et al.  ValueatRisk for country risk ratings  
Li et al.  The stock–bond comovements and crossmarket trading  
Clintworth et al.  Combining multicriteria decision analysis and cost–benefit analysis in the assessment of maritime projects financed by the European Investment Bank  
Collan et al.  Forwardlooking valuation of strategic patent portfolios under structural uncertainty  
Sergienko et al.  Optimization models in a transition economy  
JP2010134840A (en)  Future financial prediction system, future financial prediction method, and future financial prediction program  
Hussaini et al.  A multiperiod multiseason multiobjective mathematical model for guaranteeing the viability of supply chains under fluctuations: a healthcare closedloop supply chain application  
Malyscheff et al.  Natural gas storage valuation via least squares Monte Carlo and support vector regression  
Zhong et al.  Novel indexes based on network structure to indicate financial market  
Zhao et al.  Optimal effort under highwater mark contracts  
Dua  Macroeconomic modelling and bayesian methods  
Xu et al.  Comonotonic approximation to periodic investment problems under stochastic drift  
Yu et al.  Factors that influence the concession period length for tunnel projects under BOT contracts  
Xiao et al.  Volatility Transmission in Chinese Trucking Markets: An Application Using BEKK, CCC and DCCMGARCH Models  
Gupta et al.  Stocks recommendation from large datasets using important company and economic indicators 
Legal Events
Date  Code  Title  Description 

PB01  Publication  
PB01  Publication  
SE01  Entry into force of request for substantive examination  
SE01  Entry into force of request for substantive examination  
RJ01  Rejection of invention patent application after publication  
RJ01  Rejection of invention patent application after publication 
Application publication date: 20171121 