CN107368925A - Stock trend forecasting method and system - Google Patents

Stock trend forecasting method and system Download PDF

Info

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
Application number
CN201710620881.0A
Other languages
Chinese (zh)
Inventor
张国
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Golden Eggs Mdt Infotech Ltd
Original Assignee
Shenzhen Golden Eggs Mdt Infotech Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Golden Eggs Mdt Infotech Ltd filed Critical Shenzhen Golden Eggs Mdt Infotech Ltd
Priority to CN201710620881.0A priority Critical patent/CN107368925A/en
Publication of CN107368925A publication Critical patent/CN107368925A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/04Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Abstract

The invention provides stock trend forecasting method and system, including the first market data are obtained, and the first market data are pre-processed 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

Stock trend forecasting method and system
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 non-economy 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 non-economy 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 pre-processed 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 pre-processed 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 pre-processed 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 pre-processed 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 pre-processed.
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 bottom-valley 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, man-to-man 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 real-time 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 non-Indeed 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 great-leap-forward 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 pre-processed 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 system-computed 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 above-described 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 computer-readable 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 above-mentioned 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, read-only storage (ROM, Read-Only 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)

  1. 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 pre-processed 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. 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. 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>&amp;Sigma;</mo> <mi>x</mi> <mi>y</mi> <mo>)</mo> </mrow> <mo>-</mo> <mrow> <mo>(</mo> <mo>&amp;Sigma;</mo> <mi>x</mi> <mo>)</mo> </mrow> <mrow> <mo>(</mo> <mo>&amp;Sigma;</mo> <mi>y</mi> <mo>)</mo> </mrow> </mrow> <mrow> <mi>n</mi> <mrow> <mo>(</mo> <mo>&amp;Sigma;</mo> <msup> <mi>x</mi> <mn>2</mn> </msup> <mo>)</mo> </mrow> <mo>-</mo> <msup> <mrow> <mo>(</mo> <mo>&amp;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>&amp;Sigma;</mo> <mi>y</mi> <mo>)</mo> <mo>(</mo> <mo>&amp;Sigma;</mo> <msup> <mi>x</mi> <mn>2</mn> </msup> <mo>)</mo> <mo>-</mo> <mo>(</mo> <mo>&amp;Sigma;</mo> <mi>x</mi> <mo>)</mo> <mo>(</mo> <mo>&amp;Sigma;</mo> <mi>x</mi> <mi>y</mi> <mo>)</mo> </mrow> <mrow> <mi>n</mi> <mrow> <mo>(</mo> <mo>&amp;Sigma;</mo> <msup> <mi>x</mi> <mn>2</mn> </msup> <mo>)</mo> </mrow> <mo>-</mo> <msup> <mrow> <mo>(</mo> <mo>&amp;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+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, and Y is Predicting Stock Price, X are forecast date.
  4. 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. 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. 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. 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. 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. 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.
  10. 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 pre-processed 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.
CN201710620881.0A 2017-07-26 2017-07-26 Stock trend forecasting method and system Pending CN107368925A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710620881.0A CN107368925A (en) 2017-07-26 2017-07-26 Stock trend forecasting method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710620881.0A CN107368925A (en) 2017-07-26 2017-07-26 Stock trend forecasting method and system

Publications (1)

Publication Number Publication Date
CN107368925A true CN107368925A (en) 2017-11-21

Family

ID=60307232

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710620881.0A Pending CN107368925A (en) 2017-07-26 2017-07-26 Stock trend forecasting method and system

Country Status (1)

Country Link
CN (1) CN107368925A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108090625A (en) * 2017-12-31 2018-05-29 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) * 2018-09-25 2019-03-01 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) * 2018-12-28 2019-06-07 北京邮电大学 A kind of prediction technique and device
CN110263843A (en) * 2019-06-18 2019-09-20 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) * 2021-01-22 2021-04-30 上海鎏量科技有限公司 Trend device implementation method for transaction investment and transaction investment method

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108090625A (en) * 2017-12-31 2018-05-29 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) * 2018-09-25 2019-03-01 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) * 2018-09-25 2023-04-18 平安科技(深圳)有限公司 Method and device for detecting slow-falling data, electronic equipment and storage medium
CN109859039A (en) * 2018-12-28 2019-06-07 北京邮电大学 A kind of prediction technique and device
CN110263843A (en) * 2019-06-18 2019-09-20 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) * 2021-01-22 2021-04-30 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
Xiao et al. Asymmetric impacts of oil price uncertainty on Chinese stock returns under different market conditions: Evidence from oil volatility index
CN107368925A (en) Stock trend forecasting method and system
Yin et al. Predicting the oil prices: do technical indicators help?
Hahn et al. Value-based performance and risk management in supply chains: A robust optimization approach
Choudhury et al. A real time clustering and SVM based price-volatility prediction for optimal trading strategy
Liao et al. Investment project valuation based on a fuzzy binomial approach
Norouzi et al. Black gold falls, black plague arise-An Opec crude oil price forecast using a gray prediction model
Md et al. Novel optimization approach for stock price forecasting using multi-layered sequential LSTM
WO2009014756A1 (en) Systems, methods and computer program products for creating a turnover efficient frontier for an investment portfolio
Lim et al. Dynamic portfolio rebalancing through reinforcement learning
Huang et al. CAViaR-based forecast for oil price risk
McAleer et al. Value-at-Risk for country risk ratings
CN107679987A (en) Asset Allocation strategy acquisition methods, device, computer equipment and storage medium
Li et al. The stock–bond comovements and cross-market trading
Li et al. Take Bitcoin into your portfolio: a novel ensemble portfolio optimization framework for broad commodity assets
Clintworth et al. Combining multicriteria decision analysis and cost–benefit analysis in the assessment of maritime projects financed by the European Investment Bank
Aigbovo et al. The impact of macroeconomic variables on stock market index in Nigeria
Zhong et al. Novel indexes based on network structure to indicate financial market
Zhao et al. Optimal effort under high-water mark contracts
JP2010134840A (en) Future financial prediction system, future financial prediction method, and future financial prediction program
Malyscheff et al. Natural gas storage valuation via least squares Monte Carlo and support vector regression
Kutynina et al. Aggregation of forecasts and recommendations of financial analysts in the framework of evidence theory
Cheriyan et al. A dynamical systems model of price bubbles and cycles
Xu et al. Comonotonic approximation to periodic investment problems under stochastic drift
Demary Yield curve responses to market sentiments and monetary policy

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