CN105989535A - Stock fluctuation ratio predicting method and system - Google Patents
Stock fluctuation ratio predicting method and system Download PDFInfo
- Publication number
- CN105989535A CN105989535A CN201510067921.4A CN201510067921A CN105989535A CN 105989535 A CN105989535 A CN 105989535A CN 201510067921 A CN201510067921 A CN 201510067921A CN 105989535 A CN105989535 A CN 105989535A
- Authority
- CN
- China
- Prior art keywords
- stock
- risk
- factor
- return
- movement
- 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
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a stock fluctuation ratio predicting method and system. The method comprises the following steps that a stock risk control model database is established according to exchange quotation data of stocks during closing each day; an input stock code and the market weight occupied by a stock corresponding to the stock code are received, and start and end time of price trend of the stock is set; a risk control parameter which is calculated according to the exchange quotation data during closing in the last day in advance is read from the risk control model database; and the fluctuation ratio of the stock and a stock investment combination from the start time to the end time of the price trend is calculated according to the stock code, the market weight occupied by the stock corresponding to the stock code, the start and end time of the price trend of the stock and/or the risk control parameter. The stock fluctuation ratio predicting system can be used to reduce calculation time greatly, and is high in the calculation precision due to the fact that historical data needed for calculating values of each part is less than that needed by RiskMetrics.
Description
Technical field
The present invention relates to technical field of information processing, particularly relate to a kind of movement in stock and share rate prediction side
Method and system.
Background technology
Movement in stock and share rate (i.e. the variance of stock yield) is the conventional finger of tolerance stock market risk
Mark, stability bandwidth is real-time change, and Chinese scholars constructs the statistical model of various complexity and comes
Catch the time variation of stability bandwidth.
The mode of covariance matrix, referred to as RiskMetrics between stock is calculated based on historical data
Method, utilizes the method to calculate the process of covariance matrix between stock to be:
The historical yield assuming m stock is y1, y2 ... yn, wherein, when yi characterizes i
Carve the earning rate between m stock (yi is the column vector of m × 1).
Illustrate the estimated value of covariance matrix between m stock of next phase, utilize this estimation
Value can calculate any investment combination that this m stock constituted stability bandwidth in next phase.
The covariance matrix between the stock that RiskMetrics method provides is utilized to calculate stock ripple
During dynamic rate, exist and the investment combination comprising more stock needed to utilize too much historical data,
When market changes, the parameter of estimation is too much, needs to use longer historical data, and golden
Melting turn of the market quickly, the distribution of current market and historical data is different, and by shorter data
Estimate, estimate that data are the most accurate.It addition, utilize RiskMetrics method to make Data expansion
Property poor, calculate the stability bandwidth of different investment combinations every time, data to prepare again, again counts
Calculate, spend the more time.
Summary of the invention
In view of current stability bandwidth calculates above shortcomings, the present invention provides a kind of movement in stock and share
Rate Forecasting Methodology and system, user needs to obtain stock and the fluctuation of stock portfolio of input
During rate only need to from risk control model data base called data, carry out calculating i.e. according to these data
Can, greatly reduce calculating time, and required historical data during owing to calculating each several part numerical value
Few compared with RiskMetrics method, counting accuracy is high.
For reaching above-mentioned purpose, embodiments of the invention adopt the following technical scheme that
A kind of movement in stock and share rate Forecasting Methodology, described movement in stock and share rate Forecasting Methodology includes walking as follows
Rapid:
When closing every day according to each stock, exchange quotation data set up Stock Risk Controlling model data
Storehouse;
Receive the stock code inputted, the plate weight that stock code is corresponding, stock price is set and walks
The beginning and ending time of gesture;
Exchange quotation data when closing are read previously according to proxima luce (prox. luc) from risk control model data base
The risk control parameter value calculated;
According to stock code, plate weight that stock code is corresponding, the start-stop of stock price tendency
Time and Stock Risk control parameter value calculation and go out stock and/or stock portfolio at stock valency
Stability bandwidth in the beginning and ending time of lattice tendency.
According to one aspect of the present invention, described exchange quotation number when closing every day according to each stock
According to setting up, Stock Risk Controlling model database steps specifically includes following steps: collect each stock
Exchange quotation data when ticket is closed every day;When closing every day according to each stock, exchange quotation data are true
Determine the Stock Risk factor;Exchange quotation data and the Stock Risk factor when closing every day according to stock
Determine that the factor return in the profit return rate of stock and profit return rate and residual error are returned;According to
Factor return, residual error return calculate covariance matrix and the residual error stability bandwidth of factor return;Right
The Stock Risk factor, factor return, the covariance matrix of factor return and the residual error calculated
Stability bandwidth carries out process and forms Stock Risk control parameter value;Control according to each Stock Risk every day
Parameter value sets up risk control model data base.
According to one aspect of the present invention, described according to stock code, plate that stock code is corresponding
Block weight, the beginning and ending time of stock price tendency and Stock Risk control parameter value calculation and go out stock
And/or the stability bandwidth step that stock portfolio is within the beginning and ending time of stock price tendency performs
Rear execution following steps: according to stock and stock portfolio when the start-stop of stock price tendency
Interior stability bandwidth obtains the slow line of stock price amount of increase, middling speed line and high-speed line, it is judged that
Ceiling price that stock is most preferably bought in a little and sold and lowest price.
A kind of movement in stock and share rate prognoses system, described movement in stock and share rate prognoses system includes:
Risk control DBM, during for closing every day according to each stock, exchange quotation data are built
Vertical Stock Risk Controlling model data base;
Stock information receiver module, is used for the plate receiving the stock code of input, stock code is corresponding
Block weight, arranges the beginning and ending time of stock price tendency;
Risk control parameter value acquisition module, for reading root in advance from risk control model data base
The risk control parameter value that when closing according to proxima luce (prox. luc), exchange quotation data calculate;
Stability bandwidth computing module, for according to stock code, plate weight that stock code is corresponding,
The beginning and ending time of stock price tendency and/or Stock Risk control parameter value calculation and go out stock and stock
Ticket investment combination stability bandwidth within the beginning and ending time of stock price tendency.
According to one aspect of the present invention, described movement in stock and share rate prognoses system also includes: stock
Transaction data acquisition module, is used for collecting exchange quotation data when each stock is closed every day.
According to one aspect of the present invention, described movement in stock and share rate prognoses system also includes: risk
The factor determines module, and during for closing every day according to each stock, exchange quotation data determine stock wind
The danger factor.
According to one aspect of the present invention, described movement in stock and share rate prognoses system also includes: income
Return determines module, during for closing every day according to stock exchange quotation data and Stock Risk because of
Son determines that the factor return in the profit return rate of stock and profit return rate and residual error are returned.
According to one aspect of the present invention, described movement in stock and share rate prognoses system also includes: association side
Difference matrix calculus module, for calculating the covariance matrix of factor return according to factor return report.
According to one aspect of the present invention, described movement in stock and share rate prognoses system also includes: residual error
Stability bandwidth computing module, for calculating the residual error stability bandwidth of stock according to residual error return.
According to one aspect of the present invention, described movement in stock and share rate prognoses system also includes: risk
Control parameter and form module, for the Stock Risk factor calculated, factor return, the factor
The covariance matrix of return and residual error stability bandwidth carry out process and form Stock Risk control parameter
Value.
The advantage that the present invention implements: during by closing every day according to each stock, exchange quotation data are set up
Stock Risk Controlling model data base;Receive the stock code inputted, the plate that stock code is corresponding
Weight, arranges the beginning and ending time of stock price tendency;Read in advance from risk control model data base
The risk control parameter value that when closing according to proxima luce (prox. luc), exchange quotation data calculate;According to stock generation
Code, plate weight, the beginning and ending time of stock price tendency and the Stock Risk control that stock code is corresponding
Parameter value calculation processed goes out stock and/or stock portfolio within the beginning and ending time of stock price tendency
Stability bandwidth, use movement in stock and share rate prognoses system, user need obtain input stock and stock
During the stability bandwidth of investment combination only need to from risk control model data base called data, according to this number
Calculate according to carrying out, greatly reduce the calculating time, and owing to calculating each several part numerical value time institute
Needing historical data few compared with RiskMetrics method, counting accuracy is high.
Accompanying drawing explanation
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, below will be to embodiment
The accompanying drawing used required in is briefly described, it should be apparent that, the accompanying drawing in describing below
It is only some embodiments of the present invention, for those of ordinary skill in the art, is not paying
On the premise of going out creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the method for the embodiment 1 of a kind of movement in stock and share rate Forecasting Methodology of the present invention
Flow chart;
Fig. 2 is the method for the embodiment 2 of a kind of movement in stock and share rate Forecasting Methodology of the present invention
Flow chart;
Fig. 3 is the structural representation of a kind of movement in stock and share rate prognoses system of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, to the technical side in the embodiment of the present invention
Case is clearly and completely described, it is clear that described embodiment is only the present invention one
Divide embodiment rather than whole embodiments.Based on the embodiment in the present invention, this area is general
The every other embodiment that logical technical staff is obtained under not making creative work premise,
Broadly fall into the scope of protection of the invention.
Embodiment 1:
As it is shown in figure 1, movement in stock and share rate Forecasting Methodology, described movement in stock and share rate Forecasting Methodology bag
Include following steps:
Step S1: when closing every day according to each stock, exchange quotation data are set up Stock Risk and controlled mould
Type data base;
Described step S1: when closing every day according to each stock, exchange quotation data set up Stock Risk
Controlling model database steps specifically includes following steps: collect when each stock is closed every day and hand over
Easily market data;When closing every day according to each stock exchange quotation data determine Stock Risk because of
Son;When closing every day according to stock, exchange quotation data and the Stock Risk factor determine the receipts of stock
Factor return and residual error in benefit return rate and profit return rate are returned;According to the factor return, residual
Difference return calculates covariance matrix and the residual error stability bandwidth of factor return;To the stock calculated
At the return of risks and assumptions, the factor, the covariance matrix of factor return and residual error stability bandwidth
Reason forms Stock Risk and controls parameter value;Control parameter value according to each Stock Risk every day and set up wind
Danger Controlling model data base.
Due to movement in stock and share rate prognoses system can every day the automatic calculation risk factor, Stock Risk
The factor return of the factor, the covariance matrix of factor return and residual error stability bandwidth data value, and
Being automatically credited risk control model data base, user needs to obtain the stability bandwidth of the investment combination of input
Time only need to from risk control model data base called data, calculate according to these data.
Covariance matrix according to formula y=Xf+ ε calculating factor return and residual error stability bandwidth, wherein,
Y represents that in stock pond, the super risk free rate income of stock, the i.e. return of stock deduct devoid of risk profit
Rate, be can every day from day frequency transaction data in personal share earning rate extracting directly out, X
Representing the value of the Stock Risk factor, when can close every day according to each stock, exchange quotation data determine,
F represent the soluble part of the Stock Risk factor the factor return, ε represent can not by Stock Risk because of
Son is explained the residual error return of part.
Covariance matrix by formula calculating factor return as described below:
Wherein, fi represents the factor return of the i moment Stock Risk factor, i ∈ [0, T], λ table
Show the rate of decay of the weight that the factor returns, and long half-lift L corresponding relation meet: L is equal to
The integer part of-log2 (λ), for the T+1 moment the Stock Risk factor the factor return association side
Difference matrix.
According to y=Xf+ ε, the super risk free rate income statement of stock is shown as two parts, then phases
Answering, the covariance matrix of y can be expressed as Cov (y):
Cov (y)=XFXT+ Δ, it can be seen that Cov (y) is divided into two parts:
Wherein, F=Cov (f) is the covariance matrix of factor return, and Δ is the residual error stability bandwidth of stock
Matrix:
Wherein, δ 1 is the residual error stability bandwidth of first stock, and δ n is the residual error of n-th stock
Stability bandwidth.
Before implementing the calculating of residual error stability bandwidth, the residual error return ε t first obtained recurrence is carried out
Stationarity, testing for auto-correlatedness, find to there is autocorrelation and partial correlation between sequence through inspection,
And residual error returns not standard normal distribution, present the trend of spike thickness tail, therefore take GARCH
Residual error stability bandwidth is estimated by method, and adjusts through investigating the stability bandwidth estimated through GARCH
After the obedience white-noise process really of residual error.Estimation formulas is following, and (wherein, σ t is stock
Residual error stability bandwidth): ε t=μ+ζ t wherein, ζ t=σ tzt, σ
T2=κ+γ σ t-12+ α ζ t-12, k > 0, ε t are residual error return.σ t is that residual error is returned at t
The residual error stability bandwidth in moment, zt is normal distribution, and κ, γ, α are the parameter in GARCH, by
Residual error historical data is estimated to obtain.
It was verified that a), σ and the residual error stability bandwidth of a upper phase and the residual error ripple of its delayed phase
Dynamic rate is relevant, it is adaptable to the long-term autocorrelation process of stability bandwidth, has measured its volatility clustering effect.
Step S2: receive the stock code inputted, the plate weight that stock code is corresponding, stock is set
The beginning and ending time of ticket price trend;
During investor structure investment combination, can input in movement in stock and share rate prognoses system and treat structure
The stock code of each stock in the investment combination made, the stock code in investment combination is corresponding
Plate weight, and need beginning and ending time of stability bandwidth of prediction, wherein in this investment combination
A stock can be included, it is also possible to include many stocks.
Step S3: read transaction when closing previously according to proxima luce (prox. luc) from risk control model data base
The risk control parameter value that market data calculate;
Risk control parameter includes the Stock Risk factor, the factor return of the Stock Risk factor, the factor
The covariance matrix of return and residual error stability bandwidth, described residual error stability bandwidth is can not be by Stock Risk
The stability bandwidth of the factor explained part return.
Step S4: walk according to stock code, plate weight that stock code is corresponding, stock price
The beginning and ending time of gesture and Stock Risk control parameter value calculation and go out stock and/or stock portfolio
Stability bandwidth within the beginning and ending time of stock price tendency.
The Stock Risk factor, the factor of the Stock Risk factor it is calculated respectively according to basic data
Return, the covariance matrix of factor return and residual error stability bandwidth, and it is deposited into risk control
Model database, in case follow-up according to each stock code in the investment combination of user's input, each
Weight that stock code is corresponding, beginning and ending time carry out the calculating of movement in stock and share rate, to help investment
Person formulates investment combination.Certainly, follow-up according to those data, and the investment group of user's input
Stock code in conjunction, a certain date to setting, calculate the stock code pair in investment combination
The covariance matrix of the stock answered, in conjunction with the Alpha that the stock code in investment combination is corresponding
Alpha value carries out stock performance analysis and performance classification, Reasons, naturally it is also possible to carry out risk attribution
Analyzing and risk analysis, investor can utilize the prior art of some maturations according to analysis result
Determine the weight of each stock in investment combination, to adjust investment tactics.Wherein, stock is being carried out
During ticket profit return, the return that stock yield return factorized returns two parts with residual error,
Factorize the calculating of covariance matrix of return and residual error by the calculating of stock covariance matrix
The calculating of stability bandwidth, owing to the dependency relation between the income of many stocks changes greatly, but
Relation between the factor and the factor is the most stable, thus calculates the covariance matrix institute of stock
The historical data needed is shorter;Secondly as the factor is the most less relative to the number of stock,
As estimated the covariance matrix of 1000 stocks, need to estimate 1000 × 1000/2 parameters,
And if choose 34 factors, only need to estimate 34 × 34/2+1000 parameter, substantially reduce
Estimator, because estimating more accurate.
During by closing every day according to each stock, exchange quotation data set up Stock Risk Controlling model
Data base;Receive the stock code inputted, the plate weight that stock code is corresponding, stock is set
The beginning and ending time of price trend;Read from risk control model data base and receive previously according to proxima luce (prox. luc)
The risk control parameter value that during dish, exchange quotation data calculate;According to stock code, stock generation
Plate weight, the beginning and ending time of stock price tendency and Stock Risk that code is corresponding control parameter value
Calculate stock and/or the stock portfolio fluctuation within the beginning and ending time of stock price tendency
Rate, by above-mentioned steps, user needs to obtain stock and the fluctuation of stock portfolio of input
During rate only need to from risk control model data base called data, carry out calculating i.e. according to these data
Can, greatly reduce calculating time, and required historical data during owing to calculating each several part numerical value
Few compared with RiskMetrics method, counting accuracy is high.
Embodiment 2:
As in figure 2 it is shown, a kind of movement in stock and share rate Forecasting Methodology, described movement in stock and share rate prediction side
Method comprises the steps:
Step S1: when closing every day according to each stock, exchange quotation data are set up Stock Risk and controlled mould
Type data base;
Described step S1: when closing every day according to each stock, exchange quotation data set up Stock Risk
Controlling model database steps specifically includes following steps: collect when each stock is closed every day and hand over
Easily market data;When closing every day according to each stock exchange quotation data determine Stock Risk because of
Son;When closing every day according to stock, exchange quotation data and the Stock Risk factor determine the receipts of stock
Factor return and residual error in benefit return rate and profit return rate are returned;According to the factor return, residual
Difference return calculates covariance matrix and the residual error stability bandwidth of factor return;To the stock calculated
At the return of risks and assumptions, the factor, the covariance matrix of factor return and residual error stability bandwidth
Reason forms Stock Risk and controls parameter value;Control parameter value according to each Stock Risk every day and set up wind
Danger Controlling model data base.
Due to movement in stock and share rate prognoses system can every day the automatic calculation risk factor, Stock Risk
The factor return of the factor, the covariance matrix of factor return and residual error stability bandwidth data value, and
Being automatically credited risk control model data base, user needs to obtain the stability bandwidth of the investment combination of input
Time only need to from risk control model data base called data, calculate according to these data.
Covariance matrix according to formula y=Xf+ ε calculating factor return and residual error stability bandwidth, wherein,
Y represents that in stock pond, the super risk free rate income of stock, the i.e. return of stock deduct devoid of risk profit
Rate, be can every day from day frequency transaction data in personal share earning rate extracting directly out, X
Representing the value of the Stock Risk factor, when can close every day according to each stock, exchange quotation data determine,
F represent the soluble part of the Stock Risk factor the factor return, ε represent can not by Stock Risk because of
Son is explained the residual error return of part.
Covariance matrix by formula calculating factor return as described below:
Wherein, fi represents the factor return of the i moment Stock Risk factor, i ∈ [0, T], λ table
Show the rate of decay of the weight that the factor returns, and long half-lift L corresponding relation meet: L is equal to
The integer part of-log2 (λ), for the T+1 moment the Stock Risk factor the factor return association side
Difference matrix.
According to y=Xf+ ε, the super risk free rate income statement of stock is shown as two parts, then phases
Answering, the covariance matrix of y can be expressed as Cov (y):
Cov (y)=XFXT+ Δ, it can be seen that Cov (y) is divided into two parts:
Wherein, F=Cov (f) is the covariance matrix of factor return, and Δ is the residual error stability bandwidth of stock
Matrix:
Wherein, δ 1 is the residual error stability bandwidth of first stock, and δ n is the residual error of n-th stock
Stability bandwidth.
Before implementing the calculating of residual error stability bandwidth, the residual error return ε t first obtained recurrence is carried out
Stationarity, testing for auto-correlatedness, find to there is autocorrelation and partial correlation between sequence through inspection,
And residual error returns not standard normal distribution, present the trend of spike thickness tail, therefore take GARCH
Residual error stability bandwidth is estimated by method, and adjusts through investigating the stability bandwidth estimated through GARCH
After the obedience white-noise process really of residual error.Estimation formulas is following, and (wherein, σ t is stock
Residual error stability bandwidth): ε t=μ+ζ t wherein, ζ t=σ tzt, σ
T2=κ+γ σ t-12+ α ζ t-12, k > 0, ε t are residual error return.σ t is that residual error is returned at t
The residual error stability bandwidth in moment, zt is normal distribution, and κ, γ, α are the parameter in GARCH, by
Residual error historical data is estimated to obtain.
It was verified that a), σ and the residual error stability bandwidth of a upper phase and the residual error ripple of its delayed phase
Dynamic rate is relevant, it is adaptable to the long-term autocorrelation process of stability bandwidth, has measured its volatility clustering effect.
Step S2: receive the stock code inputted, the plate weight that stock code is corresponding, stock is set
The beginning and ending time of ticket price trend;
During investor structure investment combination, can input in movement in stock and share rate prognoses system and treat structure
The stock code of each stock in the investment combination made, the stock code in investment combination is corresponding
Plate weight, and need beginning and ending time of stability bandwidth of prediction, wherein in this investment combination
A stock can be included, it is also possible to include many stocks.
Step S3: read transaction when closing previously according to proxima luce (prox. luc) from risk control model data base
The risk control parameter value that market data calculate;
Risk control parameter includes the Stock Risk factor, the factor return of the Stock Risk factor, the factor
The covariance matrix of return and residual error stability bandwidth, described residual error stability bandwidth is can not be by Stock Risk
The stability bandwidth of the factor explained part return.
Step S4: walk according to stock code, plate weight that stock code is corresponding, stock price
The beginning and ending time of gesture and Stock Risk control parameter value calculation and go out stock and/or stock portfolio
Stability bandwidth within the beginning and ending time of stock price tendency.
The Stock Risk factor, the factor of the Stock Risk factor it is calculated respectively according to basic data
Return, the covariance matrix of factor return and residual error stability bandwidth, and it is deposited into risk control
Model database, in case follow-up according to each stock code in the investment combination of user's input, each
Weight that stock code is corresponding, beginning and ending time carry out the calculating of movement in stock and share rate, to help investment
Person formulates investment combination.Certainly, follow-up according to those data, and the investment group of user's input
Stock code in conjunction, a certain date to setting, calculate the stock code pair in investment combination
The covariance matrix of the stock answered, in conjunction with the Alpha that the stock code in investment combination is corresponding
Alpha value carries out stock performance analysis and performance classification, Reasons, naturally it is also possible to carry out risk attribution
Analyzing and risk analysis, investor can utilize the prior art of some maturations according to analysis result
Determine the weight of each stock in investment combination, to adjust investment tactics.Wherein, stock is being carried out
During ticket profit return, the return that stock yield return factorized returns two parts with residual error,
Factorize the calculating of covariance matrix of return and residual error by the calculating of stock covariance matrix
The calculating of stability bandwidth, owing to the dependency relation between the income of many stocks changes greatly, but
Relation between the factor and the factor is the most stable, thus calculates the covariance matrix institute of stock
The historical data needed is shorter;Secondly as the factor is the most less relative to the number of stock,
As estimated the covariance matrix of 1000 stocks, need to estimate 1000 × 1000/2 parameters,
And if choose 34 factors, only need to estimate 34 × 34/2+1000 parameter, substantially reduce
Estimator, because estimating more accurate.
Step S5: according to stock and stock portfolio within the beginning and ending time of stock price tendency
Stability bandwidth obtain the slow line of stock price amount of increase, middling speed line and high-speed line, it is judged that stock
The ceiling price most preferably bought in a little and sell and lowest price.
A kind of embodiment of movement in stock and share rate prognoses system:
A kind of movement in stock and share rate prognoses system, described movement in stock and share rate prognoses system includes:
Risk control DBM 1, exchange quotation data during for closing every day according to each stock
Set up Stock Risk Controlling model data base;
Stock information receiver module 2 is corresponding for receiving the stock code of input, stock code
Plate weight, arranges the beginning and ending time of stock price tendency;
Risk control parameter value acquisition module 3, for reading in advance from risk control model data base
The risk control parameter value that when closing according to proxima luce (prox. luc), exchange quotation data calculate;
Stability bandwidth computing module 4, for according to stock code, plate weight that stock code is corresponding,
The beginning and ending time of stock price tendency and Stock Risk control parameter value calculation and go out stock and/or stock
Ticket investment combination stability bandwidth within the beginning and ending time of stock price tendency.
In an embodiment, movement in stock and share rate prognoses system also includes: stock exchange data obtains mould
Block 5, is used for collecting exchange quotation data when each stock is closed every day.
In an embodiment, movement in stock and share rate prognoses system also includes: risks and assumptions determines module 6,
During for closing every day according to each stock, exchange quotation data determine the Stock Risk factor.
In an embodiment, movement in stock and share rate prognoses system also includes: profit return determines module 7,
During for closing every day according to stock, exchange quotation data and the Stock Risk factor determine the receipts of stock
Factor return and residual error in benefit return rate and profit return rate are returned.
In an embodiment, movement in stock and share rate prognoses system also includes: covariance matrix computing module 8,
For calculating the covariance matrix of factor return according to factor return report.
In an embodiment, movement in stock and share rate prognoses system also includes: residual error stability bandwidth computing module 9,
For calculating the residual error stability bandwidth of stock according to residual error return.
In an embodiment, movement in stock and share rate prognoses system also includes: risk control parameter forms mould
Block 10, for the Stock Risk factor calculated, factor return, the covariance of factor return
Matrix and residual error stability bandwidth carry out process and form Stock Risk control parameter value.
The advantage that the present invention implements: during by closing every day according to each stock, exchange quotation data are built
Vertical Stock Risk Controlling model data base;The stock code of reception input, stock code are corresponding
Plate weight, arranges the beginning and ending time of stock price tendency;Read from risk control model data base
Take the risk control parameter value that when closing, exchange quotation data calculate previously according to proxima luce (prox. luc);Root
According to stock code, plate weight that stock code is corresponding, the beginning and ending time of stock price tendency and
Stock Risk controls parameter value calculation and goes out stock and/or stock portfolio in stock price tendency
Beginning and ending time in stability bandwidth, use movement in stock and share rate prognoses system, user needs to obtain defeated
Only need to adjust from risk control model data base during the stability bandwidth of the stock that enters and stock portfolio
Fetch data, carry out calculating according to these data, greatly reduce the calculating time, and due to
When calculating each several part numerical value, required historical data is few compared with RiskMetrics method, counting accuracy
High.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is also
Being not limited to this, any those skilled in the art is at technology model disclosed by the invention
In enclosing, the change that can readily occur in or replacement, all should contain within protection scope of the present invention.
Therefore, protection scope of the present invention should be as the criterion with described scope of the claims.
Claims (10)
1. a movement in stock and share rate Forecasting Methodology, it is characterised in that described movement in stock and share rate is predicted
Method comprises the steps:
When closing every day according to each stock, exchange quotation data set up Stock Risk Controlling model data
Storehouse;
Receive the stock code inputted, the plate weight that stock code is corresponding, stock price is set and walks
The beginning and ending time of gesture;
Exchange quotation data when closing are read previously according to proxima luce (prox. luc) from risk control model data base
The risk control parameter value calculated;
According to stock code, plate weight that stock code is corresponding, stock price tendency start-stop time
Between and Stock Risk control parameter value calculation and go out stock and/or stock portfolio is walked in stock price
Stability bandwidth in the beginning and ending time of gesture.
Movement in stock and share rate Forecasting Methodology the most according to claim 1, it is characterised in that institute
State exchange quotation data when closing every day according to each stock and set up Stock Risk Controlling model data base
Step specifically includes following steps: collect exchange quotation data when each stock is closed every day;Root
When closing every day according to each stock, exchange quotation data determine the Stock Risk factor;According to stock every day
During closing quotation, exchange quotation data and the Stock Risk factor determine that the profit return rate of stock and income are returned
Factor return and residual error in report rate are returned;The factor is calculated according to factor return, residual error return
The covariance matrix of return and residual error stability bandwidth;The Stock Risk factor calculated, the factor are returned
The covariance matrix of report, factor return and residual error stability bandwidth carry out process and form Stock Risk control
Parameter value processed;Control parameter value according to each Stock Risk every day and set up risk control model data base.
3. according to the movement in stock and share rate Forecasting Methodology one of claim 1 to 2 Suo Shu, its feature
It is, described according to stock code, plate weight that stock code is corresponding, stock price tendency
Beginning and ending time and Stock Risk control parameter value calculation go out stock and stock portfolio at stock
Stability bandwidth step in the beginning and ending time of price trend performs following steps after performing: according to stock
And the stability bandwidth that stock portfolio is within the beginning and ending time of stock price tendency obtains stock price
The slow line of amount of increase, middling speed line and high-speed line, it is judged that stock is most preferably bought in a little and sells
High price and lowest price.
4. a movement in stock and share rate prognoses system, it is characterised in that described movement in stock and share rate is predicted
System includes:
Risk control DBM, during for closing every day according to each stock, exchange quotation data are built
Vertical Stock Risk Controlling model data base;
Stock information receiver module, is used for the plate receiving the stock code of input, stock code is corresponding
Block weight, arranges the beginning and ending time of stock price tendency;
Risk control parameter value acquisition module, for reading root in advance from risk control model data base
The risk control parameter value that when closing according to proxima luce (prox. luc), exchange quotation data calculate;
Stability bandwidth computing module, for according to stock code, plate weight that stock code is corresponding,
The beginning and ending time of stock price tendency and/or Stock Risk control parameter value calculation go out stock and/or
Stock portfolio stability bandwidth within the beginning and ending time of stock price tendency.
Movement in stock and share rate prognoses system the most according to claim 4, it is characterised in that institute
State movement in stock and share rate prognoses system also to include: stock exchange data acquisition module, be used for collecting respectively
Exchange quotation data when stock is closed every day.
Movement in stock and share rate prognoses system the most according to claim 5, it is characterised in that institute
State movement in stock and share rate prognoses system also to include: risks and assumptions determines module, for every according to each stock
During day closing quotation, exchange quotation data determine the Stock Risk factor.
Movement in stock and share rate prognoses system the most according to claim 6, it is characterised in that institute
State movement in stock and share rate prognoses system also to include: profit return determines module, for every according to stock
During day closing quotation, exchange quotation data and the Stock Risk factor determine profit return rate and the income of stock
Factor return and residual error in return rate are returned.
Movement in stock and share rate prognoses system the most according to claim 7, it is characterised in that institute
State movement in stock and share rate prognoses system also to include: covariance matrix computing module, for according to the factor
Return report calculates the covariance matrix of factor return.
Movement in stock and share rate prognoses system the most according to claim 8, it is characterised in that institute
State movement in stock and share rate prognoses system also to include: residual error stability bandwidth computing module, for according to residual error
Return calculates the residual error stability bandwidth of stock.
Movement in stock and share rate prognoses system the most according to claim 9, it is characterised in that
Described movement in stock and share rate prognoses system also includes: risk control parameter formed module, by based on
The Stock Risk factor, factor return, the covariance matrix of factor return and the residual error ripple calculated
Dynamic rate carries out process and forms Stock Risk control parameter value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510067921.4A CN105989535A (en) | 2015-02-10 | 2015-02-10 | Stock fluctuation ratio predicting method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510067921.4A CN105989535A (en) | 2015-02-10 | 2015-02-10 | Stock fluctuation ratio predicting method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105989535A true CN105989535A (en) | 2016-10-05 |
Family
ID=57041586
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510067921.4A Pending CN105989535A (en) | 2015-02-10 | 2015-02-10 | Stock fluctuation ratio predicting method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105989535A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106557313A (en) * | 2016-10-13 | 2017-04-05 | 广州新博庭网络信息科技股份有限公司 | One kind represents business object method and apparatus in vocational window |
CN108830721A (en) * | 2018-06-27 | 2018-11-16 | 兴证期货有限公司 | A kind of novel quoting model changed based on option implied volatility |
CN109684378A (en) * | 2018-12-14 | 2019-04-26 | 北京向上一心科技有限公司 | Data screening method, method for exhibiting data, device, equipment and storage medium |
CN110717663A (en) * | 2019-09-27 | 2020-01-21 | 广东奥园奥买家电子商务有限公司 | Market quotation automatic staring method, device and equipment |
CN111080446A (en) * | 2019-12-02 | 2020-04-28 | 泰康保险集团股份有限公司 | Data processing method and device |
WO2020087791A1 (en) * | 2018-10-30 | 2020-05-07 | 平安科技(深圳)有限公司 | Fund information analysis method and apparatus, storage medium, and computer device |
-
2015
- 2015-02-10 CN CN201510067921.4A patent/CN105989535A/en active Pending
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106557313A (en) * | 2016-10-13 | 2017-04-05 | 广州新博庭网络信息科技股份有限公司 | One kind represents business object method and apparatus in vocational window |
CN108830721A (en) * | 2018-06-27 | 2018-11-16 | 兴证期货有限公司 | A kind of novel quoting model changed based on option implied volatility |
WO2020087791A1 (en) * | 2018-10-30 | 2020-05-07 | 平安科技(深圳)有限公司 | Fund information analysis method and apparatus, storage medium, and computer device |
CN109684378A (en) * | 2018-12-14 | 2019-04-26 | 北京向上一心科技有限公司 | Data screening method, method for exhibiting data, device, equipment and storage medium |
CN110717663A (en) * | 2019-09-27 | 2020-01-21 | 广东奥园奥买家电子商务有限公司 | Market quotation automatic staring method, device and equipment |
CN111080446A (en) * | 2019-12-02 | 2020-04-28 | 泰康保险集团股份有限公司 | Data processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105989535A (en) | Stock fluctuation ratio predicting method and system | |
CN103455943B (en) | Stock or stock investment portfolio volatility prediction method and device | |
Keane et al. | The solution and estimation of discrete choice dynamic programming models by simulation and interpolation: Monte Carlo evidence | |
CN108536652A (en) | A kind of short-term vehicle usage amount prediction technique based on arma modeling | |
Smith | Weighted median inflation: is this core inflation? | |
CN106779859A (en) | A kind of real-time Method for Sales Forecast method of mobile terminal product | |
CN105574607A (en) | Electricity market monthly electricity utilization prediction method | |
Billio et al. | Combination schemes for turning point predictions | |
CN105305426B (en) | Mapreduce two-step short-period load prediction method based on deviation control mechanism | |
CN110047291A (en) | A kind of Short-time Traffic Flow Forecasting Methods considering diffusion process | |
CN110457867A (en) | A kind of time series data based on machine learning is filled up and restoring method | |
CN106600037A (en) | Multi-parameter auxiliary load forecasting method based on principal component analysis | |
Laforte | Pricing models: a Bayesian DSGE approach for the US economy | |
Girardi et al. | The role of indicator selection in nowcasting euro-area GDP in pseudo-real time | |
CN103236013A (en) | Stock market data analysis method based on key stock set identification | |
CN105550772A (en) | Online historical data tendency analysis method | |
CN105389637A (en) | Effective workday construction method for monthly electricity consumption prediction model | |
CN102912760A (en) | Lowest navigable water level generating method of downstream river of reservoir | |
CN103605493A (en) | Parallel sorting learning method and system based on graphics processing unit | |
CN105354644A (en) | Financial time series prediction method based on integrated empirical mode decomposition and 1-norm support vector machine quantile regression | |
Budinski-Petković et al. | Fractal properties of financial markets | |
Rao et al. | An Econometric Approach to the Construction of Complete Panels of Purchasing Power Parities | |
CN116166886A (en) | Application system of vector index smoothing new classification method in season time sequence prediction | |
CN108665090A (en) | Urban distribution network saturation load forecasting method based on principal component analysis Yu Verhulst models | |
Grant et al. | Measuring the output gap using stochastic model specification search |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161005 |
|
WD01 | Invention patent application deemed withdrawn after publication |