CN110084400A - Information forecasting method, device, computer equipment and storage medium - Google Patents
Information forecasting method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110084400A CN110084400A CN201910217866.0A CN201910217866A CN110084400A CN 110084400 A CN110084400 A CN 110084400A CN 201910217866 A CN201910217866 A CN 201910217866A CN 110084400 A CN110084400 A CN 110084400A
- Authority
- CN
- China
- Prior art keywords
- foreign exchange
- data
- base values
- index
- reserve
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves big data processing field, in particular to a kind of information forecasting method, device, computer equipment and storage medium.The described method includes: obtaining the growth rate score of foreign exchange reserve in predetermined period, and obtain the corresponding base values data of each base values one by one from base values library；Calculate separately each base values data and the related coefficient increased between rate score；The base values data with the foreign exchange reserve data correlation are filtered out as foreign exchange coupling index data according to the related coefficient；The foreign exchange coupling index data are carried out index components analysis and constructed to obtain foreign exchange reserve Index Prediction Model；Foreign exchange reserve exponential forecasting is carried out to the foreign exchange reserve according to the foreign exchange reserve Index Prediction Model.The present invention is to be predicted based on each base values under foreign exchange reserve scene foreign exchange reserve, and scientific and reliable and accuracy is higher.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of information forecasting method, device, computer equipment and
Storage medium.
Background technique
Foreign exchange reserve be a national monetary authorities held for make up payments deficit, maintain state's currency converge
The stable international generally accepted xenocurrency of rate, is a part of international reserve.Foreign exchange reserve in reserve assets the most
It is important.And foreign exchange reserve is the important component of a national economic strength.
It is, in general, that the ability of macro adjustments and controls not only can be enhanced in the increase of foreign exchange reserve, but also be conducive to maintenance country
With the prestige of enterprise in the world, helps to expand international trade, attract foreign investment, reduce domestic enterprise's finance costs, is anti-
Model and neutralizing international financial risk.But foreign exchange reserve is not the more the better, once the size of foreign exchange reserves of a state is excessive, no
Inflationary pressure can be only increased, monetary authorities is influenced and independently formulates monetary policy, and also result in the power of economic growth
Structure is unbalanced, is unfavorable for realizing transformation of the economic growth to domestic demand leading type mode.Therefore, to foreign exchange reserve growth trend into
Row prediction is to marcoeconomic regulation and control important in inhibiting.But lack has foreign exchange reserve growth trend Accurate Prediction at present
Effect means.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, providing one kind can be to the letter that foreign exchange reserve index is predicted
Cease prediction technique, device, computer equipment and storage medium.
A kind of information forecasting method, which comprises
The growth rate score of foreign exchange reserve in predetermined period is obtained, and obtains each base values one by one from base values library
Corresponding base values data；
Calculate separately each base values data and the related coefficient increased between rate score；
It is filtered out with the base values data of the foreign exchange reserve data correlation according to the related coefficient as outer
Remittance coupling index data；
The foreign exchange coupling index data are carried out index components analysis and constructed to obtain foreign exchange reserve Index Prediction Model；
Foreign exchange reserve exponential forecasting is carried out to the foreign exchange reserve according to the foreign exchange reserve Index Prediction Model.
It is described in one of the embodiments, to calculate separately between each base values data and the growth rate score
Related coefficient, comprising:
The base values data and the growth rate score are substituted into correlation calculations formula to calculate；
The absolute value for the result being calculated according to the correlation calculations formula is set as related coefficient.
It is described in one of the embodiments, to be filtered out and the foreign exchange reserve data correlation according to the related coefficient
The base values data are as foreign exchange coupling index data, comprising:
Default dependent thresholds are obtained, the base values data that the related coefficient is greater than the default dependent thresholds are extracted
For achievement data to be processed；
Attribute information corresponding with the achievement data to be processed is obtained, according to the attribute information to described to be processed
Achievement data is classified；
It is foreign exchange association by the maximum base values data setting of related coefficient in every one kind achievement data to be processed
Achievement data.
It is described by the maximum base values of related coefficient in every one kind index to be processed in one of the embodiments,
It is set as after foreign exchange coupling index, further includes:
Obtain the classification quantity and pre-set level numerical lower limits threshold value of the achievement data to be processed；
The classification quantity and the pre-set level numerical lower limits threshold value are compared；
When the classification quantity is less than the pre-set level numerical lower limits threshold value, the pre-set level numerical lower limits are calculated
The difference of threshold value and the classification quantity；
The related coefficient of the remaining achievement data to be processed is ranked up from large to small, described in standing out
Achievement data to be processed is also extracted as foreign exchange coupling index data, and the achievement data to be processed stood out extracted
Quantity it is consistent with the difference.
It is described in one of the embodiments, that index components analysis is carried out to the foreign exchange coupling index data and is constructed
To foreign exchange reserve Index Prediction Model, comprising:
Respectively each foreign exchange coupling index data are standardized to obtain data matrix；
The covariance matrix of the foreign exchange coupling index data is obtained according to the data matrix, and the association is calculated
The characteristic root and feature vector of variance matrix；
Principal component expression formula is successively determined according to the characteristic root and described eigenvector；
Foreign exchange reserve Index Prediction Model is constructed according to the principal component expression formula.
It is described in one of the embodiments, that the foreign exchange reserve exponential forecasting mould is constructed according to the principal component expression formula
Type, comprising:
Filter out the principal component expression formula that all characteristic roots are greater than 1；
Summation is weighted to the principal component expression formula filtered out and constructs foreign exchange reserve Index Prediction Model.
It is described in one of the embodiments, to calculate separately between each base values data and the growth rate score
Related coefficient, comprising:
Obtain predetermined sequence initial time；
Corresponding with predetermined sequence initial time growth rate sequence is extracted from the growth rate score, from each described
Base values sequence corresponding with the predetermined sequence initial time is extracted in base values data；
Calculate the related coefficient of each the base values sequence and the growth rate sequence.
A kind of information prediction device, described device include:
Numerical value obtains module, for obtaining the growth rate score of foreign exchange reserve in predetermined period, and from base values library
The corresponding base values data of each base values are obtained one by one；
Computing module, for calculating separately each base values data and the phase relation increased between rate score
Number；
Screening module refers to for being filtered out according to the related coefficient with the basis of the foreign exchange reserve data correlation
Data are marked as foreign exchange coupling index；
Model construction module obtains foreign exchange for the foreign exchange coupling index data to be carried out index components analysis and constructed
Lay in Index Prediction Model；
Exponential forecasting module, for carrying out foreign exchange storage to the foreign exchange reserve according to the foreign exchange reserve Index Prediction Model
Standby exponential forecasting.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
The growth rate score of foreign exchange reserve in predetermined period is obtained, and obtains each base values one by one from base values library
Corresponding base values data；
Calculate separately each base values data and the related coefficient increased between rate score；
It is filtered out with the base values of the foreign exchange reserve data correlation according to the related coefficient as foreign exchange pass
Join index；
The foreign exchange coupling index data of the foreign exchange coupling index are carried out index components analysis and constructed to obtain foreign exchange storage
Standby Index Prediction Model；
Foreign exchange reserve exponential forecasting is carried out to the foreign exchange reserve according to the foreign exchange reserve Index Prediction Model.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
The growth rate score of foreign exchange reserve in predetermined period is obtained, and obtains each base values one by one from base values library
Corresponding base values data；
Calculate separately each base values data and the related coefficient increased between rate score；
It is filtered out with the base values of the foreign exchange reserve data correlation according to the related coefficient as foreign exchange pass
Join index；
The foreign exchange coupling index data of the foreign exchange coupling index are carried out index components analysis and constructed to obtain foreign exchange storage
Standby Index Prediction Model；
Foreign exchange reserve exponential forecasting is carried out to the foreign exchange reserve according to the foreign exchange reserve Index Prediction Model.
Above- mentioned information prediction technique, device, computer equipment and storage medium, it is all by being obtained from base values library
The corresponding achievement data of base values, and foreign exchange is determined according to the related coefficient between each base values data and growth rate score
Coupling index, and then foreign exchange reserve Index Prediction Model is constructed using foreign exchange coupling index.Index of the invention is numerous and source
Abundant, the foreign exchange reserve Index Prediction Model of building is scientific and reliable.And the present invention is based on each under foreign exchange reserve scene
What a base values predicted foreign exchange reserve, accuracy is higher.
Detailed description of the invention
Fig. 1 is the application scenario diagram of information forecasting method in one embodiment；
Fig. 2 is the flow diagram of information forecasting method in one embodiment；
Fig. 3 is the flow diagram that foreign exchange coupling index data are set in one embodiment；
Fig. 4 is the flow diagram that foreign exchange reserve Index Prediction Model is constructed in another embodiment；
Fig. 5 is the schematic diagram of the 4 phases foreign exchange reserve Index Prediction Model constructed in one embodiment；
Fig. 6 is the structural block diagram of information prediction device in one embodiment；
Fig. 7 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Information forecasting method provided by the present application can be applied in application environment as shown in Figure 1.Wherein, terminal 102
It is communicated with server 104 by network by network.User, which can be sent by terminal 102 to server 104, it is expected
The foreign exchange reserve index of predetermined period is requested；Server 104 carries out the foreign exchange reserve index of predetermined period after receiving the request
Prediction, and the foreign exchange reserve index predicted is sent to terminal 102 by network；Foreign exchange reserve of the terminal 102 to predicting
Index is shown and user is allowed to know.Wherein, terminal 102 can be, but not limited to be various personal computers, notebook electricity
Brain, smart phone, tablet computer and portable intelligent device, server 104 can use independent server either multiple clothes
The server cluster of business device composition is realized.
In one embodiment, as shown in Fig. 2, providing a kind of information forecasting method, it is applied in Fig. 1 in this way
It is illustrated for server, comprising the following steps:
Step 202, the growth rate score of foreign exchange reserve in predetermined period is obtained, and is obtained one by one respectively from base values library
The corresponding base values data of base values.
In the present embodiment, the base values in base values library derives from more than 2000 a macro-performance indicators, covers substantially
Entire macroeconomic important indicator is covered.These indexs have off-farm Job population, employment rate, unemployment rate, international revenue and expenditure, its people
Total output value, GDP, production prices index, consumer price index, disposable personal income, personal consumption expenditure,
(financial indicator includes interest rate, the exchange rate, money supply, finance for savings deposits of urban and rural residents remaining sum, investment target, financial indicator
Mechanism loans and deposits remaining sum, financial asset total amount etc.), consumption confidence index, Purchase Management Index, durable goods orders, industry it is raw
Production index, capacity utilization, retail sales index, the total retail sales of consumer goods, consumer credit, new room go into operation and build and permitted
Can, building expenditure, production prices index, wholesale price index, foreign trade, factory order, durable goods order, frequent account with
And commercial inventory etc..
Each base values has corresponding base values data in base values library, and is periodically updated and deposits
Storage.1 year base values at least once being updated storage, but being had of all base values can also be obtained according to circumstances repeatedly more
New data, such as what is monthly updated storage have off-farm Job population, employment rate, unemployment rate, depository financial institution loan balance etc.,
What is quarterly updated storage has GDP, investment target, durable goods orders, capacity utilization, factory order etc..
Server 104 obtains the growth rate score of foreign exchange reserve in predetermined period, and obtains multiple base values one by one and exist
Base values data in same predetermined period.By taking base values inventory contains 2000 base values as an example, these bases refer to
Mark data constitute the data sequence of 2000 base values.Growth rate quantity in predetermined period is more, and data sequence is longer,
The foreign exchange reserve Index Prediction Model accuracy rate of building is higher, thus in order to improve the accurate of foreign exchange reserve Index Prediction Model
Rate, the corresponding data bulk of each base values is generally not less than 5 in the predetermined period.
Step 204, each base values data are calculated separately and increase the related coefficient between rate score.
Server calculates separately base values data and increases the related coefficient between rate score.Calculating related coefficient
When, server is calculated using the correlation calculations such as Pearson correlation coefficients or Spearman's correlation coefficient formula.Clothes
Business device can calculate base values data with rate score substitution correlation calculations formula is increased, and calculated result is directly set
It is set to related coefficient.
For example, Pearson correlation coefficients calculation formula can be used in server:
In above formula, X is basic achievement data, and Y is growth rate score, ρ(X,Y)For relative coefficient.Two continuous changes
Measure the pearson correlation property coefficient ρ of (X, Y)(X,Y)Equal to the covariance cov (X, Y) between them divided by each standard deviation
Product (σX,σY).For the value of coefficient always between -1.0 to 1.0, the variable close to 0 is referred to as non-correlation, close to 1 or -
1 is referred to as with strong correlation.
Spearman's correlation coefficient calculation formula can also be used in server:
For server when calculating related coefficient, X is basic achievement data, and Y is growth rate score, and ρ is server calculating
Obtained related coefficient.Dependent variable in model is foreign exchange reserve growth rate, and independent variable is multiple foreign exchange coupling index data,
Each foreign exchange coupling index data assign different weights.
In one embodiment, each base values data are calculated separately and increase the related coefficient between rate score, comprising:
Base values data and growth rate score are substituted into correlation calculations formula to calculate；It will be calculated according to correlation calculations formula
The absolute value of obtained result is set as related coefficient.
Specifically, base values data and growth rate numerical value can be brought into Pearson correlation coefficients calculation formula or this skin
Germania related coefficient calculation formula is calculated, but the absolute value of all calculated result is set as related coefficient.
Step 206, it is filtered out with the base values data of foreign exchange reserve data correlation according to related coefficient as foreign exchange pass
Join achievement data.
Server filters out symbol from 2000 base values data according to related coefficient according to pre-set level screening rule
The base values data of forex forecasting demand are closed as foreign exchange coupling index data.Pre-set level screening rule can be by extracting
The base values data for having related coefficient to fall into screening range are as foreign exchange coupling index data, or other selection rule
Then.
Step 208, foreign exchange coupling index data are carried out index components analysis and constructed to obtain foreign exchange reserve exponential forecasting
Model.
Principal component analysis is carried out to the multiple foreign exchange coupling indexs filtered out, multiple masters are obtained according to principal component analysis result
Ingredient expression formula, then principal component expression formula is screened, the quantity of the principal component expression formula filtered out is less than foreign exchange association and refers to
Mark quantity.Foreign exchange reserve Index Prediction Model is constructed according to all principal component expression formulas filtered out.
Step 210, foreign exchange reserve exponential forecasting is carried out to foreign exchange reserve according to foreign exchange reserve Index Prediction Model.
The data sequence at each foreign exchange coupling index current time is substituted into foreign exchange reserve Index Prediction Model, can be predicted
To the foreign exchange reserve exponent data of subsequent time.Since foreign exchange reserve index is according to the events such as policy, situation and each basis
The historical data of index and update, thus after the completion of the building of foreign exchange reserve Index Prediction Model, server is by current data
Sequence substitutes into the prediction data that can be obtained by the foreign exchange reserve index of subsequent time in foreign exchange reserve Index Prediction Model.Example
Such as, the data sequence of the 1st phase (first quarter) in 2018 is substituted into foreign exchange reserve Index Prediction Model and can be obtained by server
To the prediction data of the foreign exchange reserve index of the 2nd phase (second quarter) in 2018.
The foreign exchange reserve index that server can obtain prediction is analyzed, such as generates foreign exchange reserve trend graph and phase
The early warning answered, or prediction result is sent to terminal, decision is carried out for user.
In above- mentioned information prediction technique, the corresponding achievement data of all base values, and root are obtained from base values library
Foreign exchange coupling index data are determined according to the related coefficient between each base values data and growth rate score, and then are closed using foreign exchange
Join achievement data and constructs foreign exchange reserve Index Prediction Model.These parameters are numerous and abundance, thus the foreign exchange reserve constructed
Index Prediction Model is scientific and reliable.And above-mentioned foreign exchange reserve index forecasting method is based on each under foreign exchange reserve scene
Base values is predicted that foreign exchange reserve, not only accuracy is higher, but also due to data bulk one in each data sequence
As be not less than 5, can reduce because policy, situation and time etc. variation caused by influence.
In one embodiment, refer to as shown in figure 3, being filtered out according to related coefficient with the basis of foreign exchange reserve data correlation
Data are marked as foreign exchange coupling index data, specifically includes the following steps:
Step 302, default dependent thresholds are obtained, the base values data that related coefficient is greater than default dependent thresholds are extracted
For achievement data to be processed.
Server obtains pre-set dependent thresholds from database, will be calculated according to each base values data
Related coefficient is compared with default dependent thresholds respectively, when server, which determines related coefficient, is greater than default dependent thresholds,
Corresponding base values data are extracted as achievement data to be processed.
Step 304, attribute information corresponding with achievement data to be processed is obtained, according to attribute information to index to be processed
Data are classified.
Because base values covers macroeconomic various aspects, there are multiple basic macro-indicators to be able to reflect one kind
The case where economic problems.Classification mark is carried out to each base values in advance, assigns different attribute informations.Server is according to wait locate
Reason achievement data determines index to be processed respectively, and then obtains corresponding category respectively from base values library according to index to be processed
Property information, is divided into same category for the base values for belonging to same attribute information.
For example, the corresponding attribute information of off-farm Job population, employment rate, unemployment rate is divided into non-agricultural operational data；State
The corresponding attribute information such as people's total output value, GDP, the index numbers of industrial production and factory order is divided into production
Data；The corresponding attribute such as production prices index, consumer price index, retail sales index and the total retail sales of consumer goods
Information is divided into sales data.
It step 306, is foreign exchange by the maximum base values data setting of related coefficient in every one kind achievement data to be processed
Coupling index data.
Specifically, when the time cycle is T1, server divides institute's achievement data to be handled according to attribute information
Class is always divided into M class.M class data are respectively non-agricultural operational data, creation data and sales data etc..Wherein, non-agricultural work
The corresponding related coefficient of off-farm Job population in data, employment rate, unemployment rate is respectively 0.6,0.8 and 0.7, and employment rate refers to
It is maximum to mark corresponding related coefficient, therefore, the maximum employment rate of related coefficient in non-agricultural operational data is set as outer by server
Remittance coupling index data.
In above- mentioned information prediction technique, classification mark carried out to each base values in advance, and by every one kind index to be processed
The maximum base values data setting of related coefficient is foreign exchange coupling index data in data, it is ensured that every class index is all selected
It takes, realizes the diversification of achievement data to be processed, shadow caused by not only reducing because of the variation such as policy, situation and time
It rings, and further improves the accuracy of model.
In one embodiment, by the maximum base values data setting of related coefficient in every one kind achievement data to be processed
After foreign exchange coupling index data, method further include:
Step 308, the classification quantity and pre-set level numerical lower limits threshold value of achievement data to be processed are obtained.
Server obtains pre-set level numerical lower limits threshold value from database, and directly acquires point of achievement data to be processed
Class quantity.The pre-set level numerical lower limits threshold value refers to accurate in order to ensure the foreign exchange reserve Index Prediction Model that finally constructs
Property and the minimum number magnitude that sets, general pre-set level numerical lower limits threshold value are not less than 10.
Step 310, classification quantity and pre-set level numerical lower limits threshold value are compared.
To classify quantity and pre-set level numerical lower limits threshold value of server is compared, when classification quantity refers to not less than default
It when marking numerical lower limits threshold value, can reduce because using the influence caused by Principal Component Analysis dimensionality reduction, it is ensured that is finally constructed is outer
The accuracy of remittance deposit Index Prediction Model.
Step 312, when quantity of classifying is less than pre-set level numerical lower limits threshold value, pre-set level numerical lower limits threshold value is calculated
With the difference of classification quantity.
When class categories quantity is less than pre-set level numerical lower limits threshold value, calculates pre-set level numerical lower limits threshold value and divide
The difference Q of class categorical measure.
Step 314, the related coefficient of remaining achievement data to be processed is ranked up from large to small, by what is stood out
Index to be processed is also extracted as foreign exchange coupling index, and the quantity of the index to be processed stood out extracted and difference one
It causes.
The related coefficient of the remaining base values data extracted is ranked up from large to small, Q before coming
Base values data be also extracted as foreign exchange coupling index data.
In above- mentioned information prediction technique, pre-set level numerical lower limits threshold value is determined in advance, reduces because using principal component
Influence caused by analytic approach dimensionality reduction, it is ensured that the accuracy of the foreign exchange reserve Index Prediction Model finally constructed.And when classification number
Amount is less than pre-set level numerical lower limits threshold value, extracts the index to be processed that the numerical value of related coefficient is stood out, not only makes up
It is influenced caused by lazy weight, and each index to be processed and foreign exchange reserve data tight association, it is ensured that foreign exchange storage
For the accurate of Index Prediction Model.
In another embodiment, as shown in figure 4, being obtained to the progress index components analysis building of foreign exchange coupling index data outer
It converges and lays in Index Prediction Model, comprising the following steps:
Step 402, respectively each foreign exchange coupling index data are standardized to obtain data matrix.
P dimension random vector x=(X is acquired respectively to n foreign exchange coupling index data1,X2,...,Xp)T, each foreign exchange pass
Join achievement data xi=(xi1,xi2,...,xip)T, i=1,2 ..., n, n > p, structural matrix, to matrix array elements progress such as subscript
Standardization is converted to eliminate the dimension difference between different achievement datas and the difference between the order of magnitude:
Wherein,Data matrix Z after must standardizing.N is foreign exchange coupling index
The total quantity of data, p are numerical value number in the corresponding ordered series of numbers of each foreign exchange coupling index data.ZiIndicate i-th of foreign exchange association
The data matrix of achievement data, ZijIndicate the data matrix of j-th of numerical value in i-th of foreign exchange coupling index data.
Step 404, the covariance matrix of foreign exchange coupling index data is obtained according to data matrix, and covariance is calculated
The characteristic root and feature vector of matrix.
Covariance matrix R is acquired according to data matrix Z, the calculation formula of covariance matrix R is as follows:
Then it solves covariance matrix R and obtains p characteristic root.
The number m of principal component is calculated according to following formula, the utilization rate of information is made to reach default utilization rate A or more,
To each λj, j=1,2 ..., m, solving equations Rb=λjB obtains feature vectorIn order to guarantee all base values data
Representative information is used effectively, this is generally preset utilization rate A and is set as 85%.
Step 406, principal component expression formula is successively determined according to characteristic root and feature vector.
The target variable after standardization is converted into principal component according to characteristic root and feature vector, as follows:
U1Referred to as first principal component expression formula, U2Referred to as Second principal component, expression formula ..., UpReferred to as pth principal component is expressed
Formula.
Step 408, foreign exchange reserve Index Prediction Model is constructed according to principal component expression formula.
Summation is weighted to get foreign exchange reserve Index Prediction Model to m principal component expression formula.Dependent variable in model
Extremely foreign exchange reserve growth rate, independent variable are multiple foreign exchange coupling index data, and each foreign exchange coupling index data assign different
Weight, weight are the variance contribution ratio of each principal component.
In one embodiment, foreign exchange reserve Index Prediction Model, method are constructed according to principal component expression formula further include:
Filter out the principal component expression formula that all characteristic roots are greater than 1.
The information that principal component expression formula due to characteristic root no more than 1 contains is greater than 1 principal component table compared to characteristic root
It is fewer up to formula or do not have, thus extra principal component expression formula is deleted, guaranteeing foreign exchange reserve Index Prediction Model
Accuracy while, further realize the dimensionality reduction of foreign exchange coupling index data.
Summation is weighted to get foreign exchange reserve Index Prediction Model to the principal component expression formula filtered out again, flexible strategy are
The variance contribution ratio of each principal component.
In one embodiment, each base values data are calculated separately and increase the related coefficient between rate score, comprising:
Obtain predetermined sequence initial time；Growth rate sequence corresponding with predetermined sequence initial time is extracted in rate score from increasing, from
Base values sequence corresponding with predetermined sequence initial time is extracted in each base values data；Calculate each base values sequence with
The related coefficient of growth rate sequence.
This method can construct the foreign exchange reserve Index Prediction Model of following more phases, and increase to the foreign exchange reserve of following more phases
Long rate is predicted.When constructing following more phase foreign exchange reserve models, when constructing the model of next phase, in base values sequence
Data to Forward one, give up by a data originally.For example, the exponent data for predicting following 4 phases can be set, from each
The base values sequence of 4 phases is extracted in base values data.
As shown in figure 5, server constructs the (second quarter in 2018 to the 1st season in 2019 1 phase to 4 phases using this method respectively
Degree) foreign exchange reserve Index Prediction Model.Foreign exchange predetermined sequence initial time is the second quarter in 2008, and server is from growth rate
Extract corresponding with 2008 the 2nd phase (second quarter) growth rate sequence (OBJ curve in figure) in numerical value, server is from each basis
Base values sequence corresponding with predetermined sequence initial time is extracted in achievement data.
When constructing the foreign exchange reserve Index Prediction Model of the 2nd phase in 2018, server is mentioned from each base values data
It takes from the starting second quarter in 2008 to the corresponding base values sequence first quarter in 2018, at this time foreign exchange reserve exponential forecasting mould
Type is OBJ1 curve in figure.When constructing the foreign exchange reserve Index Prediction Model of the 3rd phase in 2018, server is from each base values
It extracts in data and originates from the second quarter in 2008 to the corresponding base values sequence first quarter in 2018, but server is same at this time
When give up the foreign exchange in the second quarter in 2008 and increase rate score and base values sequence, thus foreign exchange reserve Index Prediction Model
For OBJ2 curve in figure.When constructing the foreign exchange reserve Index Prediction Model of the 4th phase in 2018, server is from each base values number
It extracts according to middle from the starting second quarter in 2008 to the corresponding base values sequence first quarter in 2018, server is given up simultaneously
The foreign exchange in the second quarter in 2008 and the third quarter in 2008 increases rate score and base values sequence, thus foreign exchange reserve refers to
Number prediction model is OBJ3 curve in figure.When constructing the foreign exchange reserve Index Prediction Model of the 1st phase in 2019, server is from each
It is extracted in base values data from the starting second quarter in 2008 to the corresponding base values sequence first quarter in 2018, server
The foreign exchange for giving up the second quarter in 2008, the third quarter in 2008 and the fourth quarter in 2008 simultaneously increases rate score and basis
Index series, thus foreign exchange reserve Index Prediction Model is OBJ4 curve in figure.
When predicting not same period foreign exchange reserve index using this method, it is required to first construct foreign exchange reserve exponential forecasting mould
Type, to ensure the uniqueness of the building index of each phase.Caused by being reduced in this way because of the variation such as policy, situation and time
It influences, further promotes the accuracy of the foreign exchange building index of each phase.
It should be understood that although each step in the flow chart of Fig. 2~4 is successively shown according to the instruction of arrow,
It is these steps is not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
There is no stringent sequences to limit for rapid execution, these steps can execute in other order.Moreover, in Fig. 2~4 at least
A part of step may include that perhaps these sub-steps of multiple stages or stage are not necessarily in same a period of time to multiple sub-steps
Quarter executes completion, but can execute at different times, the execution in these sub-steps or stage be sequentially also not necessarily according to
Secondary progress, but in turn or can replace at least part of the sub-step or stage of other steps or other steps
Ground executes.
In one embodiment, as shown in fig. 6, providing a kind of information prediction device, which includes number
Value obtains module 602, computing module 604, screening module 606, model construction module 608 and exponential forecasting module 610,
In:
Numerical value obtains module 602, for obtaining the growth rate score of foreign exchange reserve in predetermined period, and from base values library
In obtain the corresponding base values data of each base values one by one.
Computing module 604, for calculating separately each base values data and increasing the related coefficient between rate score.
Screening module 606 is made for being filtered out according to related coefficient with the base values data of foreign exchange reserve data correlation
For foreign exchange coupling index.
Model construction module 608 obtains foreign exchange for foreign exchange coupling index data to be carried out index components analysis and constructed
Lay in Index Prediction Model.
Exponential forecasting module 610 refers to for carrying out foreign exchange reserve to foreign exchange reserve according to foreign exchange reserve Index Prediction Model
Number prediction.
In one embodiment, computing module 604 can be also used for base values data and increase rate score substitution phase
Closing property calculation formula is calculated；And the absolute value for the result being calculated according to correlation calculations formula is set as phase relation
Number.
In some embodiments, screening module 606 can also include extraction unit, taxon and setup unit,
In:
Related coefficient is greater than the base values number of default dependent thresholds for obtaining default dependent thresholds by extraction unit
According to being extracted as achievement data to be processed.
Taxon treats place according to attribute information for obtaining attribute information corresponding with achievement data to be processed
Reason achievement data is classified.
Setup unit, for being by the maximum base values data setting of related coefficient in every one kind achievement data to be processed
Foreign exchange coupling index data.
In another embodiment, screening module 606 can also be obtained including extraction unit, taxon, setup unit, numerical value
Take unit, comparison judgment unit and computing unit, in which:
Related coefficient is greater than the base values number of default dependent thresholds for obtaining default dependent thresholds by extraction unit
According to being extracted as achievement data to be processed.
Taxon treats place according to attribute information for obtaining attribute information corresponding with achievement data to be processed
Reason achievement data is classified.
Setup unit, for being by the maximum base values data setting of related coefficient in every one kind achievement data to be processed
Foreign exchange coupling index data.
Numerical value acquiring unit, for obtaining the classification quantity and pre-set level numerical lower limits threshold value of achievement data to be processed.
Comparison judgment unit, for that will classify quantity and pre-set level numerical lower limits threshold value is compared judgement.
When quantity of classifying is less than pre-set level numerical lower limits threshold value, computing unit, for calculating under pre-set level quantity
Limit the difference of threshold value and quantity of classifying.
Setup unit will be arranged for being also ranked up the related coefficient of remaining achievement data to be processed from large to small
Index to be processed in forefront, which is also extracted, is set as foreign exchange coupling index, and the number of the index to be processed stood out extracted
It measures consistent with difference.
In another embodiment, model construction module 608 includes processing unit, variance computing unit, the determining list of expression formula
Member and model construction unit, in which:
Processing unit, for being standardized to obtain data matrix to each foreign exchange coupling index data respectively.
Variance computing unit for obtaining the covariance matrix of foreign exchange coupling index data according to data matrix, and calculates
Obtain the characteristic root and feature vector of covariance matrix.
Expression formula determination unit, for successively determining principal component expression formula according to characteristic root and feature vector.
Model construction unit, for constructing foreign exchange reserve Index Prediction Model according to principal component expression formula.
In one embodiment, model construction module 608 include processing unit, variance computing unit, expression formula determination unit,
Screening unit and model construction unit, in which:
Processing unit, for being standardized to obtain data matrix to each foreign exchange coupling index data respectively.
Variance computing unit for obtaining the covariance matrix of foreign exchange coupling index data according to data matrix, and calculates
Obtain the characteristic root and feature vector of covariance matrix.
Expression formula determination unit, for successively determining principal component expression formula according to characteristic root and feature vector.
Screening unit, the principal component expression formula for being greater than 1 for filtering out all characteristic roots.
Model construction unit, for being weighted summation to the principal component expression formula filtered out and constructing foreign exchange reserve index
Prediction model.
In some embodiments, computing module 604 can also include time acquisition unit, sequence extraction unit and coefficient
Computing unit, in which:
Time acquisition unit, for obtaining predetermined sequence initial time.
Sequence extraction unit, for extracting growth rate sequence corresponding with predetermined sequence initial time from growth rate score
Column extract base values sequence corresponding with predetermined sequence initial time from each base values data.
Coefficient calculation unit, for calculating the related coefficient of each base values sequence and growth rate sequence.
Specific about information prediction device limits the restriction that may refer to above for information forecasting method, herein not
It repeats again.Modules in above- mentioned information prediction meanss can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 7.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database (base values library) of machine equipment is for storing foreign exchange reserve exponential forecasting data, default dependent thresholds, pre-set level
Numerical lower limits threshold value, predetermined sequence initial time, base values data and its attribute information etc..The net of the computer equipment
Network interface is used to communicate with external terminal by network connection.To realize outside one kind when the computer program is executed by processor
It converges and lays in index forecasting method.
It will be understood by those skilled in the art that structure shown in Fig. 7, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of the growth for obtaining foreign exchange reserve in predetermined period when executing computer program
Rate score, and obtain the corresponding base values data of each base values one by one from base values library；Each basis is calculated separately to refer to
It marks data and increases the related coefficient between rate score；It is filtered out according to related coefficient and is referred to the basis of foreign exchange reserve data correlation
It is denoted as foreign exchange coupling index；The foreign exchange coupling index data of foreign exchange coupling index are carried out index components analysis and constructed to obtain
Foreign exchange reserve Index Prediction Model；Foreign exchange reserve exponential forecasting is carried out to foreign exchange reserve according to foreign exchange reserve Index Prediction Model.
In one embodiment, it is realized when processor executes computer program and calculates separately each base values data and increase
It is also used to when the step of the related coefficient between rate score: by base values data and increasing rate score substitution correlation calculations public affairs
Formula is calculated；The absolute value for the result being calculated according to correlation calculations formula is set as related coefficient.
In one embodiment, it realizes and is filtered out according to related coefficient and foreign exchange reserve when processor executes computer program
It is also used to when step of the base values data of data correlation as foreign exchange coupling index data: obtaining default dependent thresholds, it will
The base values data that related coefficient is greater than default dependent thresholds are extracted as achievement data to be processed；It obtains and index number to be processed
According to corresponding attribute information, classified according to attribute information to achievement data to be processed；By every one kind index number to be processed
It is foreign exchange coupling index data according to the maximum base values data setting of middle related coefficient.
In one embodiment, realizing when processor executes computer program will be related in every one kind achievement data to be processed
Coefficient maximum base values data setting is also used to when being the step of foreign exchange coupling index data: obtaining achievement data to be processed
Classification quantity and pre-set level numerical lower limits threshold value；Classification quantity and pre-set level numerical lower limits threshold value are compared；When
When quantity of classifying is less than pre-set level numerical lower limits threshold value, the difference of pre-set level numerical lower limits threshold value and quantity of classifying is calculated；
The related coefficient of remaining achievement data to be processed is ranked up from large to small, the index to be processed stood out also is extracted
For foreign exchange coupling index, and the quantity of the index to be processed stood out extracted is consistent with difference.
In one embodiment, processor execute computer program when realize to foreign exchange coupling index data carry out index at
Analysis building obtains being also used to when the step of foreign exchange reserve Index Prediction Model: carrying out respectively to each foreign exchange coupling index data
Standardization obtains data matrix；The covariance matrix of foreign exchange coupling index data is obtained according to data matrix, and is calculated
To the characteristic root and feature vector of covariance matrix；Principal component expression formula is successively determined according to characteristic root and feature vector；According to
Principal component expression formula constructs foreign exchange reserve Index Prediction Model.
In one embodiment, it is realized when processor executes computer program and foreign exchange reserve is constructed according to principal component expression formula
It is also used to when the step of Index Prediction Model: filtering out the principal component expression formula that all characteristic roots are greater than 1；To filter out it is main at
Point expression formula is weighted summation and constructs foreign exchange reserve Index Prediction Model.
In one embodiment, it is realized when processor executes computer program and calculates separately each base values data and increase
It is also used to when the step of the related coefficient between rate score: obtaining predetermined sequence initial time；From increase rate score in extract with
The corresponding growth rate sequence of predetermined sequence initial time is extracted corresponding with predetermined sequence initial time from each base values data
Base values sequence；Calculate the related coefficient of each base values sequence and growth rate sequence.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
The growth rate score of foreign exchange reserve in predetermined period is obtained, and obtains each base values one by one from base values library
Corresponding base values data；
It calculates separately each base values data and increases the related coefficient between rate score；
It is filtered out with the base values of foreign exchange reserve data correlation according to related coefficient as foreign exchange coupling index；
Index components analysis is carried out to the foreign exchange coupling index data of foreign exchange coupling index and building obtains foreign exchange reserve and refers to
Number prediction model；
Foreign exchange reserve exponential forecasting is carried out to foreign exchange reserve according to foreign exchange reserve Index Prediction Model.
In one embodiment, it is realized when computer program is executed by processor and calculates separately each base values data and increase
It is also used to when the step of the related coefficient between long rate score: by base values data and increasing rate score substitution correlation calculations
Formula is calculated；The absolute value for the result being calculated according to correlation calculations formula is set as related coefficient.
In one embodiment, it realizes to be filtered out according to related coefficient when computer program is executed by processor and be stored up with foreign exchange
It is also used to when step of the base values data of standby data correlation as foreign exchange coupling index data: obtaining and preset dependent thresholds,
The base values data that related coefficient is greater than default dependent thresholds are extracted as achievement data to be processed；It obtains and index to be processed
The corresponding attribute information of data classifies to achievement data to be processed according to attribute information；By every one kind index to be processed
The maximum base values data setting of related coefficient is foreign exchange coupling index data in data.
In one embodiment, it realizes when computer program is executed by processor by phase in every one kind achievement data to be processed
Relationship number maximum base values data setting is also used to when being the step of foreign exchange coupling index data: obtaining index number to be processed
According to classification quantity and pre-set level numerical lower limits threshold value；Classification quantity and pre-set level numerical lower limits threshold value are compared；
When quantity of classifying is less than pre-set level numerical lower limits threshold value, the difference of pre-set level numerical lower limits threshold value and quantity of classifying is calculated
Value；The related coefficient of remaining achievement data to be processed is ranked up from large to small, the index to be processed that will be stood out
The quantity for the index to be processed stood out for being extracted as foreign exchange coupling index, and extracting is consistent with difference.
In one embodiment, it is realized when computer program is executed by processor and index is carried out to foreign exchange coupling index data
Constituent analysis constructs to be also used to when obtaining the step of foreign exchange reserve Index Prediction Model: respectively to each foreign exchange coupling index data into
Row standardization obtains data matrix；The covariance matrix of foreign exchange coupling index data is obtained according to data matrix, and is calculated
Obtain the characteristic root and feature vector of covariance matrix；Principal component expression formula is successively determined according to characteristic root and feature vector；Root
Foreign exchange reserve Index Prediction Model is constructed according to principal component expression formula.
In one embodiment, it is realized when computer program is executed by processor and foreign exchange storage is constructed according to principal component expression formula
It is also used to when the step of standby Index Prediction Model: filtering out the principal component expression formula that all characteristic roots are greater than 1；To the master filtered out
Ingredient expression formula is weighted summation and constructs foreign exchange reserve Index Prediction Model.
In one embodiment, it is realized when computer program is executed by processor and calculates separately each base values data and increase
It is also used to when the step of the related coefficient between long rate score: obtaining predetermined sequence initial time；It is extracted from increasing in rate score
Growth rate sequence corresponding with predetermined sequence initial time is extracted and predetermined sequence initial time pair from each base values data
The base values sequence answered；Calculate the related coefficient of each base values sequence and growth rate sequence.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Instruct relevant hardware to complete by computer program, computer program to can be stored in a non-volatile computer readable
It takes in storage medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, this Shen
Please provided by any reference used in each embodiment to memory, storage, database or other media, may each comprise
Non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
Above embodiments only express the several embodiments of the application, and the description thereof is more specific and detailed, but can not
Therefore it is construed as limiting the scope of the patent.It should be pointed out that for those of ordinary skill in the art,
Under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the protection scope of the application.
Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of information forecasting method, which comprises
The growth rate score of foreign exchange reserve in predetermined period is obtained, and obtains each base values one by one from base values library and corresponds to
Base values data；
Calculate separately each base values data and the related coefficient increased between rate score；
It is filtered out with the base values data of the foreign exchange reserve data correlation according to the related coefficient as foreign exchange pass
Join achievement data；
The foreign exchange coupling index data are carried out index components analysis and constructed to obtain foreign exchange reserve Index Prediction Model；
Foreign exchange reserve exponential forecasting is carried out to the foreign exchange reserve according to the foreign exchange reserve Index Prediction Model.
2. the method according to claim 1, wherein it is described calculate separately each base values data with it is described
Increase the related coefficient between rate score, comprising:
The base values data and the growth rate score are substituted into correlation calculations formula to calculate；
The absolute value for the result being calculated according to the correlation calculations formula is set as related coefficient.
3. the method according to claim 1, wherein described filter out and the foreign exchange according to the related coefficient
The associated base values data of reservoir data are as foreign exchange coupling index data, comprising:
Obtain default dependent thresholds, by the base values data that the related coefficient is greater than the default dependent thresholds be extracted as to
Handle achievement data；
Attribute information corresponding with the achievement data to be processed is obtained, according to the attribute information to the index to be processed
Data are classified；
It is foreign exchange coupling index by the maximum base values data setting of related coefficient in every one kind achievement data to be processed
Data.
4. according to the method described in claim 3, it is characterized in that, described will be related in every one kind achievement data to be processed
The maximum base values data setting of coefficient is after foreign exchange coupling index data, further includes:
Obtain the classification quantity and pre-set level numerical lower limits threshold value of the achievement data to be processed；
The classification quantity and the pre-set level numerical lower limits threshold value are compared；
When the classification quantity is less than the pre-set level numerical lower limits threshold value, the pre-set level numerical lower limits threshold value is calculated
With the difference of the classification quantity；
The related coefficient of the remaining achievement data to be processed is ranked up from large to small, will stand out described in wait locate
The number for the achievement data to be processed stood out that reason achievement data is also extracted as foreign exchange coupling index data, and extracts
It measures consistent with the difference.
5. the method according to claim 1, wherein it is described to the foreign exchange coupling index data carry out index at
It analyzes and constructs to obtain foreign exchange reserve Index Prediction Model, comprising:
Respectively each foreign exchange coupling index data are standardized to obtain data matrix；
The covariance matrix of the foreign exchange coupling index data is obtained according to the data matrix, and the covariance is calculated
The characteristic root and feature vector of matrix；
Principal component expression formula is successively determined according to the characteristic root and described eigenvector；
Foreign exchange reserve Index Prediction Model is constructed according to the principal component expression formula.
6. according to the method described in claim 5, it is characterized in that, described construct the foreign exchange according to the principal component expression formula
Lay in Index Prediction Model, comprising:
Filter out the principal component expression formula that all characteristic roots are greater than 1；
Summation is weighted to the principal component expression formula filtered out and constructs foreign exchange reserve Index Prediction Model.
7. according to claim 1 to method described in 6 any one, which is characterized in that described to calculate separately each basis and refer to
Mark data and the related coefficient increased between rate score, comprising:
Obtain predetermined sequence initial time；
Growth rate sequence corresponding with the predetermined sequence initial time is extracted from the growth rate score, from each basis
Base values sequence corresponding with the predetermined sequence initial time is extracted in achievement data；
Calculate the related coefficient of each the base values sequence and the growth rate sequence.
8. a kind of information prediction device, which is characterized in that described device includes:
Numerical value obtains module, for obtaining the growth rate score of foreign exchange reserve in predetermined period, and from base values library one by one
Obtain the corresponding base values data of each base values；
Computing module, for calculating separately each base values data and the related coefficient increased between rate score；
Screening module, for filtering out the base values number with the foreign exchange reserve data correlation according to the related coefficient
According to as foreign exchange coupling index data；
Model construction module obtains foreign exchange reserve for the foreign exchange coupling index data to be carried out index components analysis and constructed
Index Prediction Model；
Exponential forecasting module refers to for carrying out foreign exchange reserve to the foreign exchange reserve according to the foreign exchange reserve Index Prediction Model
Number prediction.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910217866.0A CN110084400A (en) | 2019-03-21 | 2019-03-21 | Information forecasting method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910217866.0A CN110084400A (en) | 2019-03-21 | 2019-03-21 | Information forecasting method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110084400A true CN110084400A (en) | 2019-08-02 |
Family
ID=67413386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910217866.0A Pending CN110084400A (en) | 2019-03-21 | 2019-03-21 | Information forecasting method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084400A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112785090A (en) * | 2021-03-03 | 2021-05-11 | 中国工商银行股份有限公司 | Model training method, type prediction method, device and computing equipment |
| CN112996015A (en) * | 2019-12-18 | 2021-06-18 | 中国移动通信集团河南有限公司 | Index association relationship construction method and device |
-
2019
- 2019-03-21 CN CN201910217866.0A patent/CN110084400A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112996015A (en) * | 2019-12-18 | 2021-06-18 | 中国移动通信集团河南有限公司 | Index association relationship construction method and device |
| CN112996015B (en) * | 2019-12-18 | 2023-11-03 | 中国移动通信集团河南有限公司 | Index association relation construction method and device |
| CN112785090A (en) * | 2021-03-03 | 2021-05-11 | 中国工商银行股份有限公司 | Model training method, type prediction method, device and computing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8577791B2 (en) | System and computer program for modeling and pricing loan products | |
| Huang et al. | An integrated DEA-MODM methodology for portfolio optimization | |
| Jouini | Stock markets in GCC countries and global factors: A further investigation | |
| CN110223137A (en) | Product mix recommended method, device, computer equipment and storage medium | |
| CN110110884A (en) | Information forecasting method, device, computer equipment and storage medium | |
| CN110110886A (en) | Information forecasting method, device, computer equipment and storage medium | |
| Hedström et al. | Emerging market contagion under geopolitical uncertainty | |
| Emeka et al. | Domestic investment, capital formation and economic growth in Nigeria | |
| Tomura | International capital flows and expectation-driven boom–bust cycles in the housing market | |
| Schmitt-Grohé et al. | The effects of permanent monetary shocks on exchange rates and uncovered interest rate differentials | |
| Kelly et al. | International trade costs, global supply chains and value-added trade in Australia | |
| Wu et al. | Construction of stock portfolios based on k-means clustering of continuous trend features | |
| CN110084400A (en) | Information forecasting method, device, computer equipment and storage medium | |
| Yu et al. | Learning risk preferences from investment portfolios using inverse optimization | |
| Al-Shawaf et al. | Economic globalization: Role of inward and outward FDI with economic growth-evidence from Malaysia | |
| Gupta et al. | DSGE model-based forecasting of modelled and nonmodelled inflation variables in South Africa | |
| CN110110885A (en) | Information forecasting method, device, computer equipment and storage medium | |
| CN110232463A (en) | Information forecasting method, device, computer equipment and storage medium | |
| Dai et al. | A novel quantitative stock selection model based on support vector regression | |
| WO2018005708A1 (en) | Systems and methods for generating industry outlook scores | |
| Murillas et al. | Valuation and management of fishing resources under price uncertainty | |
| Wang et al. | A new dynamic hedging model with futures: The Kalman filter error-correction model | |
| Yang et al. | Macroeconomic shocks, investment volatility and centrality in global manufacturing network | |
| Ray et al. | Neural network models for forecasting mutual fund net asset value | |
| CN109697528A (en) | Business revenue data predication method, device, computer equipment and storage medium |
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 |