CN115983892A - Price prediction model creation method and device, electronic equipment and readable storage medium - Google Patents
Price prediction model creation method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN115983892A CN115983892A CN202310273635.8A CN202310273635A CN115983892A CN 115983892 A CN115983892 A CN 115983892A CN 202310273635 A CN202310273635 A CN 202310273635A CN 115983892 A CN115983892 A CN 115983892A
- Authority
- CN
- China
- Prior art keywords
- prediction model
- price
- price prediction
- sequence
- predicted
- 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
- 238000000034 method Methods 0.000 title claims abstract description 86
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000005316 response function Methods 0.000 claims description 39
- 238000011161 development Methods 0.000 claims description 17
- 238000009825 accumulation Methods 0.000 claims description 16
- 238000012937 correction Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 11
- 230000000737 periodic effect Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 230000004048 modification Effects 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 6
- 230000001788 irregular Effects 0.000 abstract description 5
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 22
- 229910052799 carbon Inorganic materials 0.000 description 22
- 230000008569 process Effects 0.000 description 21
- 238000010586 diagram Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 6
- 230000009467 reduction Effects 0.000 description 6
- 238000004088 simulation Methods 0.000 description 6
- 238000010998 test method Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a price prediction model creation method and device, electronic equipment and a readable storage medium, which are applied to the field of price prediction. Wherein, the method comprises the following steps: carrying out serialization processing on original data, wherein the original data is to-be-predicted data of an object to be predicted within a preset time period; constructing a gray prediction model according to the processed original data; and determining a price prediction model by solving the grey prediction model, wherein the price prediction model is used for predicting the price of the object to be predicted. The grey theory-based price prediction model can complete prediction targets in different time periods on the basis of a small amount of irregular samples, and can improve result accuracy while reducing calculation workload.
Description
Technical Field
The application relates to the field of price prediction, in particular to a price prediction model creation method and device, electronic equipment and a readable storage medium.
Background
The price prediction is the basis of market prediction analysis and production and sales decision, is an important problem in the field of market prediction, and plays a key role in many problems such as commodity production, sales and the like. For example, the carbon trading price is under the constraint of the total amount of carbon emission, different enterprises can trade the carbon emission right through a market means due to different emission reduction costs, and the purpose of controlling the total amount of emission at lower cost is achieved by selling or purchasing the respective emission amount. As a core part of the carbon trading market, the carbon trading price guides the decision of the enterprise to trade carbon. Due to the fact that the carbon trading price has a plurality of influence factors, and factors such as immaturity of a carbon trading market, nonlinearity of carbon trading price data, subjective randomness of carbon trading participants and the like, when carbon trading price prediction is carried out, the problem that the carbon trading price prediction result is inaccurate often exists.
Disclosure of Invention
In view of the above, an object of the embodiments of the present application is to provide a price prediction model creation method, apparatus, electronic device and readable storage medium, which can improve accuracy of a price prediction result.
In a first aspect, an embodiment of the present application provides a method for creating a price prediction model, including: performing serialization processing on original data, wherein the original data is the data to be predicted corresponding to the object to be predicted within a preset time period; constructing a gray prediction model according to the processed original data; and determining a price prediction model by solving the grey prediction model, wherein the price prediction model is used for predicting the price of the object to be predicted.
In the implementation process, after the original data are processed, a gray prediction model is constructed based on the original data, the gray prediction model is solved through the original data, the gray prediction model aiming at the original data is obtained, and then price prediction is carried out through the gray prediction model. The grey prediction model can analyze the development trend and the state of the object to be predicted based on the past and present development rules of the object to be predicted, and scientific hypothesis and judgment are formed. Therefore, the grey theory-based price prediction model can complete prediction targets of different time periods on the basis of a small amount of irregular samples, and can improve result accuracy while reducing calculation workload.
In one embodiment, the determining a price prediction model by solving the gray prediction model comprises: constructing a data matrix according to the grey prediction model; calculating the data matrix to obtain the development gray number to be identified and the endogenous control quantity of the gray prediction model; and determining the price prediction model according to the development grey number to be identified and the endogenous control quantity.
In one embodiment, after determining a price prediction model by solving the gray prediction model, the method further comprises: determining a periodic response function according to the price prediction model; discretizing the periodic response function to determine a time series response function; and restoring the time series response function, and predicting the price of the object to be predicted through the restored time series corresponding function to obtain a price prediction result.
In the implementation process, after the gray prediction model is solved, when price prediction is carried out based on the solved gray prediction model, because the original data is preprocessed before modeling, after the simulation data sequence is determined, corresponding transformation is carried out to restore the simulation data sequence to the original data sequence, and the accuracy of model prediction is improved. In addition, the time series can predict the change size of the object to be predicted in time, so that the flexibility of the prediction period can be increased.
In one embodiment, after the price of the object to be predicted is predicted through the reduced time series corresponding function to obtain a price prediction result, the method further includes: and judging whether the prediction precision of the price prediction model reaches a precision threshold value or not according to the price prediction result.
In the implementation process, after the price prediction model is established, the prediction accuracy of the price prediction model is judged according to the price prediction result and the accuracy threshold of the price prediction model so as to determine the accuracy of the price prediction model, ensure that the price prediction model is in the accuracy threshold range, and improve the accuracy of the price prediction model.
In one embodiment, the method further comprises: and if the prediction precision of the price prediction model does not reach the precision threshold value, optimizing the prediction result of the price prediction model through a residual correction model.
In the implementation process, when the prediction accuracy of the price prediction model does not reach the accuracy threshold, the price prediction model is optimized through the residual correction model, so that the prediction accuracy of the price prediction model can reach the accuracy threshold, and the prediction accuracy of the price prediction model is improved.
In one embodiment, before optimizing the prediction result of the price prediction model by the residual error correction model, the method further includes: determining a time series response function of the residual error sequence according to the time series response function; and restoring the time sequence response function of the residual sequence into an original residual sequence so as to optimize the prediction result of the price prediction model through the original residual sequence.
In the implementation process, before optimizing the price prediction model, an original residual sequence is determined through a series of calculations, so that the prediction result of the price prediction model is optimized through the original residual sequence. Namely, a residual error correction model is established before the price prediction model is optimized, so that the price prediction model prediction result is optimized through the residual error correction model, and the result prediction precision can be improved.
In one embodiment, the serializing the raw data includes: establishing an original sequence according to the original data; performing accumulation operation on the original sequence to generate an accumulation generation sequence; and generating an adjacent mean sequence through the accumulation generation sequence.
In the implementation process, the original data is serialized before the model is constructed, so that the integral property hidden in the original data can be gradually presented, the potential law of the original data is found from the phenomenon of disorder, the price of the object to be predicted can be predicted accurately by the price prediction model in a future period of time, the prediction of irregular change data is realized, the requirement on variable selection is lowered, and the accuracy of price prediction is improved.
In a second aspect, an embodiment of the present application further provides a price prediction model creating apparatus, including: the processing module is used for carrying out serialization processing on original data, wherein the original data is to-be-predicted data of an object to be predicted in a preset time period; the construction module is used for constructing a gray prediction model according to the processed original data; and the determining module is used for determining a price prediction model by solving the grey prediction model, and the price prediction model is used for predicting the price of the object to be predicted.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory storing machine-readable instructions executable by the processor, the machine-readable instructions, when executed by the processor, performing the steps of the method of the first aspect described above, or any possible implementation of the first aspect, when the electronic device is run.
In a fourth aspect, the present application further provides a computer-readable storage medium, where a computer program is stored, and the computer program is executed by a processor to perform the steps of the method for creating a price prediction model in the first aspect or any one of the possible implementation manners of the first aspect.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
FIG. 1 is a flow chart of a method for creating a price forecasting model according to an embodiment of the present disclosure;
FIG. 2 is a functional block diagram of a price prediction model creation apparatus according to an embodiment of the present disclosure;
fig. 3 is a block diagram of an electronic device according to an embodiment of the present disclosure.
Detailed Description
The technical solution in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
The carbon trading mechanism is based on international convention and law, takes market mechanism as means, and takes greenhouse gas emission rights as a system arrangement of trading objects. The carbon trading is a process of encouraging enterprises with low emission reduction cost to carry out excessive emission reduction through artificially setting the shortage of emission quotas and selling the surplus of the obtained quotas to the enterprises with high emission reduction cost. Generally, the carbon is distributed or sold to a control enterprise in a quota mode, the initial control mode of the carbon market is controlled by strength, and the later stage is gradually transited to total control. Therefore, under the constraint of the total amount of carbon emission, carbon emission right trading can be performed according to different emission reduction costs of different enterprises, so that the aim of controlling the total amount of emission at low cost is fulfilled. The current carbon trading price is influenced by various external factors and generally changes in a nonlinear way, so that the change rule is difficult to find, and further the carbon price needs to be predicted in advance.
However, when carbon transaction price prediction is performed, the problem that the carbon transaction price prediction result is not accurate often exists.
Grey theory is an applied mathematical discipline that studies incomplete information with uncertainty phenomena. Although, the black box method can be used for some systems with poor information at present to make corresponding prediction. However, this method is not sufficiently studied for some data with incomplete internal information. The grey system theory mainly researches data of ' small samples and poor information ' with definite extension and indefinite content '.
In view of this, the present application provides a price prediction model creating method, which performs a gray model creation according to processed raw data, and determines a corresponding price prediction model after solving the gray model, so as to perform price prediction. Namely, a corresponding price prediction model is established based on the grey prediction model, so that the price prediction of the object to be predicted is realized, and the accuracy of the price prediction is improved.
Please refer to fig. 1, which is a flowchart illustrating a method for creating a price prediction model according to an embodiment of the present application. The specific process shown in FIG. 1 will be described in detail below.
The original data is the data to be predicted corresponding to the object to be predicted in a preset time period. The preset time period may be a period of time in which the price of the object to be predicted is relatively stable, a period of time in which the price of the object to be predicted is relatively fluctuated, or a random period of time, and the preset time period may be selected according to actual conditions, and the application is not particularly limited.
The data to be predicted can be average price per day, average price per week, average price per hour and the like of the object to be predicted in a preset time period.
For example, if the data to be predicted is the average daily price of the object to be predicted in the preset time period, the raw data may be:
it can be understood that the original data is a plurality of data within a preset time period, when the original data is processed, the original data may be serialized, and when the original data is serialized, integral properties hidden in the original data may be gradually presented, so that a potential rule of the original data is discovered from a miscellaneous and disordered phenomenon.
And step 202, constructing a gray prediction model according to the processed original data.
Grey prediction is a method for predicting a system containing uncertain factors. The grey prediction is to identify the degree of dissimilarity of development trends among system factors, namely, to perform correlation analysis, and to perform generation processing on the original data to find the rule of system change, to generate a data sequence with strong regularity, and then to establish a corresponding differential equation model, thereby predicting the condition of future development trends of objects. A gray prediction model is constructed by using a series of quantitative values which are observed at equal time intervals and reflect the characteristics of a prediction object, and the characteristic quantity of a certain future moment or the time for reaching a certain characteristic quantity is predicted.
When constructing the gray prediction model, a differential equation of the gray prediction model GM (1,1) may be established:
wherein,
is the development gray to be recognized, is>
Is gray endogenous control and/or>
Is the original data.
And step 203, determining a price prediction model by solving the grey prediction model.
The price prediction model is used for predicting the price of the object to be predicted.
Understandably, in the gray prediction model
And &>
Is unknown, and therefore needs to be corrected first according to the original data
And &>
And calculating to obtain a solved gray prediction model, wherein the solved gray prediction model is the price prediction model.
In the implementation process, after the original data are processed, a gray prediction model is constructed based on the original data, the gray prediction model is solved through the original data to obtain a gray prediction model aiming at the original data, and then price prediction is carried out through the gray prediction model. The grey prediction model can analyze the development trend and the state of the object to be predicted based on the past and present development rules of the object to be predicted, and scientific hypothesis and judgment are formed. Therefore, the grey theory-based price prediction model can complete prediction targets of different time limits on the basis of a small amount of irregular samples, and can improve result accuracy while reducing calculation workload.
In one possible implementation, step 203 includes constructing a data matrix according to a gray prediction model; calculating a data matrix to obtain the development gray number to be identified and the endogenous control quantity of the gray prediction model; and determining a price prediction model according to the development gray number to be identified and the endogenous control quantity.
Due to the number of developing grays to be identified in the established gray prediction model
And an endogenous control quantity>
Is an unknown number, when solving the gray prediction model, a data matrix can be established firstly: namely ûIs used for>
、/>
Constructed unknown parameter measure, û = { [ MEASUREMENT ]>
；
The data matrix is solved as:
û=
T =(B T B) -1 B T Y（1）
wherein,
Y=
，B=/>
（2）
obtained by solving the formula (1) and the formula (2)
And &>
And then determining a gray prediction model.
Alternatively, the data matrix described above may be calculated by a least squares method.
In a possible implementation, after step 203, the method further includes determining a periodic response function according to a price prediction model; discretizing the periodic response function to determine a time series response function; and reducing the time series response function, and predicting the price of the object to be predicted through the reduced time series corresponding function to obtain a price prediction result.
Solving the development gray number to be identified
And an endogenous control quantity->
Then, a solution of the gray prediction model GM (1,1) can be determined, which in turn determines the periodic response function:
discretizing the periodic response function to obtain a corresponding time sequence response function as follows:
and restoring the analog data sequence into an original data sequence:
wherein,
for the original data sequence, is>
For simulating a data sequence>
In order to be a function of the periodic response,
is a time series response function of the simulated data.
The above-described reduction of the analog data sequence to the original data sequence may be performed by an overlap-subtraction process.
It can be understood that, after the relationship between the original data sequence and the simulation data sequence is determined, the simulation data can be predicted through the original data based on the relationship, that is, the price of the object to be predicted is predicted through the original data, so as to obtain a price prediction result.
In the implementation process, after the gray prediction model is solved, when price prediction is carried out based on the solved gray prediction model, because the original data is preprocessed before modeling, after the simulation data sequence is determined, corresponding transformation is carried out to restore the simulation data sequence to the original data sequence, and the accuracy of model prediction is improved. In addition, the time-series prediction of the temporal change size of the object to be predicted can increase the flexibility of the prediction period.
In a possible implementation manner, after predicting the price of the object to be predicted by the reduced time series corresponding function to obtain a price prediction result, the method further includes: and judging whether the prediction precision of the price prediction model reaches a precision threshold value or not according to the price prediction result.
Alternatively, the prediction accuracy of the price prediction model may be determined by a relative residual error test method, a variance ratio test method, a small error probability test method, or the like.
Wherein, the relative residual error detection method comprises the following steps:
let the actual data sequence be
The analog data sequence is->
Then the residual is->
Comprises the following steps:
the relative error is:
variance ratio test method:
let the residual sequence be
In a sequence standard deviation of->
The original sequence is->
The standard deviation of the sequence is B, the variance ratio is->
Comprises the following steps:
small error probability test method:
with a small error probability of
The residual sequence mean is:
then the
The original data sequence length.
It is understood that, when the model accuracy is checked by the above-described determination methods such as the relative residual error check method, the variance ratio check method, and the small error probability check method, the smaller the numerical values of the relative error, the small error probability check method, and the variance ratio, the higher the accuracy.
In some embodiments, the accuracy level of the prediction model may be determined by setting a model accuracy judgment table, and determining the accuracy threshold according to the usage scenario of the price prediction and the effect to be achieved.
Alternatively, the precision threshold may be one-level, two-level, three-level, etc., and the precision threshold may be determined according to actual situations. For example, for a scenario where the price prediction accuracy is high, the accuracy threshold may be set to one level. For scenarios with moderate price prediction accuracy, the accuracy threshold may be set to two levels. For scenarios where the price prediction accuracy is low, the accuracy threshold may be set to four levels.
It is to be understood that the above precision levels and the corresponding precision division values are only exemplary, the precision levels can be increased or decreased according to actual conditions, the precision division values can be determined according to actual conditions, and the present application is not limited specifically.
For example, the model accuracy determination table of the relative residual error test method may be as shown in table 1:
table 1:
in the implementation process, after the price prediction model is established, the prediction accuracy of the price prediction model is judged according to the price prediction result and the accuracy threshold of the price prediction model so as to determine the accuracy of the price prediction model, ensure that the price prediction model is in the accuracy threshold range, and improve the accuracy of the price prediction model.
In one possible implementation, the method further includes: and if the prediction precision of the price prediction model does not reach the precision threshold value, optimizing the prediction result of the price prediction model through the residual correction model.
It is understood that the analog data obtained by performing the superposition subtraction on the data according to the time series response function is different from the original data due to the existence of the error. If the prediction precision of the price prediction model does not reach the precision threshold value, the error between the price prediction model and the precision threshold value is large. In this regard, the price prediction model may be optimized by modifying the residual error generated by comparing the raw data with the simulated data.
The above-described optimization of the price prediction model by means of the residual may be handled by means of a residual modification model.
In some embodiments, since the number of sequences of residual data should be non-negative in the model, if there is a negative number in the number of sequences of residual data, it is necessary to forward process the sequence of residual data, i.e. add a suitable positive value to each item of data in the sequence
So that the data sequence becomes a forward residual data sequence meeting the requirements, then the added positive values are solved and restored by using an inequality, and finally the prediction result is optimized by using a residual correction model.
In the implementation process, when the prediction accuracy of the price prediction model does not reach the accuracy threshold, the price prediction model is optimized through the residual correction model, so that the prediction accuracy of the price prediction model can reach the accuracy threshold, and the prediction accuracy of the price prediction model is improved.
In a possible implementation manner, before optimizing the prediction result of the price prediction model by using the residual error correction model, the method further includes: determining a time series response function of the residual error sequence according to the time series response function; and restoring the time sequence response function of the residual sequence into the original residual sequence so as to optimize the prediction result of the price prediction model through the original residual sequence.
The time series response function of the residual sequence here is:
restoring the time series response function of the residual sequence into a simulated forward residual sequence of the original data:
further reducing the simulated forward residual sequence of the original data to an original residual sequence:
wherein,
is based on a time-series response function>
Is to be identifiedIn the development of (D), in the presence of a characteristic number of gray>
Is gray endogenous control and/or>
For the original data, is asserted>
For an analog forward residual sequence of raw data, be->
For an original residual sequence, <' > based on>
Is an added positive constant of the residual sequence.
Alternatively, the overlap-subtract method may be employed in restoring the time-series response function of the residual sequence to the simulated forward residual sequence of the original data and restoring the simulated forward residual sequence of the original data to the original residual sequence.
In some embodiments, if there is no negative number in the sequence number of the residual data, the sequence number of the residual data does not need to be processed in a forward direction, and when the time-series response function of the residual sequence is restored to the original residual sequence, the time-series response function of the residual sequence can be directly restored to the original residual sequence.
It can be understood that, after determining the original residual sequence, the original data sequence may be added to the original residual sequence, and then an optimized sequence of the price prediction model is obtained as follows:
the optimized sequence is the result predicted by the price prediction model.
In the implementation process, before optimizing the price prediction model, an original residual sequence is determined through a series of calculations, so that the prediction result of the price prediction model is optimized through the original residual sequence. Namely, a residual error correction model is established before the price prediction model is optimized, so that the price prediction model prediction result is optimized through the residual error correction model, and the result prediction precision can be improved.
In one possible implementation, step 201 includes establishing an original sequence from original data; performing accumulation operation on the original sequence to generate an accumulation generation sequence; and generating an adjacent mean value sequence by accumulating the generated sequences.
If the original data is: x (1) = Price (day 1); x (2) = Price (day 2); … x (n) = Price (dayn).
The original sequence established may be:
the generating of the accumulated sequence by accumulating the original sequence may be:
understandably, in order to reduce the randomness of the original data and enhance its ordering, the original data sequence is therefore modeled according to the idea of grey prediction
Performing an accumulation generation operation to obtain an accumulation generation sequence>
This is an operation to make the data white from grey. The running track in the gray data accumulation process can be found through accumulation generation operation, so that the integral property hidden in the original data is gradually presented, and further miscellaneous data are shownThe potential regularity is found in the phenomenon of disorder.
When data are collected, due to the fact that some difficulties which are not easy to overcome cause that data sequences have vacant or abnormal data which cannot be used, the method can carry out processing of constructing new data, filling old data holes, generating new data sequences and the like on abnormal data by using the adjacent mean value generation.
The neighbor mean sequence generated by accumulating the generated sequences is:
when the original data is processed, the original data may be accumulated, the sequence number of the original sequence subjected to the accumulation processing must be a non-negative number, otherwise, the accumulated result causes the cancellation of the positive and negative numbers, and thus, the law of potential increment of the accumulated sequence cannot be realized.
In some embodiments, the method further comprises: and carrying out level ratio checking processing on the original sequence. The level ratio checking process performed on the original sequence here includes: calculating a grade ratio; and judging whether the level ratio is within the level ratio threshold range, and if so, processing the original sequence to generate an adjacent mean value sequence. And if the level ratio is not within the level ratio threshold range, the original sequence is determined again.
The step ratio calculation formula here is:
wherein,
is a step ratio, is greater than or equal to>
Is the original data sequence.
The above-mentioned level ratio threshold range may be:
an interval.
In the implementation process, the original data is serialized before the model is constructed, so that the integral property hidden in the original data can be gradually presented, the potential rule of the original data is found from the phenomenon of miscellaneous disorder, the price of the object to be predicted can be predicted accurately by the price prediction model in a future period of time, the prediction of irregular change data is realized, the requirement for variable selection is reduced, and the accuracy of price prediction is improved.
Based on the same application concept, a price prediction model creation device corresponding to the price prediction model creation method is further provided in the embodiment of the present application, and since the principle of solving the problem of the device in the embodiment of the present application is similar to that of the embodiment of the price prediction model creation method, the implementation of the device in the embodiment of the present application can refer to the description in the embodiment of the method, and repeated details are not repeated.
Please refer to fig. 2, which is a functional module diagram of a price prediction model creation apparatus according to an embodiment of the present application. Each module in the price prediction model creation apparatus in this embodiment is configured to execute each step in the above method embodiments. The price prediction model creating device comprises a processing module 301, a building module 302 and a determining module 303; wherein,
the processing module 301 is configured to perform serialization processing on raw data, where the raw data is data to be predicted of an object to be predicted within a preset time period.
The construction module 302 is configured to construct a gray prediction model from the processed raw data.
The determining module 303 is configured to determine a price prediction model by solving the gray prediction model, where the price prediction model is used to predict the price of the object to be predicted.
In a possible implementation, the determining module 303 is further configured to: constructing a data matrix according to the grey prediction model; calculating the data matrix to obtain the development gray number to be identified and the endogenous control quantity of the gray prediction model; and determining the price prediction model according to the development grey number to be identified and the endogenous control quantity.
In one possible embodiment, the price prediction model creating device further includes: the prediction module is used for determining a periodic response function according to the price prediction model; discretizing the periodic response function to determine a time series response function; and restoring the time series response function, and predicting the price of the object to be predicted through the restored time series corresponding function to obtain a price prediction result.
In one possible embodiment, the price prediction model creating device further includes: and the judging module is used for judging whether the prediction precision of the price prediction model reaches a precision threshold value according to the price prediction result.
In one possible embodiment, the price prediction model creating device further includes: and the optimization module is used for optimizing the prediction result of the price prediction model through a residual error correction model if the prediction precision of the price prediction model does not reach the precision threshold value.
In one possible embodiment, the price prediction model creating device further includes: the restoring module is used for determining a time series response function of the residual error sequence according to the time series response function; and restoring the time sequence response function of the residual sequence into an original residual sequence so as to optimize the prediction result of the price prediction model through the original residual sequence.
In a possible implementation, the processing module 301 is further configured to: establishing an original sequence according to the original data; performing accumulation operation on the original sequence to generate an accumulation generation sequence; and generating an adjacent mean sequence through the accumulation generation sequence.
To facilitate understanding of the embodiment, the following describes an electronic device for executing the price prediction model creation method disclosed in the embodiment of the present application in detail.
As shown in fig. 3, is a block schematic diagram of an electronic device. The electronic device 100 may include a memory 111 and a processor 113. It will be understood by those of ordinary skill in the art that the structure shown in fig. 3 is merely exemplary and is not intended to limit the structure of the electronic device 100. For example, electronic device 100 may also include more or fewer components than shown in FIG. 3, or have a different configuration than shown in FIG. 3.
The memory 111 and the processor 113 are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The processor 113 is used to execute the executable modules stored in the memory.
The Memory 111 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 111 is used for storing a program, the processor 113 executes the program after receiving an execution instruction, and the method executed by the electronic device 100 defined by the process disclosed in any embodiment of the present application may be applied to the processor 113, or implemented by the processor 113.
The processor 113 may be an integrated circuit chip having signal processing capability. The Processor 113 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The electronic device 100 in this embodiment may be configured to perform each step in each method provided in this embodiment. The implementation of the price prediction model creation method is described in detail below by several embodiments.
Furthermore, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the price prediction model creation method in the above method embodiment.
The computer program product of the price prediction model creation method provided in the embodiment of the present application includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the steps of the price prediction model creation method described in the above method embodiment, which may be referred to in detail in the above method embodiment, and are not described herein again.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes. It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of another like element in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for creating a price prediction model, comprising:
performing serialization processing on original data, wherein the original data is the data to be predicted corresponding to the object to be predicted within a preset time period;
constructing a gray prediction model according to the processed original data;
and determining a price prediction model by solving the grey prediction model, wherein the price prediction model is used for predicting the price of the object to be predicted.
2. The method of claim 1, wherein determining a price prediction model by solving the gray prediction model comprises:
constructing a data matrix according to the grey prediction model;
calculating the data matrix to obtain the development gray number to be identified and the endogenous control quantity of the gray prediction model;
and determining the price prediction model according to the development grey number to be identified and the endogenous control quantity.
3. The method of claim 1, wherein after determining a price prediction model by solving the gray prediction model, the method further comprises:
determining a periodic response function according to the price prediction model;
discretizing the periodic response function to determine a time series response function;
and restoring the time series response function, and predicting the price of the object to be predicted through the restored time series corresponding function to obtain a price prediction result.
4. The method according to claim 3, wherein after predicting the price of the object to be predicted through the reduced time series corresponding function to obtain a price prediction result, the method further comprises:
and judging whether the prediction precision of the price prediction model reaches a precision threshold value or not according to the price prediction result.
5. The method of claim 4, further comprising:
and if the prediction precision of the price prediction model does not reach the precision threshold value, optimizing the prediction result of the price prediction model through a residual correction model.
6. The method of claim 5, wherein prior to optimizing the prediction of the price prediction model by the residual modification model, the method further comprises:
determining a time series response function of the residual error sequence according to the time series response function;
and restoring the time sequence response function of the residual sequence into an original residual sequence so as to optimize the prediction result of the price prediction model through the original residual sequence.
7. The method of claim 1, wherein the serializing the raw data comprises:
establishing an original sequence according to the original data;
performing accumulation operation on the original sequence to generate an accumulation generation sequence;
and generating an adjacent mean sequence through the accumulation generation sequence.
8. A price prediction model creation apparatus, comprising:
the processing module is used for carrying out serialization processing on original data, wherein the original data is to-be-predicted data of an object to be predicted in a preset time period;
the building module is used for building a gray prediction model according to the processed original data;
and the determining module is used for determining a price prediction model by solving the grey prediction model, and the price prediction model is used for predicting the price of the object to be predicted.
9. An electronic device, comprising: a processor, a memory storing machine-readable instructions executable by the processor, the machine-readable instructions when executed by the processor performing the steps of the method of any of claims 1 to 7 when the electronic device is operated.
10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, is adapted to carry out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310273635.8A CN115983892A (en) | 2023-03-21 | 2023-03-21 | Price prediction model creation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310273635.8A CN115983892A (en) | 2023-03-21 | 2023-03-21 | Price prediction model creation method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115983892A true CN115983892A (en) | 2023-04-18 |
Family
ID=85976510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310273635.8A Pending CN115983892A (en) | 2023-03-21 | 2023-03-21 | Price prediction model creation method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115983892A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2413985A1 (en) * | 2001-12-11 | 2003-06-11 | Recognia Inc. | Method of rule constrained statistical pattern recognition |
| CN108230043A (en) * | 2018-01-31 | 2018-06-29 | 安庆师范大学 | A kind of product area pricing method based on Grey Neural Network Model |
| CN111553407A (en) * | 2020-04-26 | 2020-08-18 | 广州珠江黄埔大桥建设有限公司 | Engineering project cost prediction method based on Markov gray model |
| CN111626789A (en) * | 2020-06-01 | 2020-09-04 | 武汉轻工大学 | House price prediction method, device, equipment and storage medium |
| CN114662780A (en) * | 2022-04-06 | 2022-06-24 | 国网冀北电力有限公司计量中心 | Carbon emission prediction method, carbon emission prediction device, electronic apparatus, and storage medium |
| CN114860496A (en) * | 2022-05-25 | 2022-08-05 | 苏州浪潮智能科技有限公司 | Cluster fault duration prediction method, device, equipment and storage medium |
-
2023
- 2023-03-21 CN CN202310273635.8A patent/CN115983892A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2413985A1 (en) * | 2001-12-11 | 2003-06-11 | Recognia Inc. | Method of rule constrained statistical pattern recognition |
| CN108230043A (en) * | 2018-01-31 | 2018-06-29 | 安庆师范大学 | A kind of product area pricing method based on Grey Neural Network Model |
| CN111553407A (en) * | 2020-04-26 | 2020-08-18 | 广州珠江黄埔大桥建设有限公司 | Engineering project cost prediction method based on Markov gray model |
| CN111626789A (en) * | 2020-06-01 | 2020-09-04 | 武汉轻工大学 | House price prediction method, device, equipment and storage medium |
| CN114662780A (en) * | 2022-04-06 | 2022-06-24 | 国网冀北电力有限公司计量中心 | Carbon emission prediction method, carbon emission prediction device, electronic apparatus, and storage medium |
| CN114860496A (en) * | 2022-05-25 | 2022-08-05 | 苏州浪潮智能科技有限公司 | Cluster fault duration prediction method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 石全 等: "《系统决策与建模》", 北京：国防工业出版社, pages: 163 - 165 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Meinshausen et al. | Monte Carlo methods for the valuation of multiple‐exercise options | |
| Wu et al. | A prediction method using the grey model GMC (1, n) combined with the grey relational analysis: a case study on Internet access population forecast | |
| Park et al. | An analysis of the ripple effect for disruptions occurring in circular flows of a supply chain network | |
| US8010324B1 (en) | Computer-implemented system and method for storing data analysis models | |
| US7251589B1 (en) | Computer-implemented system and method for generating forecasts | |
| Millner et al. | Ambiguity and climate policy | |
| Benkard et al. | Oblivious equilibrium for concentrated industries | |
| D’Amico et al. | Copula based multivariate semi-Markov models with applications in high-frequency finance | |
| EP3371764A1 (en) | Systems and methods for pricing optimization with competitive influence effects | |
| Agliari et al. | Inflation targeting, recursive inattentiveness, and heterogeneous beliefs | |
| Dobbs | Replacement investment: Optimal economic life under uncertainty | |
| CN116188061B (en) | Commodity sales predicting method and device, electronic equipment and storage medium | |
| Gulay et al. | Comparison of forecasting performances: Does normalization and variance stabilization method beat GARCH (1, 1)‐type models? Empirical Evidence from the Stock Markets | |
| CN112150205A (en) | Price prediction method and device and electronic equipment | |
| Çanakoğlu et al. | Portfolio selection with imperfect information: A hidden Markov model | |
| CN117132315A (en) | Active user prediction method, device, equipment and storage medium | |
| CN109993374B (en) | Cargo quantity prediction method and device | |
| CN111783883A (en) | Abnormal data detection method and device | |
| CN115983892A (en) | Price prediction model creation method and device, electronic equipment and readable storage medium | |
| CN115983897A (en) | Engineering quantity measuring method, device, equipment and storage medium | |
| Balogh et al. | Profit Forecast Model Using Monte Carlo Simulation in Excel | |
| CN115146997A (en) | Evaluation method and device based on power data, electronic equipment and storage medium | |
| CN113129127A (en) | Early warning method and device | |
| CN114418776A (en) | Data processing method, device, terminal equipment and medium | |
| CN112669093A (en) | Ocean economy prediction method, system, electronic device 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230418 |