CN109325811A - Value of house prediction technique, device, computer equipment and storage medium - Google Patents
Value of house prediction technique, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109325811A CN109325811A CN201811291737.8A CN201811291737A CN109325811A CN 109325811 A CN109325811 A CN 109325811A CN 201811291737 A CN201811291737 A CN 201811291737A CN 109325811 A CN109325811 A CN 109325811A
- Authority
- CN
- China
- Prior art keywords
- index
- value
- house
- prediction
- data
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves smart city technical fields, applied to real estate industry, in particular to a kind of Value of house prediction technique, device, computer equipment and storage medium, wherein, method includes obtaining the index and Value of house index that influence Value of house, and index and Value of house index to extraction carry out quantization and standardization, and the shortlist data set of index is formed according to default shortlist create-rule, according to shortlist data set, constructs room rate prediction prediction model and carry out Value of house prediction.In whole process, quantization and standardization are carried out to data, reduce the influence of abnormal data, and and the training that shortlist data set carries out model is rationally generated based on having the shortlist create-rule that real estate models generate in real estate industry's expertise and historical record, room rate prediction prediction model can be accurately obtained, to realize the Accurate Prediction to Value of house.
Description
Technical field
This application involves prediction electric powder predictions, more particularly to a kind of Value of house prediction technique, device, computer
Equipment and storage medium.
Background technique
In real life, room rate has become the focal point of people's daily life, and the variation of room rate affects each row
The heart of each industry and ordinary people is whether engaged in the professional of the industries such as development of real estate, Real Estate Finance and building
Or ordinary people is intended to can have a more accurately prediction prediction to the following room rate tendency.
Traditional room rate prediction majority is that the appraiser of profession is supplied based on the proximal segment time come some regional Basic Housing Price, the source of houses
Relationship, policy and experience is needed to provide room rate prediction.This mode can generally depend critically upon the subjective judgement of appraiser
And experience, for the room rate of the same area, different appraisers finally show that room rate prediction may be different.
It can be seen that traditional room rate prediction technique is in significant ASIC limitation, room rate prediction result is not accurate enough.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of Value of house prediction for capableing of Accurate Prediction room rate
Method, apparatus, computer equipment and storage medium.
A kind of Value of house prediction technique, which comprises
Value of house historical data in region to be predicted is obtained, extracting from the Value of house historical data influences house valence
The index and Value of house index of value；
Index to extraction and Value of house index carry out quantification treatment, and index to extraction and Value of house index into
Row standardization；
According to the index and Value of house index after default shortlist create-rule and the quantization and standardization
Form the shortlist data set of index；
According to shortlist data set, room rate prediction prediction model is constructed.
Described according to shortlist data set in one of the embodiments, constructing room rate prediction prediction model includes:
Choosing first part's data in the shortlist data set is that training data leads to respectively according to the training data
Multiple default machine learning method training are crossed, different room rate prediction prediction models is constructed；
First part's data are training data in the selection shortlist data set, according to the training data, are divided
Not Tong Guo multiple default machine learning methods training, after constructing different room rate prediction prediction models further include:
Choosing second part data in the shortlist data set is test data, looks forward to the prospect and predicts to the different room rate
Model is tested, before selecting the corresponding room rate of the smallest machine learning method of mean error to look forward to the prospect prediction model as optimal room rate
Look forward or upwards prediction model.
First part's data are training data in the selection shortlist data set in one of the embodiments,
According to the training data, respectively by multiple default machine learning method training, different room rate prediction prediction models is constructed
Include:
Configuration is grouped to all indexs in the shortlist data set, according to grouping situation, from short name forms data
Concentrate obtain it is each grouping it is corresponding enter modular character training data；
By it is each grouping it is corresponding enter modular character training data, multiple default machine learning methods are trained,
Construct different room rate look-forward models；
Second part data are test data in the selection shortlist data set, are looked forward to the prospect to the different room rate
Prediction model is tested, and selecting the corresponding room rate prediction prediction model of the smallest machine learning method of mean error is optimal room
Valence prediction prediction model include:
According to the grouping situation, obtained from shortlist data set each grouping it is corresponding enter modular character test number
According to；
By it is each grouping it is corresponding enter modular character test data, to the corresponding room rate of each machine learning method look forward to the prospect mould
The accuracy of type is tested；
The mean error of the corresponding test result of each room rate look-forward model is calculated, it is corresponding to choose the smallest algorithm of mean error
Room rate prediction prediction model as optimal room rate look-forward model.
The acquisition Value of house historical data in region to be predicted includes: in one of the embodiments,
Obtain the corresponding room rate prediction predictive factor system in region to be predicted；
It is looked forward to the prospect predictive factor system according to the corresponding room rate in the region to be predicted, obtains region Value of house to be predicted and go through
History data.
The room rate prediction predictive factor system includes main gene, is attached to the main cause in one of the embodiments,
The slave factor of son, the index for being attached to the subfactor from the factor and the characterization subfactor, the main gene includes macro
See economic indicator main gene, meso-economics index main gene, urban planning main gene, public opinion influence main gene and policies and regulations
Main gene, the macro-performance indicator main gene include world economy index, Country reading, currency bank, real estate and
Construction industry and the slave factor in financial market；Meso-economics index main gene includes urban economy, urban life, real estate and builds
Build the slave factor in industry and second-hand house market；Urban planning main gene includes the slave factor of regional city planning to be predicted；Public opinion
Influence main gene from include mainstream media, the Internet portal and forum, from the slave factor of media and search engine temperature；Policy
Regulation main gene includes the slave factor of the urban policy in national policy and region to be predicted.
In one of the embodiments, before the index and Value of house index progress quantification treatment of described pair of extraction, also
Include:
Identify subjective factor in the index extracted and Value of house index；
Independent model is established respectively for the subjective factor, and subjective factor is corresponded into situation in the independent model
It is divided into multiple types；
Specific decision condition is set for each type situation, and is assigned respectively for each type different decision result
It is worth corresponding index value, obtains assignment rule；
The described pair of index extracted and Value of house index carry out quantification treatment
According to the assignment rule, index and Value of house index to extraction carry out quantification treatment.
A kind of Value of house prediction meanss, described device include:
Data acquisition module, for obtaining Value of house historical data in region to be predicted, from the Value of house history number
According to the middle index and Value of house index for extracting influence Value of house；
Processing module, for extraction index and Value of house index carry out quantification treatment, and to the index of extraction and
Value of house index is standardized；
Dataset generation module, after according to shortlist create-rule and the quantization and standardization is preset
Index and Value of house index form the shortlist data set of index；
Model construction module, for constructing room rate prediction prediction model according to shortlist data set.
The model construction module is also used to choose in the shortlist data set first in one of the embodiments,
Divided data is training data, according to the training data, respectively by multiple default machine learning method training, is constructed different
Room rate prediction prediction model；
The Value of house prediction meanss further include:
Optimization module is test data for choosing second part data in the shortlist data set, to the difference
Room rate prediction prediction model tested, select the smallest machine learning method of mean error corresponding room rate prediction prediction mould
Type is optimal room rate prediction prediction model.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device is realized when executing the computer program such as the step of the above method.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It realizes when row such as the step of above-mentioned method.
Premises Value Prediction Methods, device, computer equipment and storage medium obtain the index for influencing Value of house
And Value of house index, index and Value of house index to extraction carry out quantification treatment, and to the index and house of extraction
Value index nember is standardized, and the shortlist data set of index is formed according to default shortlist create-rule, according to short name
Forms data collection, building room rate prediction prediction model carry out Value of house prediction.In whole process, quantization and standard are carried out to data
Change processing reduces the influence of abnormal data, and and based on premises existing in real estate industry's expertise and historical record
It produces the shortlist create-rule that model generates and rationally generates the training that shortlist data set carries out model, can accurately obtain room rate
Prediction prediction model, to realize the Accurate Prediction to Value of house.
Detailed description of the invention
Fig. 1 is the flow diagram of Value of house prediction technique in one embodiment；
Fig. 2 is the flow diagram of Value of house prediction technique in another embodiment；
Fig. 3 is the structural block diagram of Value of house prediction meanss in one embodiment；
Fig. 4 is the structural block diagram of Value of house prediction meanss in another embodiment；
Fig. 5 is the experimental result comparison diagram using premises Value Prediction Methods；
Fig. 6 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.
As shown in Figure 1, a kind of Value of house prediction technique, method include:
S200: obtaining Value of house historical data in region to be predicted, and extracting from Value of house historical data influences house
The index and Value of house index of value.
Region to be predicted refers to that the target area of this Value of house prediction, the region can be some administrative region,
Such as Beijing, Shanghai, Guangzhou etc..The region can also be a smaller range, such as some cell etc..Region house to be predicted
Value historical data can be the terminal in current entry and acquire the data being sent under server aggregates, can be server
Outside, which is obtained, by means such as internets has corresponding data.Extracting in Value of house historical data influences Value of house
Index and Value of house index, the index for influencing Value of house includes: all kinds of macro-performance indicators, for example, GDP, CPI, PMI,
Per capita disposable income etc.；Meso-economics index, for example, each city (area) Urbanization Rate, subway mileage, per capita living space with
And the commercial house area for sale etc.；Policies and regulations such as real estate limit is sold limit purchase policy, first suite interest rate policy, is sent out in city for a long time
Exhibition planning etc..Value of house index specifically can be room rate, may include hanging disk and transaction value.It is non-essential, in order to true
Protect the accuracy of subsequent Value of house prediction, the Value of house historical data in region to be predicted in the available proximal segment time, example
It such as obtains nearest 1 year, obtain the Value of house historical data in region to be predicted in the nearest 6 months time, for the number of acquisition
It rationally arranges corresponding index according to the time is also based on, such as using the moon as foundation.Such as by taking " resident population " this index as an example,
The history value of the index be [h1, h2 ..., hi ...], wherein hi indicates i-th month resident population within a preset time
Number.
S400: index and Value of house index to extraction carry out quantification treatment, and to the index and Value of house of extraction
Index is standardized.
The purpose for carrying out quantification treatment is by the subjective factor parameter side of being quantified as in the index of extraction and Value of house index
Just the data handled.The purpose being standardized is will to remove exceptional value in the index extracted and Value of house index, become
Gesture and seasonal effect.Index and Value of house index to extraction carry out quantification treatment and standardization further removes in data
Subjective factor, exceptional value, trend and seasonal parameter, provide reliable data basis for subsequent objective prediction Value of house.
S600: according to the index and Value of house index after default shortlist create-rule and quantization and standardization
Form the shortlist data set of index.
Default shortlist create-rule specifically can be based on real estate industry expert based on historical data
Have real estate models in experience and historical record to generate.Real estate industry's expertise refers to the real estate in historical experience
The relevant some empirical datas of industry and information, for example, land supply amount room rate is moved towards influence degree, bank's lending interest rate
The influence degree etc. that influence degree, the urban economy growth rate of room rate trend move towards room rate.Existing real estate models are
Mature real estate models before feeling the pulse with the finger-tip, such as conventional real estate models neural network based, the room based on big data analysis
Real estate model.Default shortlist create-rule is to be tied the two based on having had ripe experience and having had real estate models
Close and discuss generation.Record has corresponding in history use for each index in this way in default shortlist create-rule
Significance level.In simple terms, the index generation that according to preset shortlist create-rule, can filter out preset quantity here is short
List, and shortlist data set is generated, which can be used as the training data of following model.
S800: according to shortlist data set, room rate prediction prediction model is constructed.
Specifically, the room rate prediction prediction model based on default machine learning method can be constructed, machine learning is preset
Method may include linear regression, Lasso, ridge regression (Ridge Regression), random forest, k nearest neighbor algorithm (k
Neighbour Regression), decision tree, Support vector regression (SVR), grad enhancement return
(GradientBoostingRegressor) model and XGBoost algorithm are made with the shortlist data set that step S600 is obtained
Corresponding room rate prediction prediction model can be constructed by any one of the above machine learning method for training data.
Premises Value Prediction Methods obtain the index and Value of house index for influencing Value of house, to extraction
Index and Value of house index carry out quantification treatment, and index to extraction and Value of house index are standardized, root
The shortlist data set that index is formed according to default shortlist create-rule constructs room rate prediction prediction according to shortlist data set
Model carries out Value of house prediction.In whole process, quantization and standardization are carried out to data, reduce the shadow of abnormal data
It rings, and and generates rule based on having the shortlist that real estate models generate in real estate industry's expertise and historical record
The training that shortlist data set carries out model is then rationally generated, room rate prediction prediction model can be accurately obtained, thus realization pair
The Accurate Prediction of Value of house.
As shown in Fig. 2, step S800 includes: to choose first part in shortlist data set in one of the embodiments,
Data are training data, according to training data, respectively by multiple default machine learning method training, before constructing different room rates
Look forward or upwards prediction model；
After step S800 further include:
S900: choosing second part data in shortlist data set is test data, to different room rate prediction prediction moulds
Type is tested, and the corresponding room rate prediction prediction model of the smallest machine learning method of mean error is selected to look forward to the prospect for optimal room rate
Prediction model.
Machine learning method includes linear regression, Lasso, ridge regression (Ridge Regression), random forest, K close
Adjacent algorithm (k Neighbour Regression), decision tree, Support vector regression (SVR), grad enhancement return
(GradientBoostingRegressor) model and XGBoost algorithm, different room rates can be constructed based on these algorithms
Prediction prediction model.Shortlist data intensive data is divided into training data and test data, different machines learning method is instructed
The room rate prediction prediction model got is tested, and the corresponding room rate prediction of the smallest machine learning method of mean error is selected
Prediction model is optimal room rate prediction prediction model, to realize most accurately Value of house prediction prediction.
Choosing first part's data in shortlist data set in one of the embodiments, is training data, according to training
Data, respectively by multiple default machine learning method training, constructing different room rate prediction prediction models includes: to shortlist
All indexs in data set are grouped configuration, according to grouping situation, each grouping are obtained from shortlist data set and is corresponded to
The training data for entering modular character；By it is each grouping it is corresponding enter modular character training data, to multiple default machine learning
Method is trained, and constructs different room rate look-forward models；
Choosing second part data in shortlist data set is test data, is carried out to different room rate prediction prediction models
Test selects the corresponding room rate prediction prediction model of the smallest machine learning method of mean error to look forward to the prospect for optimal room rate and predicts mould
Type include: according to grouping situation, obtained from shortlist data set it is each grouping it is corresponding enter modular character test data；Pass through
Each grouping it is corresponding enter modular character test data, to the accuracy of the corresponding room rate look-forward model of each machine learning method into
Row test.
Specifically, configuration can be grouped to all indexs in shortlist data set, according to grouping situation, respectively
Obtained from shortlist data set it is each grouping it is corresponding enter modular character training data and test data；Pass through each grouping pair
That answers enters the training data of modular character, is trained to multiple default machine learning methods, constructs different room rate look-forward models；
By it is each grouping it is corresponding enter modular character test data, to the accurate of the corresponding room rate look-forward model of each machine learning method
Property is tested；The mean error of the corresponding test result of each room rate look-forward model is calculated, the smallest algorithm of mean error is chosen
Corresponding room rate prediction prediction model is as optimal room rate look-forward model.
Obtaining Value of house historical data in region to be predicted in one of the embodiments, includes: to obtain region to be predicted
Corresponding room rate prediction predictive factor system；According to the corresponding room rate prediction predictive factor system in region to be predicted, obtain to pre-
Survey region Value of house historical data.
A large amount of indexs for influencing Value of house are carried in room rate prediction predictive factor system with Value of house index, shadow
The index for ringing Value of house includes: all kinds of macro-performance indicators, such as GDP, CPI, PMI, per capita disposable income etc.；Middle sight
Economic indicator, such as each city (area) Urbanization Rate, subway mileage, per capita living space and the commercial house area for sale etc.；Political affairs
Plan regulation such as real estate limit sells limit purchase policy, first suite interest rate policy, the planning of city Long-and Medium-term Development etc..Value of house index
It specifically can be room rate, may include hanging disk and transaction value.Macro-performance indicator main gene includes world economy index, state
People's economic indicator, currency bank, real estate and construction industry and the slave factor in financial market；Meso-economics index main gene includes
Urban economy, urban life, real estate and construction industry and the slave factor in second-hand house market；Urban planning main gene includes to pre-
Survey the slave factor of regional city planning；Public opinion influence main gene from include mainstream media, the Internet portal and forum, from media with
And the slave factor of search engine temperature；Policies and regulations main gene include the urban policy in national policy and region to be predicted it is slave because
Son.Non-essential, in order to ensure the accuracy of subsequent Value of house prediction, in the available proximal segment time region room to be predicted
Room is worth historical data, such as obtains the Value of house history in region to be predicted in the times such as nearest 1 year, acquisition nearest 6 months
Data are also based on the time and rationally arrange corresponding index for the data of acquisition, such as using the moon as foundation.
Before carrying out quantification treatment to the index of extraction and Value of house index in one of the embodiments, further includes:
Identify subjective factor in the index extracted and Value of house index；Independent model is established respectively for subjective factor, in independence
Subjective factor is corresponded into situation in model and is divided into multiple types；Specific decision condition is set for each type situation, and
And for the corresponding index value of each type different decision result difference assignment, assignment rule is obtained；To the index and room of extraction
It includes: that index according to assignment rule, to extraction and Value of house index carry out at quantization that room value index nember, which carries out quantification treatment,
Reason.
By taking policies and regulations as an example, independent policies and regulations model is constructed, according to Policy Background and new policy itself, by policy
Background is divided into loose, tightening, turns tight, by tightly turning loose 4 classes by pine, and new policy respective heights are loose, loose, tightening, height are tightened
Four classes finally influence the historical experience of Value of house trend based on all kinds of policies, give the corresponding index value of all kinds of policies respectively, obtain
To assignment rule.When needing index and Value of house index carries out quantification treatment, according to above-mentioned assignment rule, to the finger of extraction
Mark and Value of house index distinguish assignment, to realize quantification treatment.
As shown in figure 3, a kind of Value of house prediction meanss, device include:
Data acquisition module 200, for obtaining Value of house historical data in region to be predicted, from Value of house historical data
It is middle to extract the index and Value of house index for influencing Value of house；
Processing module 400, for the index and Value of house index progress quantification treatment to extraction, and to the index of extraction
It is standardized with Value of house index；
Dataset generation module 600, after according to shortlist create-rule and quantization and standardization is preset
Index and Value of house index form the shortlist data set of index；
Model construction module 800, for constructing room rate prediction prediction model according to shortlist data set.
Premises value forecasting device, data acquisition module 200 obtain the index and house valence for influencing Value of house
Value index number, the index and Value of house index progress quantification treatment of 400 pairs of processing module extractions, and to the index and house of extraction
Value index nember is standardized, and dataset generation module 600 forms the short name of index according to default shortlist create-rule
It is pre- to construct room rate prediction prediction model progress Value of house according to shortlist data set for forms data collection, model construction module 800
It surveys.In whole process, quantization and standardization are carried out to data, reduce the influence of abnormal data, and and based on real estate
Have the shortlist create-rule that real estate models generate in industry specialists experience and historical record and rationally generates short name odd number
The training that model is carried out according to collection can accurately obtain room rate prediction prediction model, to realize the Accurate Prediction to Value of house
As shown in figure 4, model construction module 800 is also used to choose in shortlist data set in one of the embodiments,
First part's data are training data, and according to training data, respectively by multiple default machine learning method training, building is different
Room rate look forward to the prospect prediction model；
Value of house prediction meanss further include optimization module 900, for choosing second part data in shortlist data set
For test data, different room rate prediction prediction models is tested, the smallest machine learning method pair of mean error is selected
The room rate prediction prediction model answered is optimal room rate prediction prediction model.
Data acquisition module 200 is also used to obtain the corresponding room rate prediction in region to be predicted in one of the embodiments,
Predictive factor system；According to the corresponding room rate prediction predictive factor system in region to be predicted, region Value of house to be predicted is obtained
Historical data.
In one of the embodiments, room rate prediction predictive factor system include main gene, be attached to main gene it is slave because
Son, the index for being attached to from the subfactor of the factor and characterizing subfactor, main gene includes macro-performance indicator main gene, middle sight
Economic indicator main gene, urban planning main gene, public opinion influence main gene and policies and regulations main gene, macro-performance indicator master
The factor include world economy index, Country reading, currency bank, real estate and construction industry and financial market it is slave because
Son；Meso-economics index main gene include urban economy, urban life, real estate and construction industry and second-hand house market it is slave because
Son；Urban planning main gene includes the slave factor of regional city planning to be predicted；Public opinion influence main gene from include mainstream media,
The Internet portal and forum, from the slave factor of media and search engine temperature；Policies and regulations main gene include national policy and
The slave factor of the urban policy in region to be predicted.
Processing module 400 is also used to identify main in the index and Value of house index of extraction in one of the embodiments,
Sight factor；Establish independent model respectively for subjective factor, in independent model by subjective factor correspond to situation be divided into it is more
Seed type；Specific decision condition is set for each type situation, and is assigned respectively for each type different decision result
It is worth corresponding index value, obtains assignment rule；According to assignment rule, index and Value of house index to extraction are carried out at quantization
Reason.
Specific about Value of house prediction meanss limits the limit that may refer to above for Value of house prediction technique
Fixed, details are not described herein.Modules in premises value forecasting device can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In practical application, a certain region room rate in Chengdu is predicted with the room rate prediction prediction model of the application building,
Shown in its obtained experimental result Fig. 5.It can be accurately to a certain area in Chengdu based on the visible the application room rate prediction prediction model of Fig. 5
Domain room rate is predicted.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.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 of machine equipment is for storing Value of house historical data.The network interface of the computer equipment is used for and external terminal
It is communicated by network connection.To realize a kind of Value of house prediction technique when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 6, 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 is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor perform the steps of when executing computer program
Value of house historical data in region to be predicted is obtained, extracting from Value of house historical data influences Value of house
Index and Value of house index；
Index to extraction and Value of house index carry out quantification treatment, and index to extraction and Value of house index into
Row standardization；
According to default shortlist create-rule and quantization and standardization after index and Value of house index formed
The shortlist data set of index；
According to shortlist data set, room rate prediction prediction model is constructed.
In one embodiment, it is also performed the steps of when processor executes computer program
Choosing first part's data in shortlist data set is training data, according to training data, respectively by multiple pre-
If machine learning method training, different room rate prediction prediction models is constructed；Choose second part data in shortlist data set
For test data, different room rate prediction prediction models is tested, the smallest machine learning method pair of mean error is selected
The room rate prediction prediction model answered is optimal room rate prediction prediction model.
In one embodiment, it is also performed the steps of when processor executes computer program
Configuration is grouped to all indexs in shortlist data set, according to grouping situation, from shortlist data set
Obtain it is each grouping it is corresponding enter modular character training data；By it is each grouping it is corresponding enter modular character training data, it is right
Multiple default machine learning methods are trained, and construct different room rate look-forward models；According to grouping situation, from short name forms data
Concentrate obtain it is each grouping it is corresponding enter modular character test data；By it is each grouping it is corresponding enter modular character test number
According to testing the accuracy of the corresponding room rate look-forward model of each machine learning method；It is corresponding to calculate each room rate look-forward model
Test result mean error, choose the smallest algorithm of mean error corresponding room rate prediction prediction model as optimal room rate
Look-forward model.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain the corresponding room rate prediction predictive factor system in region to be predicted；According to the corresponding room rate prediction in region to be predicted
Predictive factor system obtains Value of house historical data in region to be predicted.
In one embodiment, it is also performed the steps of when processor executes computer program
Identify subjective factor in the index extracted and Value of house index；Establish independent mould respectively for subjective factor
Subjective factor is corresponded to situation in independent model and is divided into multiple types by type；Explicitly sentence for the setting of each type situation
Fixed condition, and for the corresponding index value of each type different decision result difference assignment, obtain assignment rule；According to assignment
Rule, index and Value of house index to extraction carry out quantification treatment.
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
Value of house historical data in region to be predicted is obtained, extracting from Value of house historical data influences Value of house
Index and Value of house index；
Index to extraction and Value of house index carry out quantification treatment, and index to extraction and Value of house index into
Row standardization；
According to default shortlist create-rule and quantization and standardization after index and Value of house index formed
The shortlist data set of index；
According to shortlist data set, room rate prediction prediction model is constructed.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Choosing first part's data in shortlist data set is training data, according to training data, respectively by multiple pre-
If machine learning method training, different room rate prediction prediction models is constructed；Choose second part data in shortlist data set
For test data, different room rate prediction prediction models is tested, the smallest machine learning method pair of mean error is selected
The room rate prediction prediction model answered is optimal room rate prediction prediction model.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Configuration is grouped to all indexs in shortlist data set, according to grouping situation, from shortlist data set
Obtain it is each grouping it is corresponding enter modular character training data；By it is each grouping it is corresponding enter modular character training data, it is right
Multiple default machine learning methods are trained, and construct different room rate look-forward models；According to grouping situation, from short name forms data
Concentrate obtain it is each grouping it is corresponding enter modular character test data；By it is each grouping it is corresponding enter modular character test number
According to testing the accuracy of the corresponding room rate look-forward model of each machine learning method；It is corresponding to calculate each room rate look-forward model
Test result mean error, choose the smallest algorithm of mean error corresponding room rate prediction prediction model as optimal room rate
Look-forward model.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Obtain the corresponding room rate prediction predictive factor system in region to be predicted；According to the corresponding room rate prediction in region to be predicted
Predictive factor system obtains Value of house historical data in region to be predicted.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Identify subjective factor in the index extracted and Value of house index；Establish independent mould respectively for subjective factor
Subjective factor is corresponded to situation in independent model and is divided into multiple types by type；Explicitly sentence for the setting of each type situation
Fixed condition, and for the corresponding index value of each type different decision result difference assignment, obtain assignment rule；According to assignment
Rule, index and Value of house index to extraction carry out quantification treatment.
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 Value of house prediction technique, which comprises
Value of house historical data in region to be predicted is obtained, extracting from the Value of house historical data influences Value of house
Index and Value of house index；
Index to extraction and Value of house index carry out quantification treatment, and index to extraction and Value of house index are marked
Quasi-ization processing；
According to default shortlist create-rule and it is described quantization and standardization after index and Value of house index formed
The shortlist data set of index；
According to shortlist data set, room rate prediction prediction model is constructed.
2. building room rate prediction is pre- the method according to claim 1, wherein described according to shortlist data set
Surveying model includes:
Choosing first part's data in the shortlist data set is training data, according to the training data, respectively by more
A default machine learning method training constructs different room rate prediction prediction models；
First part's data are that training data leads to respectively according to the training data in the selection shortlist data set
Multiple default machine learning methods training are crossed, after constructing different room rate prediction prediction models further include:
Choosing second part data in the shortlist data set is test data, to the different room rate prediction prediction model
It is tested, selects the corresponding room rate prediction prediction model of the smallest machine learning method of mean error pre- for the prediction of optimal room rate
Survey model.
3. according to the method described in claim 2, it is characterized in that, described choose first part's number in the shortlist data set
Different room rates respectively by multiple default machine learning method training, is constructed according to the training data according to for training data
Prediction prediction model include:
Configuration is grouped to all indexs in the shortlist data set, according to grouping situation, from shortlist data set
Obtain it is each grouping it is corresponding enter modular character training data；
By it is each grouping it is corresponding enter modular character training data, multiple default machine learning methods are trained, construct
Different room rate look-forward models；
Second part data are test data in the selection shortlist data set, look forward to the prospect and predict to the different room rate
Model carries out test
According to the grouping situation, obtained from shortlist data set each grouping it is corresponding enter modular character test data；
By it is each grouping it is corresponding enter modular character test data, to the corresponding room rate look-forward model of each machine learning method
Accuracy is tested.
4. the method according to claim 1, wherein described obtain Value of house historical data packet in region to be predicted
It includes:
Obtain the corresponding room rate prediction predictive factor system in region to be predicted；
It is looked forward to the prospect predictive factor system according to the corresponding room rate in the region to be predicted, obtains Value of house history number in region to be predicted
According to.
5. according to the method described in claim 4, it is characterized in that, the room rate prediction predictive factor system include main gene,
It is attached to the slave factor of the main gene, is attached to the subfactor from the factor and the index of the characterization subfactor, institute
Stating main gene includes macro-performance indicator main gene, meso-economics index main gene, urban planning main gene, public opinion influence main cause
Son and policies and regulations main gene, the macro-performance indicator main gene include world economy index, Country reading, currency
Bank, real estate and construction industry and the slave factor in financial market；Meso-economics index main gene includes urban economy, city life
Living, real estate and construction industry and the slave factor in second-hand house market；Urban planning main gene includes regional city planning to be predicted
The slave factor；Public opinion influence main gene from include mainstream media, the Internet portal and forum, from media and search engine temperature
The slave factor；Policies and regulations main gene includes the slave factor of the urban policy in national policy and region to be predicted.
6. the method according to claim 1, wherein the index and the Value of house index amount of progress of described pair of extraction
Before change processing, further includes:
Identify subjective factor in the index extracted and Value of house index；
Independent model is established respectively for the subjective factor, and subjective factor is corresponded into situation in the independent model and is divided
For multiple types；
Specific decision condition is set for each type situation, and distinguishes assignment pair for each type different decision result
The index value answered, obtains assignment rule；
The described pair of index extracted and Value of house index carry out quantification treatment
According to the assignment rule, index and Value of house index to extraction carry out quantification treatment.
7. a kind of Value of house prediction meanss, which is characterized in that described device includes:
Data acquisition module, for obtaining Value of house historical data in region to be predicted, from the Value of house historical data
Extract the index and Value of house index for influencing Value of house；
Processing module, for the index and Value of house index progress quantification treatment to extraction, and to the index and house of extraction
Value index nember is standardized；
Dataset generation module, for according to the index after default shortlist create-rule and the quantization and standardization
The shortlist data set of index is formed with Value of house index；
Model construction module, for constructing room rate prediction prediction model according to shortlist data set.
8. device according to claim 7, which is characterized in that the model construction module is also used to choose the shortlist
First part's data are training data in data set, according to the training data, pass through multiple default machine learning methods respectively
Training constructs different room rate prediction prediction models；
The Value of house prediction meanss further include:
Optimization module is test data for choosing second part data in the shortlist data set, to the different room
Valence prediction prediction model is tested, select the corresponding room rate of the smallest machine learning method of mean error look forward to the prospect prediction model for
Optimal room rate prediction prediction model.
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 6 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 6 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811291737.8A CN109325811A (en) | 2018-10-31 | 2018-10-31 | Value of house prediction technique, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811291737.8A CN109325811A (en) | 2018-10-31 | 2018-10-31 | Value of house prediction technique, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109325811A true CN109325811A (en) | 2019-02-12 |
Family
ID=65260010
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811291737.8A Pending CN109325811A (en) | 2018-10-31 | 2018-10-31 | Value of house prediction technique, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109325811A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109872003A (en) * | 2019-03-06 | 2019-06-11 | 中国科学院软件研究所 | Obj State prediction technique, system, computer equipment and storage medium |
| CN114819903A (en) * | 2022-04-28 | 2022-07-29 | 重庆锐云科技有限公司 | Method and device for setting broker incentive activity reward amount and computer equipment |
-
2018
- 2018-10-31 CN CN201811291737.8A patent/CN109325811A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109872003A (en) * | 2019-03-06 | 2019-06-11 | 中国科学院软件研究所 | Obj State prediction technique, system, computer equipment and storage medium |
| CN114819903A (en) * | 2022-04-28 | 2022-07-29 | 重庆锐云科技有限公司 | Method and device for setting broker incentive activity reward amount and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Martin et al. | On the empirical content of carbon leakage criteria in the EU Emissions Trading Scheme | |
| Hong et al. | Probabilistic electric load forecasting: A tutorial review | |
| CN109376936A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN109858957A (en) | Finance product recommended method, device, computer equipment and storage medium | |
| Mentis | Hypothetico-deductive and inductive approaches in ecology | |
| Minku et al. | How to make best use of cross-company data for web effort estimation? | |
| CN107230108A (en) | The processing method and processing device of business datum | |
| CN109615280A (en) | Employee's data processing method, device, computer equipment and storage medium | |
| CN109523068A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN110097216A (en) | For the prediction technique and device of enterprise development, server | |
| McCluskey | A critical review of computer assisted mass appraisal techniques | |
| CN109325811A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN115391561A (en) | Method and device for processing graph network data set, electronic equipment, program and medium | |
| CN109345035A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN109325868A (en) | Questionnaire data processing method, device, computer equipment and storage medium | |
| Kumar et al. | Stock Price Prediction Using Machine Learning | |
| Wanke et al. | Endogenous and exogenous performance sources in Asian Banking: A hybrid stochastic Multi-Criteria Decision-Making approach based on sign decomposition and transfer entropy | |
| CN109583940A (en) | Cell source of houses value parameter estimation method and device | |
| CN109242578A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| US11120503B2 (en) | Analysis and visual presentation of dataset components | |
| McCluskey et al. | Computer assisted mass appraisal and the property tax | |
| Brzezicka et al. | The applicability of the speculative frame method for detecting disturbances on the real estate market: evidence from Poland | |
| CN109544215A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN114254762A (en) | Interpretable machine learning model construction method and device and computer equipment | |
| CN110378481A (en) | Decision-making treatment method, apparatus, computer and storage medium based on rough set |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190212 |