CN109376936A - 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
- CN109376936A CN109376936A CN201811289837.7A CN201811289837A CN109376936A CN 109376936 A CN109376936 A CN 109376936A CN 201811289837 A CN201811289837 A CN 201811289837A CN 109376936 A CN109376936 A CN 109376936A
- Authority
- CN
- China
- Prior art keywords
- index
- value
- house
- data
- prediction
- 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 55
- 238000012549 training Methods 0.000 claims abstract description 49
- 238000000605 extraction Methods 0.000 claims abstract description 30
- 238000011002 quantification Methods 0.000 claims abstract description 14
- 238000013139 quantization Methods 0.000 claims abstract description 11
- 230000001932 seasonal effect Effects 0.000 claims abstract description 7
- 238000006243 chemical reaction Methods 0.000 claims description 48
- 238000012545 processing Methods 0.000 claims description 40
- 238000004590 computer program Methods 0.000 claims description 25
- 238000010801 machine learning Methods 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 8
- 238000012217 deletion Methods 0.000 claims description 6
- 230000037430 deletion Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 8
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 4
- 108090000623 proteins and genes Proteins 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000012417 linear regression Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0278—Product appraisal
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Finance (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (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: that the index and Value of house index that influence Value of house are extracted from Value of house historical data, index and Value of house index to extraction carry out quantization and standardization, filter out the variable and sample for meeting economics logic, extracting partial data in the variable and sample filtered out is training data, it is prediction target with Value of house index in region to be predicted, it constructs room rate prediction prediction model and carries out Value of house prediction.In whole process, the index and Value of house index of the influence Value of house to acquisition carry out quantification treatment and standardization, and removal exceptional value, trend and seasonal effect factor influence, accurately obtain training data, may be implemented to Value of house Accurate Prediction.
Description
Technical field
This application involves prediction electric powder predictions, more particularly to a kind of Value of house prediction technique, device, calculating
Machine 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 be profession appraiser based on the proximal segment time come some area Basic Housing Price, the source of houses
Relation between supply and demand, policy and experience provide room rate prediction.This mode can generally depend critically upon the subjectivity of appraiser
Judgement 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 technique, device, computer and set
Standby 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
The index and Value of house index of value；
Index and Value of house index to extraction carry out quantification treatment, and index and Value of house index to extraction
It is standardized；
From after quantization and standardization index and Value of house index in filter out and meet the variable and sample of economics logic
This；
Extracting partial data in the variable and sample filtered out is training data, with Value of house index in region to be predicted
To predict target, building room rate prediction prediction model.
The index of the extraction and Value of house index removal exceptional value, trend and season in one of the embodiments,
Section property influence factor, which is standardized, includes:
Rule is filled up according to preset missing values, missing values are carried out to the index that there is missing in the index and are filled up, are obtained
The data set finished is filled up to missing values；
The data set finished is filled up for missing values, and according to preset index frequency conversion rule, index is carried out at frequency conversion
Reason；
According to the index after frequency-conversion processing, the corresponding derivative index of index is determined；
To the derivative index progress index conversion, at the derivative index and corresponding frequency conversion after index is converted
Index after reason merges, the index after obtaining standardization.
The preset missing values fill up rule in one of the embodiments, are as follows: miss rate are less than or equal to pre-
If the index of threshold value, according to index property and index deletion condition, filled up to missing values are carried out there are the index of missing values；It is right
It is rejected in the index that miss rate is greater than the preset threshold
It is described in one of the embodiments, to include: to index progress frequency-conversion processing
Obtain the season index and annual index in index；
Monthly data is converted by the method for linear interpolation by the season index and the annual index.
The index according to after frequency-conversion processing in one of the embodiments, determines the corresponding derivative index packet of index
It includes:
Obtain default room rate prediction predictive factor system；
According to the default room rate prediction predictive factor system, derivative achievement data is obtained；
The achievement data that can directly acquire is identified from the derivative achievement data and need to be by other index operation sides
The achievement data of method determines the corresponding derivative index of each index.
Partial data is training data in the variable and sample that the extraction filters out in one of the embodiments, with
Value of house index in region to be predicted is prediction target, and building room rate prediction prediction model includes:
Extracting partial data in the variable and sample filtered out is training data, with Value of house index in region to be predicted
To predict target, respectively by multiple default machine learning method training, different room rate prediction prediction models is constructed；
Partial data is training data in the variable and sample that the extraction filters out, with region Value of house to be predicted
Index is prediction target, respectively by multiple default machine learning methods training, construct different room rate prediction prediction models it
Afterwards, further includes:
Choosing another part data in the variable and sample filtered out is test data, is looked forward to the prospect to the different room rate
Prediction model is tested, and it is optimal for selecting the corresponding room rate prediction prediction model of the smallest machine learning method of mean error
Room rate prediction prediction model.
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；
Data processing module, for the index and Value of house index progress quantification treatment to extraction, and to the finger of extraction
Mark and Value of house index are standardized；
Screening module, for from after quantization and standardization index and Value of house index in filter out and meet economics
The variable and sample of logic；
Model construction module is training data for extracting partial data in the variable and sample filtered out, with to be predicted
Region Value of house index is prediction target, building room rate prediction prediction model.
The data processing module is also used to fill up rule according to preset missing values in one of the embodiments, right
The index that there is missing in the index carries out missing values and fills up, and obtains missing values and fills up the data set finished；For missing values
The data set finished is filled up, according to preset index frequency conversion rule, frequency-conversion processing is carried out to index；After frequency-conversion processing
Index determines the corresponding derivative index of index；Index conversion is carried out to the derivative index, after index is converted described in spread out
Index after raw index and corresponding frequency-conversion processing merges, the index after obtaining standardization.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the place
Reason device was realized when executing the computer program such as a the step of stating 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, from Value of house historical data
The index and Value of house index for influencing Value of house are extracted, index and Value of house index to extraction carry out at quantization
Reason, and index to extraction and Value of house index are standardized, and filter out the variable and sample for meeting economics logic
This, extracting partial data in the variable and sample filtered out is training data, is prediction with Value of house index in region to be predicted
Target, building room rate prediction prediction model carry out Value of house prediction.Influence Value of house in whole process, to acquisition
Index and Value of house index carry out quantification treatment and standardization, removal exceptional value, trend and seasonal effect factor shadow
It rings, accurately obtains training data, may be implemented to Value of house Accurate Prediction.
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
In order to which the objects, technical solutions and advantages of the application are more clearly understood, with reference to the accompanying drawings and embodiments,
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application,
It is not used to limit 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 room to be predicted
Room value historical data can be the terminal in current entry and acquire the data being sent under server aggregates, can be clothes
Business device obtains outside by means such as internets and has corresponding data.Extracting in Value of house historical data influences house
The index and Value of house index of value, the index for influencing Value of house includes: all kinds of macro-performance indicators, such as GDP,
CPI, PMI, per capita disposable income etc.；Meso-economics index, such as each city (area) Urbanization Rate, subway mileage, live per capita
Room area and the commercial house area for sale etc.；Policies and regulations such as real estate limit sells limit purchase policy, first suite interest rate policy, city
City's Long-and Medium-term Development planning etc..Value of house index specifically can be room rate, may include hanging disk and transaction value.It is non-must
It wants, the region Value of house to be predicted in order to ensure the accuracy of subsequent Value of house prediction, in the available proximal segment time
Historical data, such as the Value of house historical data in region to be predicted in the times such as nearest 1 year, acquisition nearest 6 months is obtained,
It is also based on the time for the data of acquisition and rationally arranges corresponding index, such as using the moon as foundation.Such as with " resident population "
For this index, the history value of the index be [h1, h2 ..., hi ...], wherein hi indicates i-th within a preset time
Resident population's number of the moon.
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 data
Middle subjective factor, exceptional value, trend and seasonal parameter, provide reliable data base for subsequent objective prediction Value of house
Plinth.
S600: from after quantization and standardization index and Value of house index in filter out and meet the change of economics logic
Amount and sample.
Filter out meet economics logic specifically can be based on the mode of big data analysis, from quantization and standardization
It is screened in rear index and Value of house index.Training data of the variable and sample filtered out as next step.It needs
Point out when, this screening process can need to select a certain number of variables and sample according to the actual situation.Work as actual conditions
When needing to compare high request, covering comprehensive room rate prediction prediction result, the good sample conduct of variables more as far as possible can choose
Training data；When actual conditions need the relatively low room rate prediction prediction result for requiring, covering certain content, can choose
A small amount of good sample of variable reduces the data processing amount of subsequent training as training data.
S800: extracting partial data in the variable and sample filtered out is training data, with region Value of house to be predicted
Index is prediction target, building room rate prediction prediction model.
Default machine learning method be previously selected machine make angry learning method can with continuous learning ability
Based on training data, reasonable model is trained.Specifically, default machine learning method may include linear regression,
Lasso, it ridge regression (Ridge Regression), random forest, k nearest neighbor algorithm (k Neighbour Regression), determines
Plan tree, Support vector regression (SVR), grad enhancement return (GradientBoostingRegressor) model and
XGBoost algorithm.Above-mentioned any a machine learning method is selected, is prediction target with Value of house index in region to be predicted,
It is trained using the variable and sample that filter out as training data, building room rate prediction prediction model, before the room rate based on building
It looks forward or upwards prediction model and treats estimation range Value of house and predicted.
Premises Value Prediction Methods, from Value of house historical data extract influence Value of house index and
Value of house index, 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, and is filtered out the variable and sample for meeting economics logic, is extracted in the variable and sample filtered out
Partial data is training data, with Value of house index in region to be predicted be prediction target, building room rate look forward to the prospect prediction model into
The value forecasting of having sexual intercourse room.In whole process, the index and Value of house index of the influence Value of house to acquisition quantify
Processing and standardization, removal exceptional value, trend and seasonal effect factor influence, accurately obtain training data, may be implemented
To Value of house Accurate Prediction.
Index and Value of house index removal exceptional value, trend and the seasonality extracted in one of the embodiments,
Influence factor, which is standardized, includes:
Step 1: filling up rule according to preset missing values, carries out missing values to the index that there is missing in index and fills out
It mends, obtains missing values and fill up the data set finished.
Certain indexs the case where there are shortage of data, rule is filled up according to preset missing values in this case
And data with existing carries out missing values tune benefit, polishing data set.Specifically, preset threshold is less than or equal to for miss rate
Index filled up to missing values are carried out there are the index of missing values according to index property and index deletion condition；For missing
The index that rate is greater than preset threshold is rejected.In practical applications, 30% pre-set level is less than or equal to for miss rate
For, according to index property and index deletion condition, filled up to missing values are carried out there are the index of missing values；And for missing
For pre-set level of the rate greater than 30%, (in the case where investigating remaining available data source can not fill up), to the index
It is rejected.When factor depletion be index periodically lack, such as annual January, 2 month data periodically lack.Due to this
Deletion condition is related to statistics bureau's statistical work period, therefore, is not fixed the influence of factor bring to eliminate the date in the Spring Festival,
The comparativity for enhancing data, need to fill up certain index in January, 2 months.If the index is aggregate-value, with current year
Spend the one third of data in March, 2/3rds make respectively this year January, 2 month shortage of data value fill up；If the index is
Of that month occurrence value, then with 3 month value of year make current year 1,2 month missing values fill up.When factor depletion index missing number compared with
Less, irregularities carry out linear interpolation according to the latter moon data before missing this month and fill up scarce if the index is aggregate-value
It loses；If the index is to actually occur value in this month, filled up with distance missing nearest 6 months of the moon.For the special finger in part
Mark, such as construction area retrodict missing values using the mean annual rate of increase due to the particularity of the index property.
Step 2: filling up the data set finished for missing values, according to preset index frequency conversion rule, carries out to index
Frequency-conversion processing.
Monthly data is converted by the method for linear interpolation by the index in season and the index in year, realizes default refer to
Target frequency-conversion processing, convenient for the derivative index of subsequent calculating.For example, " GDP " this index be season data, " permanent resident population " this
One index is annual data, carries out linear interpolation usually using the annual historical data of continuous two season or two, calculates
Obtain the data of every month.
Step 3: according to the index after frequency-conversion processing, the corresponding derivative index of index is determined.
The general relevant derivative index being related to by subsystem of Value of house is 24 total, can directly obtain from data source
Total 13, remaining 11 each derivative indexs, which mainly the methods of are divided by, are subtracted each other by certain existing several index, to be obtained.Such as:
" permanent resident population/household registration population's ratio " this index is obtained by " permanent resident population " and " household registration population " the two indexs derivative.Specifically
For, above-mentioned steps include: to obtain default room rate prediction predictive factor system；According to default room rate look forward to the prospect predictive factor system,
Obtain derivative achievement data；The achievement data that can be directly acquired is identified from derivative achievement data and need to be by other indexs
The achievement data of operation method determines the corresponding derivative index of each index.Wherein room rate prediction predictive factor system is preparatory structure
It builds, carries a large amount of indexs for influencing Value of house in room rate prediction predictive factor system with Value of house index, influence
The index of 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 refers to
Number specifically can be room rate, may include hanging disk and transaction value.Macro-performance indicator main gene includes that world economy refers to
Mark, Country reading, currency bank, real estate and construction industry and the slave factor in financial market；Meso-economics index main cause
Attached bag includes the slave factor in urban economy, urban life, real estate and construction industry and second-hand house market；Urban planning main gene
The slave factor including regional city to be predicted planning；It includes certainly mainstream media, the Internet portal and opinion that public opinion, which influences main gene,
Altar, from the slave factor of media and search engine temperature；Policies and regulations main gene includes the city of national policy and region to be predicted
The slave factor of city's policy.
Step 4: index conversion, derivative index and corresponding frequency-conversion processing after index is converted are carried out to derivative index
Index afterwards merges, the index after obtaining standardization.
Derivative index generation finishes, that is, forms the wide table of data set before index converts.Make index based on this, then to it
Conversion, index transform mode include: that 3 on a month-on-month basis, a year-on-year, standardization and original value.For example, for room trading volume
Index will use 3 on a month-on-month basis, accumulation Value Datas (for example, sale area), will use a year-on-year, index sheet as than
Rate will use original value.It should be noted that in index conversion process, the index that need to partially convert on year-on-year basis, due to original
The limitation of data initial time, it may appear that after conversion the case where shortage of data, number after such index missing can be converted with index
According to median filled up as missing values.
As shown in Fig. 2, step S800 includes: to extract in the middle part of the variable and sample filtered out in one of the embodiments,
Divided data is training data, is prediction target with Value of house index in region to be predicted, passes through multiple default machine learning respectively
Method training constructs different room rate prediction prediction models；
After step S800 further include:
S900: choosing another part data in the variable and sample filtered out is test data, is looked forward to the prospect to different room rates
Prediction model is tested, and it is optimal for selecting the corresponding room rate prediction prediction model of the smallest machine learning method of mean error
Room rate prediction 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 rooms can be constructed based on these algorithms
Valence prediction prediction model, partial data tests the flat of each room rate prediction prediction model as test data using in sample data
Equal error 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.
More specifically, can be filtered out according to default shortlist create-rule meet economics logic variable and
Sample.Shortlist create-rule combination real estate industry's expertise and existing real estate models discussion generate.According to this
Shortlist create-rule, the index that preset quantity is filtered out from the index of extraction generates shortlist, such as can choose 53
Significance level is high index as model training shortlist in index, is generated according to the best lag period data of each index
Sample data set, for machine learning modeling training.It should be pointed out that sample data concentration includes training data and survey
Data are tried, training data is for machine learning modeling training, and test data is for testing whether established model predicts standard
Really.
Above-mentioned steps S900 includes: in one of the embodiments,
D1, configuration is grouped to all indexs in shortlist, according to grouping situation, is successively concentrated from sample data
Obtain it is each grouping it is corresponding enter modular character training set, test set.
D2, using it is each grouping it is corresponding enter modular character training set, preset machine learning method is trained,
Construct room rate look-forward model.
D3, using it is each grouping it is corresponding enter modular character test set, to the corresponding room rate of each machine learning method look forward to the prospect
The accuracy of model is tested.
D4, the mean error (RMSE) for calculating the corresponding test result of each room rate look-forward model choose mean error
(RMSE) the corresponding room rate prediction prediction model of the smallest algorithm is as optimal room rate look-forward model.
Firstly, being grouped configuration to shortlist, the modular character quantity that enters of each grouping is controlled at one and only one,
Due to different cities, its quality of data is not quite similar, if all equal no datas of index in being grouped, this group of index quantity is zero.
For example, being grouped during packet configuration according to pointer type: middle sight, macroscopic view, derivative etc..Wherein, training pattern group
The quantity of conjunction is that the traversal of 1 index is chosen in all groupings.For example, B group has 2 indexs, then group if A group has 3 indexs
Conjunction number is 3*2=6, and totally 6 kinds, combined index has 2.Based on all number of combinations of model, 9 will be respectively adopted to each combination
Kind of machine learning method is trained, and is respectively as follows: linear regression, Lasso, ridge regression (Ridge Regression), random gloomy
Woods, k nearest neighbor algorithm (k Neighbour Regression), decision tree, Support vector regression (SVR), grad enhancement return
(GradientBoostingRegressor) model and XGBoost algorithm.By the training of the above method, average miss is chosen
The corresponding room rate prediction prediction model of difference (RMSE) the smallest algorithm is as optimal room rate look-forward model.
It should be understood that although each step in the flow chart of Fig. 1-2 is successively shown according to the instruction of arrow,
It is these steps is not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
There is no stringent sequences to limit for rapid execution, these steps can execute in other order.Moreover, at least one in Fig. 1-2
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in same a period of time to multiple sub-steps
Quarter executes completion, but can execute at different times, the execution in these sub-steps or stage be sequentially also not necessarily according to
Secondary progress, but in turn or can be handed over at least part of the sub-step or stage of other steps or other steps
Alternately execute
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 history number
According to the middle index and Value of house index for extracting influence Value of house；
Data processing module 400, for the index and Value of house index progress quantification treatment to extraction, and to extraction
Index and Value of house index be standardized；
Screening module 600, for from after quantization and standardization index and Value of house index in filter out and meet economy
Learn the variable and sample of logic；
Model construction module 800 is training data for extracting in the variable and sample filtered out partial data, with to
Estimation range Value of house index is prediction target, building room rate prediction prediction model.
Premises value forecasting device, data acquisition module 200 is extracted from Value of house historical data influences house
The index and Value of house index of value, 400 pairs of the data processing module indexs extracted and Value of house index quantify
Processing, and index to extraction and Value of house index are standardized, screening module 600, which filters out, meets economics
The variable and sample of logic, it is training data that model construction module 800, which extracts partial data in the variable and sample filtered out,
It is prediction target with Value of house index in region to be predicted, building room rate prediction prediction model carries out Value of house prediction.Entirely
In the process, the index of the influence Value of house to acquisition and Value of house index carry out quantification treatment and standardization, remove different
Constant value, trend and seasonal effect factor influence, and accurately obtain training data, may be implemented to Value of house Accurate Prediction.
Data processing module 400 is also used to fill up rule according to preset missing values in one of the embodiments, right
The index that there is missing in index carries out missing values and fills up, and obtains missing values and fills up the data set finished；It is filled up for missing values
The data set finished carries out frequency-conversion processing to index according to preset index frequency conversion rule；According to the index after frequency-conversion processing,
Determine the corresponding derivative index of index；Index conversion is carried out to derivative index, derivative index after index is converted and corresponding
Index after frequency-conversion processing merges, the index after obtaining standardization.
Preset missing values fill up rule in one of the embodiments, are as follows: are less than or equal to default threshold for miss rate
The index of value is filled up according to index property and index deletion condition to missing values are carried out there are the index of missing values；For lacking
The index that mistake rate is greater than preset threshold is rejected
Data processing module 400, which is also used to obtain, in one of the embodiments, index and refers in the season in index in year
Mark；Monthly data is converted by the method for linear interpolation by season index and annual index.
Data processing module 400 is also used to obtain default room rate prediction predictive factor body in one of the embodiments,
System；According to default room rate prediction predictive factor system, derivative achievement data is obtained；Identification can be straight from derivative achievement data
It obtains the achievement data taken and the corresponding derivative index of each index need to be determined by the achievement data of other index operation methods.
Model construction module 800 is also used to extract part in the variable and sample filtered out in one of the embodiments,
Data are training data, are prediction target with Value of house index in region to be predicted, pass through multiple default machine learning sides respectively
Method training constructs different room rate prediction prediction models.As shown in figure 4, premises value forecasting device further includes optimization mould
Block 900 is test data for choosing another part data in the variable and sample filtered out, looks forward to the prospect to different room rates pre-
It surveys model to be tested, selecting the corresponding room rate prediction prediction model of the smallest machine learning method of mean error is optimal room
Valence prediction prediction model.
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
A combination thereof is realized.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also
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 Hangzhou is carried out with the room rate prediction prediction model of the application building pre-
It surveys, shown in obtained experimental result Fig. 5.It can be accurately to Hangzhou based on the visible the application room rate prediction prediction model of Fig. 5
A certain region room rate is predicted.
In one embodiment, a kind of computer equipment is provided, which can be server, inside
Structure chart can be as shown in Figure 6.The computer equipment includes processor, the memory, network interface connected by system bus
And database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The storage of the computer equipment
Device includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program
And database.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.
The database of the computer equipment is for storing each region Value of house historical data and data.The net of the computer equipment
Network interface is used to communicate with external terminal by network connection.To realize one kind when the computer program is executed by processor
Value of house prediction technique.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme
The block diagram of structure, does not constitute the restriction for the computer equipment being applied thereon to application scheme, and specific computer is set
Standby may include perhaps combining certain components or with different component cloth than more or fewer components as shown in the figure
It sets.
In one embodiment, it provides a kind of computer equipment, including memory, processor and is stored in memory
Computer program that is upper and can running 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 and Value of house index to extraction carry out quantification treatment, and index and Value of house index to extraction
It is standardized；
From after quantization and standardization index and Value of house index in filter out and meet the variable and sample of economics logic
This；
Extracting partial data in the variable and sample filtered out is training data, with Value of house index in region to be predicted
To predict target, building room rate prediction prediction model.
In one embodiment, it is also performed the steps of when processor executes computer program
Rule is filled up according to preset missing values, missing values are carried out to the index that there is missing in index and are filled up, are lacked
Mistake value fills up the data set finished；The data set finished is filled up for missing values, according to preset index frequency conversion rule, to finger
Mark carries out frequency-conversion processing；According to the index after frequency-conversion processing, the corresponding derivative index of index is determined；Derivative index is referred to
Mark conversion, the index after derivative index and corresponding frequency-conversion processing after index is converted merge, and obtain standardization
Index afterwards.
In one embodiment, the season obtained in index is also performed the steps of when processor executes computer program
Index and annual index；Monthly data is converted by the method for linear interpolation by season index and annual index.
In one embodiment, acquisition default room rate prediction is also performed the steps of when processor executes computer program
Predictive factor system；According to default room rate prediction predictive factor system, derivative achievement data is obtained；From derivative achievement data
It identifies the achievement data that can be directly acquired and need to determine that each index is corresponding by the achievement data of other index operation methods
Derivative index.
In one embodiment, it is also performed the steps of when processor executes computer program
Extracting partial data in the variable and sample filtered out is training data, with Value of house index in region to be predicted
To predict target, respectively by multiple default machine learning method training, different room rate prediction prediction models is constructed；It chooses
Another part data are test data in the variable and sample filtered out, are tested different room rate prediction prediction models,
Select the corresponding room rate prediction prediction model of the smallest machine learning method of mean error for optimal room rate prediction prediction model.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is counted
Calculation 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 and Value of house index to extraction carry out quantification treatment, and index and Value of house index to extraction
It is standardized；
From after quantization and standardization index and Value of house index in filter out and meet the variable and sample of economics logic
This；
Extracting partial data in the variable and sample filtered out is training data, with Value of house index in region to be predicted
To predict target, building room rate prediction prediction model.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Rule is filled up according to preset missing values, missing values are carried out to the index that there is missing in index and are filled up, are lacked
Mistake value fills up the data set finished；The data set finished is filled up for missing values, according to preset index frequency conversion rule, to finger
Mark carries out frequency-conversion processing；According to the index after frequency-conversion processing, the corresponding derivative index of index is determined；Derivative index is referred to
Mark conversion, the index after derivative index and corresponding frequency-conversion processing after index is converted merge, and obtain standardization
Index afterwards.
In one embodiment, the season obtained in index is also performed the steps of when computer program is executed by processor
Spend index and annual index；Monthly data is converted by the method for linear interpolation by season index and annual index.
In one embodiment, before acquisition default room rate is also performed the steps of when computer program is executed by processor
Look forward or upwards predictive factor system；According to default room rate prediction predictive factor system, derivative achievement data is obtained；From derivative achievement data
The achievement data and each index pair need to be determined by the achievement data of other index operation methods that middle identification can directly acquire
The derivative index answered.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Extracting partial data in the variable and sample filtered out is training data, with Value of house index in region to be predicted
To predict target, respectively by multiple default machine learning method training, different room rate prediction prediction models is constructed；It chooses
Another part data are test data in the variable and sample filtered out, are tested different room rate prediction prediction models,
Select the corresponding room rate prediction prediction model of the smallest machine learning method of mean error for optimal room rate prediction prediction model.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can
Completed with instructing relevant hardware by computer program, computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
It may include non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), may be programmed
ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory can
Including random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is in a variety of forms
It can obtain, such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram
(DDRSDRAM), enhanced 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,
Without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection model of the application
It encloses.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；
From after quantization and standardization index and Value of house index in filter out and meet the variable and sample of economics logic；
Extracting partial data in the variable and sample filtered out is training data, is prediction with Value of house index in region to be predicted
Target, building room rate prediction prediction model.
2. the method according to claim 1, wherein the index and Value of house index of the extraction remove exception
Value, trend and seasonal effect factor are standardized and include:
Rule is filled up according to preset missing values, missing values are carried out to the index that there is missing in the index and are filled up, are lacked
Mistake value fills up the data set finished；
The data set finished is filled up for missing values, and according to preset index frequency conversion rule, frequency-conversion processing is carried out to index；
According to the index after frequency-conversion processing, the corresponding derivative index of index is determined；
To the derivative index progress index conversion, after the derivative index and corresponding frequency-conversion processing after index is converted
Index merges, the index after obtaining standardization.
3. according to the method described in claim 2, it is characterized in that, the preset missing values fill up rule are as follows: for missing
Rate is less than or equal to the index of preset threshold, according to index property and index deletion condition, to there are the progress of the index of missing values
Missing values are filled up；The index for being greater than the preset threshold for miss rate is rejected.
4. according to the method described in claim 2, it is characterized in that, described include: to index progress frequency-conversion processing
Obtain the season index and annual index in index；
Monthly data is converted by the method for linear interpolation by the season index and the annual index.
5. according to the method described in claim 2, it is characterized in that, the index according to after frequency-conversion processing, determines index pair
The derivative index answered includes:
Obtain default room rate prediction predictive factor system；
According to the default room rate prediction predictive factor system, derivative achievement data is obtained；
The achievement data that can directly acquire is identified from the derivative achievement data and need to be by other index operation methods
Achievement data determines the corresponding derivative index of each index.
6. the method according to claim 1, wherein described extract partial data in the variable and sample filtered out
It is prediction target with Value of house index in region to be predicted for training data, building room rate prediction prediction model includes:
Extracting partial data in the variable and sample filtered out is training data, is prediction with Value of house index in region to be predicted
Target constructs different room rate prediction prediction models respectively by multiple default machine learning method training；
Partial data is training data in the variable and sample that the extraction filters out, and is with Value of house index in region to be predicted
It predicts target, is also wrapped after constructing different room rate prediction prediction models by multiple default machine learning method training respectively
It includes:
Choosing another part data in the variable and sample filtered out is test data, to the different room rate prediction prediction mould
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.
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；
Data 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；
Screening module, for from after quantization and standardization index and Value of house index in filter out and meet economics logic
Variable and sample；
Model construction module is training data for extracting partial data in the variable and sample filtered out, with region to be predicted
Value of house index is prediction target, building room rate prediction prediction model.
8. device according to claim 7, which is characterized in that the data processing module is also used to according to preset missing
Value fills up rule, carries out missing values to the index that there is missing in the index and fills up, obtains missing values and fill up the data finished
Collection；The data set finished is filled up for missing values, and according to preset index frequency conversion rule, frequency-conversion processing is carried out to index；According to
Index after frequency-conversion processing determines the corresponding derivative index of index；Index conversion is carried out to the derivative index, index is converted
The index after the derivative index and corresponding frequency-conversion processing afterwards merges, the index after obtaining standardization.
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 |
|---|---|---|---|
| CN201811289837.7A CN109376936A (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 |
|---|---|---|---|
| CN201811289837.7A CN109376936A (en) | 2018-10-31 | 2018-10-31 | Value of house prediction technique, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109376936A true CN109376936A (en) | 2019-02-22 |
Family
ID=65391388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811289837.7A Pending CN109376936A (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) | CN109376936A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109935338A (en) * | 2019-03-07 | 2019-06-25 | 平安科技（深圳）有限公司 | Data prediction processing method, device and computer equipment based on machine learning |
| CN110110901A (en) * | 2019-04-15 | 2019-08-09 | 平安科技（深圳）有限公司 | Data predication method, device, computer equipment and storage medium |
| CN112183861A (en) * | 2020-09-28 | 2021-01-05 | 辽宁省肿瘤医院 | Method for predicting treatment cost based on lasso regression |
| CN113177806A (en) * | 2021-05-18 | 2021-07-27 | 中移(上海)信息通信科技有限公司 | Information processing method, device and equipment |
| CN113962744A (en) * | 2021-10-29 | 2022-01-21 | 重庆汇集源科技有限公司 | Real estate rent dynamic monitoring system |
| CN113988639A (en) * | 2021-10-29 | 2022-01-28 | 重庆汇集源科技有限公司 | Asset value dynamic management system |
| CN114119062A (en) * | 2021-10-11 | 2022-03-01 | 深圳市房帮帮互联网科技有限公司 | Multi-variable-based real estate automatic valuation method |
| CN116308441A (en) * | 2023-03-07 | 2023-06-23 | 太原科技大学 | House price prediction method with variable selection capability |
| WO2024021630A1 (en) * | 2022-07-27 | 2024-02-01 | 京东城市(北京)数字科技有限公司 | Method and apparatus for calculating indicator data |
-
2018
- 2018-10-31 CN CN201811289837.7A patent/CN109376936A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109935338A (en) * | 2019-03-07 | 2019-06-25 | 平安科技（深圳）有限公司 | Data prediction processing method, device and computer equipment based on machine learning |
| CN110110901A (en) * | 2019-04-15 | 2019-08-09 | 平安科技（深圳）有限公司 | Data predication method, device, computer equipment and storage medium |
| CN112183861A (en) * | 2020-09-28 | 2021-01-05 | 辽宁省肿瘤医院 | Method for predicting treatment cost based on lasso regression |
| CN112183861B (en) * | 2020-09-28 | 2024-01-26 | 辽宁省肿瘤医院 | Method for predicting treatment cost based on lasso regression |
| CN113177806A (en) * | 2021-05-18 | 2021-07-27 | 中移(上海)信息通信科技有限公司 | Information processing method, device and equipment |
| CN114119062A (en) * | 2021-10-11 | 2022-03-01 | 深圳市房帮帮互联网科技有限公司 | Multi-variable-based real estate automatic valuation method |
| CN113962744A (en) * | 2021-10-29 | 2022-01-21 | 重庆汇集源科技有限公司 | Real estate rent dynamic monitoring system |
| CN113988639A (en) * | 2021-10-29 | 2022-01-28 | 重庆汇集源科技有限公司 | Asset value dynamic management system |
| WO2024021630A1 (en) * | 2022-07-27 | 2024-02-01 | 京东城市(北京)数字科技有限公司 | Method and apparatus for calculating indicator data |
| CN116308441A (en) * | 2023-03-07 | 2023-06-23 | 太原科技大学 | House price prediction method with variable selection capability |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109376936A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN109523068A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN109272364A (en) | Automatic Valuation Modelling modeling method | |
| CN109345035A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN105678414A (en) | Data processing method of predicting resource consumption | |
| CN112712203A (en) | Method and system for predicting daily maximum load of power distribution network | |
| CN109635996A (en) | Room rate tendency look-forward model construction method, device and storage medium | |
| CN114398669A (en) | Joint credit scoring method and device based on privacy protection calculation and cross-organization | |
| CN114529154A (en) | Method for constructing population scale prediction index system, prediction method, device and system | |
| CN109325811A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN109242578A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN109583940A (en) | Cell source of houses value parameter estimation method and device | |
| 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 | |
| CN110580542A (en) | Power consumption prediction method and device | |
| CN110084400A (en) | Information forecasting method, device, computer equipment and storage medium | |
| CN109492806A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN109214603A (en) | Value of house prediction technique, device, computer equipment and storage medium | |
| CN112434019A (en) | Historical electric quantity tracing and cleaning method applied to household variable relation change and electric power center | |
| CN113298575A (en) | Method, system, equipment and storage medium for trademark value batch evaluation | |
| Malgarini et al. | Re-engineering the ISAE manufacturing survey | |
| CN114154768A (en) | Natural gas demand prediction method, device, electronic equipment and medium | |
| CN110969297A (en) | Power load prediction method and device based on backward interval partial least square method | |
| CN111797924A (en) | Three-dimensional garden portrait method and system based on clustering algorithm | |
| Sinitsyna et al. | Some practical aspects of electric power consumption time series analysis |
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 |