CN109816409A - A kind of used car pricing method, device, equipment and computer-readable medium - Google Patents
A kind of used car pricing method, device, equipment and computer-readable medium Download PDFInfo
- Publication number
- CN109816409A CN109816409A CN201711159685.4A CN201711159685A CN109816409A CN 109816409 A CN109816409 A CN 109816409A CN 201711159685 A CN201711159685 A CN 201711159685A CN 109816409 A CN109816409 A CN 109816409A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- price
- model
- pricing
- car
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of used car pricing method, device, equipment and computer-readable mediums, this method comprises: the step that gets parms, obtains the vehicle parameter of used car to be fixed a price;Data processing step is obtained based on the vehicle parameter and refers to vehicle parameter;Pricing model generation step constructs n vehicle pricing model based on the vehicle parameter and the reference vehicle parameter, and is weighted to obtain vehicle weighting pricing model to n vehicle pricing model using BOOST;Pricing steps obtain the price of used car based on the vehicle parameter using vehicle weighting pricing model.The invention proposes the modes that data set expands, so that the price of used car is more objective and accurate, propose the syncretizing mechanism of the BOOST of single model, so that the price result of fused weighting pricing model is more accurate, propose the calculation of profit margin, the retail price and auction price that used car can be estimated simultaneously, improve Pricing Efficiency and accuracy.
Description
Technical field
The present invention relates to technical field of data processing, especially a kind of used car pricing method, device, equipment and computer
Readable medium.
Background technique
Currently, being sent out according to China Automobile Dealers Association with the improvement of people's living standards, car replacement speed is getting faster
Cloth data, annual Chinese Second-hand Vehicle Transaction amount reaches 1039.07 ten thousand within 2016, breaches ten million for the first time, China it is second-hand
Car market just one eruptive growth stage of experience.And in used automobile market, used car belongs to nonstandard product, and that does not unify determines
Valence mode, currently there are pricing service it is irregular, price coverage rate is not high, price is inaccurate, cannot for consumer,
Car trader buys and sells used car and provides accurately price service, therefore in this nonstandard product transaction of used car, there are certain prices
Risk is unfavorable for fair, just, the transparent transaction of both parties.Therefore, how accurately to assess the price of used car is one
Technical problem.
Existing data set is only used only in the prior art to be trained, when existing data set is smaller, used car
Pricing bais is larger, is in the prior art only to carry out simply integrating to existing pricing model, price result is still inadequate
Ideal, and it is single to the pricing function of used car in the prior art, auction price and retail price can not be provided simultaneously, can not also be calculated
Profit margin.
Summary of the invention
The present invention is directed to above-mentioned defect in the prior art, proposes following technical solution.
A kind of used car pricing method, this method comprises:
Get parms step, obtains the vehicle parameter of used car to be fixed a price;
Data processing step is obtained based on the vehicle parameter and refers to vehicle parameter;
Pricing model generation step constructs n vehicle price mould based on the vehicle parameter and the reference vehicle parameter
Type, and vehicle weighting pricing model is weighted to obtain to n vehicle pricing model using BOOST;
Pricing steps obtain the price of used car based on the vehicle parameter using vehicle weighting pricing model;
Wherein, n is integer.
Further, the vehicle parameter includes brand, vehicle system, vehicle, time of registering the license, region and/or mileage travelled.
Further, the data processing step includes:
Judgment step, judges whether amount of training data relevant to the vehicle parameter is greater than or equal to certain threshold value, obtains
To judging result;
Data extending step, if the judging result be it is yes, using the training data as refer to vehicle parameter, if
The judging result be it is no, training data is expanded according to time, region, vehicle or vehicle group, vehicle condition network of personal connections, will be expanded
Training data afterwards, which is used as, refers to vehicle parameter.
Further, the vehicle pricing model includes: unitary robust linear model, binary robust linear model and one
First Robust Exponential model.
Further, the unitary robust linear model are as follows: price1=a0+a1*carage;
The binary robust linear model are as follows: price2=b0+b1*carage+b2*carmil;
The unitary Robust Exponential model are as follows: lnprice3=c0+carage;
Wherein, price1, price2, price3 are the vehicle price under different models, a0、b0And c0For constant, a1、b1、
b2And c1It for weighting coefficient, is calculated by allowance for depreciation, carageIndicate vehicle age, carmilIndicate VMT Vehicle-Miles of Travel.
Further, the vehicle weights pricing model are as follows:
Wherein, price is the price of used car, MAPEiFor the goodness of fit of i-th of model,For the quasi- of i-th model
Conjunction value, i=1,2,3, wherein j is number of data in current reference vehicle parameter, and y is true price price,Currently to cut
The price expectation value that "current" model is predicted under piece.
Further, this method further include:
Pricing adjustments step, when determining that the second-hand training set can not be expanded, using new car price multiplied by depreciation
Rate is fixed a price;
Profit margin calculates step, establishes the Profit Rate Model between retail price, auction price, and the price based on used car calculates
The profit margin.
The invention also provides a kind of used car pricing device, which includes:
Get parms unit, obtains the vehicle parameter of used car to be fixed a price;
Data processing unit is obtained based on the vehicle parameter and refers to vehicle parameter;
Pricing model generation unit constructs n vehicle price mould based on the vehicle parameter and the reference vehicle parameter
Type, and vehicle weighting pricing model is weighted to obtain to n vehicle pricing model using BOOST;
Price unit obtains the price of used car based on the vehicle parameter using vehicle weighting pricing model;
Wherein, n is integer.
Further, the vehicle parameter includes brand, vehicle system, vehicle, time of registering the license, region and/or mileage travelled.
Further, the data processing unit includes:
Judgment module, judges whether amount of training data relevant to the vehicle parameter is greater than or equal to certain threshold value, obtains
To judging result;
Data extending module, if the judging result be it is yes, using the training data as refer to vehicle parameter, if
The judging result be it is no, training data is expanded according to time, region, vehicle or vehicle group, vehicle condition network of personal connections, will be expanded
Training data afterwards, which is used as, refers to vehicle parameter.
Further, the vehicle pricing model includes: unitary robust linear model, binary robust linear model and one
First Robust Exponential model.
Further, the unitary robust linear model are as follows: price1=a0+a1*carage;
The binary robust linear model are as follows: price2=b0+b1*carage+b2*carmil;
The unitary Robust Exponential model are as follows: lnprice3=c0+carage;
Wherein, price1, price2, price3 are the vehicle price under different models, a0、b0And c0For constant, a1、b1、
b2And c1It for weighting coefficient, is calculated by allowance for depreciation, carageIndicate vehicle age, carmilIndicate VMT Vehicle-Miles of Travel.
Further, the vehicle weights pricing model are as follows:
Wherein, price is the price of used car, MAPEiFor the goodness of fit of i-th of model,For the quasi- of i-th model
Conjunction value, i=1,2,3, wherein j is number of data in current reference vehicle parameter, and y is true price price,Currently to cut
The price expectation value that "current" model is predicted under piece.
Further, the device further include:
Pricing adjustments unit, when determining that the second-hand training set can not be expanded, using new car price multiplied by depreciation
Rate is fixed a price;
Profit margin computing unit establishes the Profit Rate Model between retail price, auction price, and the price based on used car calculates
The profit margin.
The invention also provides a kind of used car pricing device equipment, the equipment includes processor, memory, the place
Reason device is connected with the memory by bus, and machine readable code is stored in the memory, and the processor execution is deposited
One of above-mentioned method can be performed in machine readable code in reservoir.
The invention also provides a kind of computer readable storage medium, computer program generation is stored on the storage medium
Code, one of above-mentioned method can be performed when the computer program code is computer-executed.
Technical effect of the invention are as follows: the invention proposes the modes that data set expands, so that the price of used car is more
It is objective and accurate, the syncretizing mechanism of the BOOST of single model is proposed, so that the price result of fused weighting pricing model is more
Accurately, the calculation of profit margin is proposed, the retail price and auction price of used car can be estimated simultaneously, improves price effect
Rate and accuracy.
Detailed description of the invention
Fig. 1 is the flow chart of used car pricing method one embodiment of the present invention.
Fig. 2 is the flow chart of the data processing step of one embodiment of the invention.
Fig. 3 is a kind of flow chart of used car pricing method of another embodiment of the present invention.
Fig. 4 is the structural schematic diagram of used car pricing device one embodiment of the present invention.
Fig. 5 is the structural schematic diagram of the processing unit of one embodiment of the invention.
Fig. 6 is a kind of structural schematic diagram of used car pricing device of another embodiment of the present invention.
Fig. 7 is a kind of structural schematic diagram of used car pricing equipment one embodiment of the invention.
Specific embodiment
1-7 is specifically described with reference to the accompanying drawing.
Fig. 1 shows the flow chart of used car pricing method one embodiment of the present invention, this method comprises:
The step that gets parms S11, obtains the vehicle parameter of used car to be fixed a price;
Data processing step S12 is obtained based on the vehicle parameter and is referred to vehicle parameter;
Pricing model generation step S13 constructs n vehicle price based on the vehicle parameter and the reference vehicle parameter
Model, and vehicle weighting pricing model is weighted to obtain to n vehicle pricing model using BOOST;
Pricing steps S14 obtains the price of used car based on the vehicle parameter using vehicle weighting pricing model;
N model can be weighted by the present invention, and n is integer, and certain n can also be equal to 1, at this point, effect is equivalent to
It is fixed a price using single model, n is greater than or equal to 2 under normal circumstances.One specific embodiment is n=3, at this point, vehicle
Pricing model may include: unitary robust linear model, binary robust linear model and unitary Robust Exponential model.Certain n
4, etc. can be equal to.
In general, the vehicle parameter obtained in the step that gets parms S11 include brand, vehicle system, vehicle, the time of registering the license,
Region and/or mileage travelled.In general, brand, vehicle system, time of registering the license are important vehicle parameters.
The expansion of data be since it is considered that vehicle, vehicle age be car fare major influence factors, and vehicle system, region, mileage,
Influence of the data apart from factors such as the now times is weaker compared with the first two factor, more if directly establishing multivariate model
Characteristic dimension need sufficient data to be trained, but since the long-tail of vehicle is distributed obvious, preceding 20% vehicle
Type just occupies preceding 80% data, and therefore, when directly using multivariate model, most of vehicle can encounter the insufficient feelings of data volume
Condition.Therefore, when modeling, the master data dimension selected is same city with vehicle and nearly 5 months data, and controls other changes
It measures identical, maintains the preferable consistency of data in this way, be equivalent to the influence for considering its dependent variable to price.But it is certain
Vehicle obtains in this stringent dimension less than enough data, therefore, it is necessary to successively be expanded to data, to the greatest extent
Model is established while data consistency can be able to maintain.Therefore, the expansion of data is an important inventive point of the invention.
When data deficiencies is to carry out used car price, using the logic gradually expanded, successively from region dimension, data
Timeliness dimension and close vehicle dimension are gradually expanded, until the data volume of acquisition can provide suitable appraisal.
As shown in Fig. 2, the data processing step S12 includes:
Judgment step S121, judges whether amount of training data relevant to the vehicle parameter is greater than or equal to certain threshold
Value, obtains judging result;
Data extending step S122, if the judging result be it is yes, using the training data as refer to vehicle parameter,
If the judging result be it is no, training data is expanded according to time, region, vehicle or vehicle group, vehicle condition network of personal connections, will
Training data after expansion, which is used as, refers to vehicle parameter.
As n=3, the unitary robust linear model are as follows: price1=a0+a1*carage;
The binary robust linear model are as follows: price2=b0+b1*carage+b2*carmil;
The unitary Robust Exponential model are as follows: lnprice3=c0+carage;
Wherein, price1, price2, price3 are the vehicle price under different models, a0、b0And c0For constant, a1、b1、
b2And c1It for weighting coefficient, is calculated by allowance for depreciation, carageIndicate vehicle age, carmilIndicate VMT Vehicle-Miles of Travel.
It is being weighted coefficient a1、b1、b2And c1When calculating, for empirically, it is believed that annual rate of discount is arrived 8%
Between 16%, 8% is set by rate of discount if it is less than 8%, similarly, when being greater than 16%, sets 16% for rate of discount, root
A is calculated according to the available data as training set0、b0And c0, and model is trained, so that above-mentioned single model aligns
Really.
In order to use above-mentioned single model, the method that the present invention has investigated BOOST weighting obtains vehicle by this method
Pricing model is weighted, this is another important inventive point of the invention.The vehicle weights pricing model are as follows:
Wherein, price is the price of used car, MAPEiFor the goodness of fit of i-th of model,For the quasi- of i-th model
Conjunction value, wherein i=1,2,3, wherein j is number of data in current reference vehicle parameter, and y is true price price,For
The price expectation value that "current" model is predicted under current slice.
Fig. 3 shows another embodiment of used car pricing method, this method further include:
The step that gets parms S31, obtains the vehicle parameter of used car to be fixed a price;
Data processing step S32 is obtained based on the vehicle parameter and is referred to vehicle parameter;
Pricing model generation step S33 constructs n vehicle price based on the vehicle parameter and the reference vehicle parameter
Model, and vehicle weighting pricing model is weighted to obtain to n vehicle pricing model using BOOST;
Pricing steps S34 obtains the price of used car based on the vehicle parameter using vehicle weighting pricing model;
Pricing adjustments step S35, when determining that the second-hand training set can not be expanded, using new car price multiplied by folding
Old rate is fixed a price;
Profit margin calculates step S36, establishes the Profit Rate Model between retail price, auction price, the price based on used car
Calculate the profit margin.
Above-mentioned steps S31-S34 is identical as the step S11-S14 of method shown in Fig. 1, and relevant operation is not repeating.
In pricing adjustments step S35, the vehicle age ratio of vehicle, vehicle group data deficiencies or vehicle to be estimated where vehicle to be estimated
Most trolley age is much smaller in data set at present, and when cannot obtain appraisal by the above method, the present invention can be according to vehicle where it
The naked car fare of new car, evaluate at present according to the new car that annual certain rate of discount obtains the vehicle, for example annual allowance for depreciation is
7%.
It calculates in step S36, the profit margin between retail price, auction price is modeled, for example establish line in profit margin
Property model finds the relationship of profit margin and vehicle age, mileage etc. in same vehicle or vehicle system, when treat estimate vehicle and evaluated after, can
To obtain the profit margin of the vehicle according to model, auction can be released from retail price (or auction price) according to profit margin is counter in this way
Valence (or retail price).Improve appraisal efficiency.
Fig. 4 shows the structural schematic diagram of used car pricing device one embodiment, which includes:
Get parms unit 41, obtains the vehicle parameter of used car to be fixed a price;
Data processing unit 42 is obtained based on the vehicle parameter and refers to vehicle parameter;
Pricing model generation unit 43 constructs n vehicle price based on the vehicle parameter and the reference vehicle parameter
Model, and vehicle weighting pricing model is weighted to obtain to n vehicle pricing model using BOOST;
Price unit 44 obtains the price of used car based on the vehicle parameter using vehicle weighting pricing model.
N model can be weighted by the present invention, and n is integer, and certain n can also be equal to 1, at this point, effect is equivalent to
It is fixed a price using single model, n is greater than or equal to 2 under normal circumstances.One specific embodiment is n=3, at this point, vehicle
Pricing model may include: unitary robust linear model, binary robust linear model and unitary Robust Exponential model.Certain n
4, etc. can be equal to.
As n=3, the unitary robust linear model are as follows: price1=a0+a1*carage;
The binary robust linear model are as follows: price2=b0+b1*carage+b2*carmil;
The unitary Robust Exponential model are as follows: lnprice3=c0+carage;
Wherein, price1, price2, price3 are the vehicle price under different models, a0、b0And c0For constant, a1、b1、
b2And c1It for weighting coefficient, is calculated by allowance for depreciation, carageIndicate vehicle age, carmilIndicate VMT Vehicle-Miles of Travel.
It is being weighted coefficient a1、b1、b2And c1When calculating, for empirically, it is believed that annual rate of discount is arrived 8%
Between 16%, 8% is set by rate of discount if it is less than 8%, similarly, when being greater than 16%, sets 16% for rate of discount, root
A is calculated according to the available data as training set0、b0And c0, and model is trained, so that above-mentioned single model aligns
Really.
In order to use above-mentioned single model, the method that the present invention has investigated BOOST weighting obtains vehicle by this method
Pricing model is weighted, this is another important inventive point of the invention.The vehicle weights pricing model are as follows:
Wherein, price is the price of used car, MAPEiFor the goodness of fit of i-th of model,For the quasi- of i-th model
Conjunction value, wherein i=1,2,3, wherein j is number of data in current reference vehicle parameter, and y is true price price,For
The price expectation value that "current" model is predicted under current slice.
In general, the vehicle parameter obtained in unit 41 that gets parms include brand, vehicle system, vehicle, the time of registering the license,
Domain and/or mileage travelled.In general, brand, vehicle system, time of registering the license are important vehicle parameters.
The data processing unit 42 is the unit for executing the step S12 of method shown in Fig. 1, as shown in figure 5, comprising:
Judgment module 421, judges whether amount of training data relevant to the vehicle parameter is greater than or equal to certain threshold value,
Obtain judging result;
Data extending module 422, if the judging result be it is yes, using the training data as refer to vehicle parameter,
If the judging result be it is no, training data is expanded according to time, region, vehicle or vehicle group, vehicle condition network of personal connections, will
Training data after expansion, which is used as, refers to vehicle parameter.
Fig. 6 shows the used car pricing device of another embodiment of the present invention comprising:
Get parms unit 61, obtains the vehicle parameter of used car to be fixed a price;
Data processing unit 62 is obtained based on the vehicle parameter and refers to vehicle parameter;
Pricing model generation unit 63 constructs n vehicle price based on the vehicle parameter and the reference vehicle parameter
Model, and vehicle weighting pricing model is weighted to obtain to n vehicle pricing model using BOOST;
Price unit 64 obtains the price of used car based on the vehicle parameter using vehicle weighting pricing model;
Pricing adjustments unit 65, when determining that the second-hand training set can not be expanded, using new car price multiplied by folding
Old rate is fixed a price;
Profit margin computing unit 66 establishes the Profit Rate Model between retail price, auction price, based on the price of used car
Calculate the profit margin.
Said units 61-64 is identical as the unit 41-44 of Fig. 4 shown device, and relevant operation is not repeating.
In pricing adjustments unit 65, the vehicle age ratio of vehicle, vehicle group data deficiencies or vehicle to be estimated where vehicle to be estimated
Most trolley age is much smaller in data set at present, and when cannot obtain appraisal by the above method, the present invention can be according to vehicle where it
The naked car fare of new car, evaluate at present according to the new car that annual certain rate of discount obtains the vehicle, for example annual allowance for depreciation is
7%.
In profit margin computing unit 66, the profit margin between retail price, auction price is modeled, for example is established linear
Model finds the relationship of profit margin and vehicle age, mileage etc. in same vehicle or vehicle system, when treat estimate vehicle and evaluated after, can be with
The profit margin of the vehicle is obtained according to model, can release auction price from retail price (or auction price) according to profit margin is counter in this way
(or retail price).Improve appraisal efficiency.
Fig. 7 shows a kind of structural schematic diagram of used car pricing equipment one embodiment, and the equipment includes processor
71, memory 72, the processor 71 are connected with the memory 72 by bus, and storing machine in the memory 72 can
Code is read, the processor executes the method that the machine readable code in memory executes one of above-mentioned Fig. 1-3, changes equipment and may be used also
To include display 73, for used car price to be presented to user.
The invention also provides a kind of computer readable storage medium, computer program generation is stored on the storage medium
Code, the method for one of above-mentioned Fig. 1-3 is executed when the computer program code is computer-executed.
Method of the present invention can be realized by computer program, and computer program can also be stored in storage
On medium, processor reads computer program from storage medium, and executes corresponding method.
It should be noted last that: above embodiments only illustrate and not to limitation technical solution of the present invention, although reference
Above-described embodiment describes the invention in detail, those skilled in the art should understand that: it still can be to this hair
It is bright to be modified or replaced equivalently, it without departing from the spirit or scope of the invention, or any substitutions, should all
It is included within the scope of the claims of the present invention.
Claims (16)
1. a kind of used car pricing method, which is characterized in that this method comprises:
Get parms step, obtains the vehicle parameter of used car to be fixed a price;
Data processing step is obtained based on the vehicle parameter and refers to vehicle parameter;
Pricing model generation step constructs n vehicle pricing model based on the vehicle parameter and the reference vehicle parameter, and
Vehicle weighting pricing model is weighted to obtain to n vehicle pricing model using BOOST;
Pricing steps obtain the price of used car based on the vehicle parameter using vehicle weighting pricing model;
Wherein, n is integer.
2. the method according to claim 1, which is characterized in that the vehicle parameter include brand, vehicle system, vehicle, the time of registering the license,
Region and/or mileage travelled.
3. method according to claim 2, which is characterized in that the data processing step includes:
Judgment step, judges whether amount of training data relevant to the vehicle parameter is greater than or equal to certain threshold value, is sentenced
Disconnected result;
Data extending step, if the judging result be it is yes, using the training data as refer to vehicle parameter, if described
Judging result be it is no, training data is expanded according to time, region, vehicle or vehicle group, vehicle condition network of personal connections, after expansion
Training data, which is used as, refers to vehicle parameter.
4. according to the method in claim 3, which is characterized in that the vehicle pricing model includes: unitary robust linear model, two
First robust linear model and unitary Robust Exponential model.
5. method according to claim 4, which is characterized in that the unitary robust linear model are as follows: price1=a0+a1*
carage;
The binary robust linear model are as follows: price2=b0+b1*carage+b2*carmil;
The unitary Robust Exponential model are as follows: lnprice3=c0+carage;
Wherein, price1, price2, price3 are the vehicle price under different models, a0、b0And c0For constant, a1、b1、b2And c1
It for weighting coefficient, is calculated by allowance for depreciation, carageIndicate vehicle age, carmilIndicate VMT Vehicle-Miles of Travel.
6. method according to claim 5, which is characterized in that the vehicle weights pricing model are as follows:
Wherein, price is the price of used car, MAPEiFor the goodness of fit of i-th of model,For the match value of i-th of model,
I=1,2,3, wherein j is number of data in current reference vehicle parameter, and y is true price price,For under current slice when
The price expectation value that preceding model prediction obtains.
7. method according to claim 6, which is characterized in that this method further include:
Pricing adjustments step, when determining that the second-hand training set can not be expanded, using new car price multiplied by allowance for depreciation into
Row price;
Profit margin calculates step, establishes the Profit Rate Model between retail price, auction price, described in the price calculating based on used car
Profit margin.
8. a kind of used car pricing device, which is characterized in that the device includes:
Get parms unit, obtains the vehicle parameter of used car to be fixed a price;
Data processing unit is obtained based on the vehicle parameter and refers to vehicle parameter;
Pricing model generation unit constructs n vehicle pricing model based on the vehicle parameter and the reference vehicle parameter, and
Vehicle weighting pricing model is weighted to obtain to n vehicle pricing model using BOOST;
Price unit obtains the price of used car based on the vehicle parameter using vehicle weighting pricing model;
Wherein, n is integer.
9. device according to claim 8, which is characterized in that the vehicle parameter include brand, vehicle system, vehicle, the time of registering the license,
Region and/or mileage travelled.
10. device according to claim 9, which is characterized in that the data processing unit includes:
Judgment module, judges whether amount of training data relevant to the vehicle parameter is greater than or equal to certain threshold value, is sentenced
Disconnected result;
Data extending module, if the judging result be it is yes, using the training data as refer to vehicle parameter, if described
Judging result be it is no, training data is expanded according to time, region, vehicle or vehicle group, vehicle condition network of personal connections, after expansion
Training data, which is used as, refers to vehicle parameter.
11. device according to claim 10, which is characterized in that the vehicle pricing model include: unitary robust linear model,
Binary robust linear model and unitary Robust Exponential model.
12. device according to claim 11, which is characterized in that the unitary robust linear model are as follows: price1=a0+a1*
carage;
The binary robust linear model are as follows: price2=b0+b1*carage+b2*carmil;
The unitary Robust Exponential model are as follows: lnprice3=c0+carage;
Wherein, price1, price2, price3 are the vehicle price under different models, a0、b0And c0For constant, a1、b1、b2And c1
It for weighting coefficient, is calculated by allowance for depreciation, carageIndicate vehicle age, carmilIndicate VMT Vehicle-Miles of Travel.
13. device according to claim 12, which is characterized in that the vehicle weights pricing model are as follows:
Wherein, price is the price of used car, MAPEiFor the goodness of fit of i-th of model,For the match value of i-th of model,
I=1,2,3, wherein j is number of data in current reference vehicle parameter, and y is true price price,For under current slice when
The price expectation value that preceding model prediction obtains.
14. device according to claim 13, which is characterized in that the device further include:
Pricing adjustments unit, when determining that the second-hand training set can not be expanded, using new car price multiplied by allowance for depreciation into
Row price;
Profit margin computing unit establishes the Profit Rate Model between retail price, auction price, described in the price calculating based on used car
Profit margin.
15. a kind of used car pricing device equipment, which is characterized in that the equipment includes processor, memory, the processor
It is connected with the memory by bus, machine readable code is stored in the memory, the processor executes memory
In machine readable code perform claim require 1-7 any one method.
16. a kind of computer readable storage medium, which is characterized in that it is stored with computer program code on the storage medium,
When the computer program code is computer-executed, perform claim requires any method of 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711159685.4A CN109816409A (en) | 2017-11-20 | 2017-11-20 | A kind of used car pricing method, device, equipment and computer-readable medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711159685.4A CN109816409A (en) | 2017-11-20 | 2017-11-20 | A kind of used car pricing method, device, equipment and computer-readable medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109816409A true CN109816409A (en) | 2019-05-28 |
Family
ID=66598699
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711159685.4A Pending CN109816409A (en) | 2017-11-20 | 2017-11-20 | A kind of used car pricing method, device, equipment and computer-readable medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109816409A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110544135A (en) * | 2019-09-10 | 2019-12-06 | 金瓜子科技发展(北京)有限公司 | Data processing method and device |
CN111383060A (en) * | 2020-03-18 | 2020-07-07 | 浙江大搜车软件技术有限公司 | Vehicle price determination method and device, electronic equipment and storage medium |
CN111768220A (en) * | 2019-06-28 | 2020-10-13 | 北京沃东天骏信息技术有限公司 | Method and apparatus for generating vehicle pricing models |
CN113052633A (en) * | 2021-03-26 | 2021-06-29 | 中国第一汽车股份有限公司 | Vehicle residual value evaluation method, device, equipment and medium |
CN113256325A (en) * | 2021-04-21 | 2021-08-13 | 北京巅峰科技有限公司 | Second-hand vehicle valuation method, system, computing device and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105808975A (en) * | 2016-03-14 | 2016-07-27 | 南京理工大学 | Multi-core-learning and Boosting algorithm based protein-DNA binding site prediction method |
CN106651464A (en) * | 2016-12-30 | 2017-05-10 | 中国地质大学(武汉) | Agricultural product price prediction method and apparatus |
CN106779187A (en) * | 2016-11-30 | 2017-05-31 | 广东电网有限责任公司电网规划研究中心 | The price parameter generation method and device of electricity power engineering equipment and materials |
-
2017
- 2017-11-20 CN CN201711159685.4A patent/CN109816409A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105808975A (en) * | 2016-03-14 | 2016-07-27 | 南京理工大学 | Multi-core-learning and Boosting algorithm based protein-DNA binding site prediction method |
CN106779187A (en) * | 2016-11-30 | 2017-05-31 | 广东电网有限责任公司电网规划研究中心 | The price parameter generation method and device of electricity power engineering equipment and materials |
CN106651464A (en) * | 2016-12-30 | 2017-05-10 | 中国地质大学(武汉) | Agricultural product price prediction method and apparatus |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111768220A (en) * | 2019-06-28 | 2020-10-13 | 北京沃东天骏信息技术有限公司 | Method and apparatus for generating vehicle pricing models |
CN110544135A (en) * | 2019-09-10 | 2019-12-06 | 金瓜子科技发展(北京)有限公司 | Data processing method and device |
CN111383060A (en) * | 2020-03-18 | 2020-07-07 | 浙江大搜车软件技术有限公司 | Vehicle price determination method and device, electronic equipment and storage medium |
CN113052633A (en) * | 2021-03-26 | 2021-06-29 | 中国第一汽车股份有限公司 | Vehicle residual value evaluation method, device, equipment and medium |
CN113256325A (en) * | 2021-04-21 | 2021-08-13 | 北京巅峰科技有限公司 | Second-hand vehicle valuation method, system, computing device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109816409A (en) | A kind of used car pricing method, device, equipment and computer-readable medium | |
CN111445134B (en) | Commodity sales prediction method, commodity sales prediction apparatus, computer device, and storage medium | |
US7769628B2 (en) | Systems, methods and computer program products for modeling uncertain future demand, supply and associated profitability of a good | |
Qian et al. | Incorporating heterogeneity to forecast the demand of new products in emerging markets: Green cars in China | |
CN109308538B (en) | Method and device for predicting transaction conversion rate | |
CN107133825A (en) | The Forecasting Methodology and device of a kind of businessman's volume of the flow of passengers | |
JPWO2017221448A1 (en) | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND PROGRAM | |
Clemente-Císcar et al. | A methodology based on profitability criteria for defining the partial defection of customers in non-contractual settings | |
CN107330744A (en) | The recommendation method and system of air ticket derived product | |
KR20180117286A (en) | Method and Apparatus for pricing based on machine learning | |
CN108876465A (en) | A kind of pair of trade company's mode of carrying on the work divides the method, apparatus and server of group | |
US20050262012A1 (en) | Systems, methods and computer program products for modeling demand, supply and associated profitability of a good in a differentiated market | |
CN104346751A (en) | Semi-automatic algorithm transaction method | |
Konstantakis et al. | Modeling the dynamic response of automobile sales in troubled times: A real-time Vector Autoregressive analysis with causality testing for Greece | |
Awad et al. | Performance of urban rail transit: a review of measures and interdependencies | |
CN114596111A (en) | Risk identification model generation method, device, equipment and storage medium | |
CN111091401A (en) | Network appointment pricing method, system, storage medium and equipment | |
CN111507779A (en) | Method and device for grading commodities | |
CN110428281A (en) | Combine the method and apparatus for determining peers amount for a variety of related products | |
Chaouch | Inventory control and periodic price discounting campaigns | |
CN115063178A (en) | Method and device for determining sensitivity degree of target group to service scene | |
CN112232945B (en) | Method and device for determining personal client credit | |
CN108805603A (en) | Marketing activity method for evaluating quality, server and computer readable storage medium | |
CN114004626A (en) | Method, system and application for evaluating monetary value of patent | |
CN109360032B (en) | Customer evaluation method, apparatus, device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200520 Address after: Room 323605, building 5, yard 1, Futong East Street, Chaoyang District, Beijing 100020 Applicant after: Youxuan (Beijing) Information Technology Co.,Ltd. Address before: 200131 Shanghai futesz Pudong New Area Free Trade Zone No. 211 North Road, room 368, 302 parts Applicant before: YOUGU (SHANGHAI) INFORMATION TECHNOLOGY CO.,LTD. |
|
TA01 | Transfer of patent application right | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190528 |
|
RJ01 | Rejection of invention patent application after publication |