Vehicle valuation method based on machine learning, storage medium, and device

A technology of machine learning and vehicle configuration, applied in the field of vehicle valuation
CN107180367AInactive Publication Date: 2017-09-19HANGZHOU DASOUCHE AUTO SERVICE CO LTD
0 Cites 9 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HANGZHOU DASOUCHE AUTO SERVICE CO LTD
Publication Date
2017-09-19
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a method for evaluating a vehicle based on machine learning, which includes the following steps: information acquisition step: acquiring the original data of the vehicle, the original data of the vehicle including the vehicle year, license plate time and vehicle configuration; preprocessing step: The raw data of the vehicle is preprocessed according to different classifications to obtain the feature set of the vehicle, the feature set includes its own feature set; the residual rate calculation step: obtain the residual rate corresponding to each feature in the feature set of the vehicle through the GBRT model ; Estimate calculation steps: Obtain the residual rate corresponding to the vehicle and the manufacturer's guide price to obtain the vehicle valuation. The invention also discloses a storage medium and a device. The present invention utilizes the transaction data of used cars and the currently available vehicle data information, uses GBRT to mine the relationship between each feature of the vehicle and the residual rate, and in addition to query parameters, introduces real-time data to accurately evaluate used cars .
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the technical field of vehicle valuation, in particular to a method, storage medium and device for vehicle valuation based on machine learning. Background technique

[0002] At present, the current valuation of second-hand cars mainly depends on the personal experience of car collectors, who can often only make accurate valuations for some regions and some models. Although the valuation method based on rule statistics seems to be effective, the granularity is too coarse. Once it is refined to different models, the accuracy needs to be considered. Looking at the entire market, used cars of various brands, regions, and mileages are being traded every day to generate a large amount of data.

[0003] At present, there are mainly the following schemes: use the same retail price ratio of vehicles of the same model in different intervals to estimate the price. This program uses the vehicle transaction data in the most recent...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More