Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A second-hand vehicle valuation method and a valuation system

A technology for used cars and models, applied in the field of used car valuation, can solve the problems of data collection and data processing reducing the ability of machine learning models, and achieve the effect of clear abnormal data, reduce abnormal situations, and improve accuracy.

Inactive Publication Date: 2019-05-17
优轩(北京)信息科技有限公司
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Machine learning models get better with good data, wrong data collection and data processing can reduce your ability to build predictive and inductive machine learning models

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A second-hand vehicle valuation method and a valuation system
  • A second-hand vehicle valuation method and a valuation system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention is described below based on examples, but the present invention is not limited to these examples.

[0032] Through the statistical analysis of the historical data of a large number of real transactions of used cars accumulated, the price of used cars of the same model basically satisfies the distribution that decreases linearly with the increase of the age of the car. Therefore, the present invention provides a used car valuation method, which includes the following steps:

[0033] (1) Linear model training stage

[0034] Construct a linear model f(x)=w based on supervised learning for the predicted vehicle type 1 x 1 +w 2 x 2 +...+w n x n +b, and use the existing historical transaction data of this model for linear regression training.

[0035] Further, as the years increase, the price of used cars of the same model shows a stepwise downward trend, and it is a linearly decreasing function only in a certain time interval, so the linear model ...

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

PUM

No PUM Login to View More

Abstract

The invention provides a second-hand vehicle valuation method and a valuation system. The method comprises the following steps of firstly, constructing a supervised learning-based linear model for a predicted vehicle model, and carrying out linear regression training by utilizing historical transaction data of the predicted vehicle model; and then the second-hand vehicle price evaluator performs manual adjustment on the abnormal point until the linear model prediction result reaches a preset target. According to the invention, the manual adjustment system is introduced into the training process of the machine learning model, so that the generalization capability of the machine learning model can be effectively enhanced, and the prediction precision of the machine learning model is improved.

Description

technical field [0001] The invention relates to used car valuation, in particular to a used car valuation method and valuation system based on a manual adjustment system. Background technique [0002] The main task of supervised learning in machine learning is to use models to achieve accurate predictions. By training the machine learning model to achieve the highest possible accuracy on new data (unlabeled). In other words, it is hoped that the model trained with the training data can be applied to the new data to be tested. Just like this, when a new model is trained in actual development, it is only possible to use it to predict high-quality results. [0003] Therefore, when evaluating the performance of a model, you need to know how well a certain model performs on a new dataset. This seemingly simple problem hides many difficulties and pitfalls, even experienced machine learning users can't help but fall into it. [0004] In order to obtain accurate predictions, the...

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

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q30/02
Inventor 石玉明邱慧高冬
Owner 优轩(北京)信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com