Used car valuation based on Bayesian optimization in random forest

Jinling Wei; Shangyu Meng

doi:10.1117/12.3031114

19 July 2024 Used car valuation based on Bayesian optimization in random forest

Jinling Wei, Shangyu Meng

Proceedings Volume 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024); 131814T (2024) https://doi.org/10.1117/12.3031114
Event: Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 2024, Beijing, China

Abstract

Aiming at the problem of second-hand car valuation, this paper makes an in-depth research on second-hand car data from mothercup Big data competition. First of all, we preprocessed the data and processed the missing values and outliers by a variety of methods, such as direct deletion, mode filling, correlation filling, support vector machine missing value filling, etc., and finally got 29539 data of 30 feature fields. Next, we carried out feature engineering to construct two new feature registration time and vehicle age by means of exhibition time, registration time and registration time, and logized the predicted price value to make the predicted value biased to normal distribution. In addition, we combined 36 columns of features into 25 columns of features. In terms of the establishment and solution of the model, we adopted the stochastic forest model based on Bayesian optimization, and got an excellent result with an evaluation index of 0.83, which is better than the 0.78 of the direct use of stochastic forest. The superiority of this model can be determined by comparing it with four models. The purpose of this study is to improve the accuracy of used car valuation and provide a more valuable reference for related industries.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jinling Wei and Shangyu Meng "Used car valuation based on Bayesian optimization in random forest", Proc. SPIE 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 131814T (19 July 2024); https://doi.org/10.1117/12.3031114

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Mathematical optimization

Random forests

Decision trees

Performance modeling

Education and training

Machine learning

Stochastic processes

Show All Keywords

Keywords/Phrases

Search In:

Publication Years