Comparisons of different methods used for second-hand car price prediction

Jian Chen; Fangfang Li; Jing Xu; Qing Wang; Qingzhen Han; Ming Yan

doi:10.1117/12.2638739

17 May 2022 Comparisons of different methods used for second-hand car price prediction

Jian Chen, Fangfang Li, Jing Xu, Qing Wang, Qingzhen Han, Ming Yan

Proceedings Volume 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022); 122594N (2022) https://doi.org/10.1117/12.2638739
Event: 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing, 2022, Kunming, China

Abstract

By establishing correlation coefficient matrix, huge sample data of second-hand car trading was processed so that, the irrelevant variables were deleted, as well as the missing and outlier values were handled. Then, the main variables have been extracted by using Xgboost algorithm. 13 of 36 major characteristic variables affecting the second-hand car price were filtered out according to their importance ranking, which include the mileage, tradeTime, brand, model et al. With the selected variables as independent variables and the price of second-hand car as dependent variable, the BP neural network model, linear regression model and random forest model were established to predict the price of second-hand cars. Finally, the predicting results were compared, which show that the fit goodness of random forest model is 0.992, and the model evaluation is 0.527, which gives the best performance.

Citation Download Citation

Jian Chen, Fangfang Li, Jing Xu, Qing Wang, Qingzhen Han, and Ming Yan "Comparisons of different methods used for second-hand car price prediction", Proc. SPIE 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022), 122594N (17 May 2022); https://doi.org/10.1117/12.2638739

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