Research on Second-hand car problem based on neural network model
DOI: 10.23977/jeis.2022.070119 | Downloads: 25 | Views: 948
Fengting Bai 1
1 Faculty of Electronic Information and Automation, Tianjin University of Science and Technology, Tianjin, 300222, China
Corresponding AuthorFengting Bai
In order to promote the stable development of second-hand car market, this paper constructs a mathematical model to quickly and reasonably predict and evaluate each index of second-hand car. Firstly, the collected large-scale data are cleaned, and then the cleaned data are tested by J-B test. The results show that the P values of all variables are less than the significance level, and the dimension of the data can be reduced by calculating the correlation coefficient. Then, by calculating and selecting 15 variables with large Pearson correlation coefficient with the second-hand car transaction price, the neural network model is established and trained. By adjusting the super parameters and using various methods to optimize the performance of the neural network, it is finally used for the regression prediction of the data, and a more reasonable result is obtained.
KEYWORDSsecond-hand car price, correlation coefficient, neural network
CITE THIS PAPER
Fengting Bai, Research on Second-hand car problem based on neural network model. Journal of Electronics and Information Science (2022) Vol. 7: 108-112. DOI: http://dx.doi.org/10.23977/jeis.2022.070119.
 Liu Sen Research on used car price evaluation method based on neural network [J] Automotive industry research, 2019 (1): 21-24.
 Zhang Cuijuan, Feng Xuejun, Sheng min Development steps of factor analysis and implementation of R language program code [J] Journal of Anqing Normal University (NATURAL SCIENCE EDITION), 2013 (2): 28-31.
 He Xiaoqun Modern statistical analysis methods and applications 3rd Edition [M] Renmin University of China Press, 2012.
 Edited by Si Shoukui, sun Xijing, Zhang Decun, Zhou Gang and Han Qinglong Mathematical modeling algorithm and application problem solving [M] Beijing: National Defense Industry Press, 2015.08.