Li, Junlu, and Wei, Yuxing (2022) Evaluation of the market acceptance of vehicles with Random Forest. In: Proceedings of the IEEE 5th International Conference on Advanced Electronic Materials, Computers and Software Engineering. pp. 464-469. From: AEMCSE 2022: IEEE 5th International Conference on Advanced Electronic Materials, Computers and Software Engineering, 22-24 April 2022, Wuhan, China.

PDF (Published Version) - Published Version Restricted to Repository staff only

Abstract

At present, in order to minimize the risk of automobile sales and maximize the sales profit, various machine learning algorithms are widely used to predict the market acceptance of a car. This paper proposes to use the stochastic forest algorithm, an integrated learning algorithm, to model the characteristics of vehicles, predict the market acceptance of vehicles, and use the Gini importance index to evaluate the characteristics that have the greatest impact on the market acceptance of vehicles. The research of this paper can be divided into the following points: The random forest algorithm is used to model the characteristics of the automobile, and the probability distribution of the automobile market acceptance is obtained, so as to predict the automobile market acceptance. The regression model is established, and the Gini importance index, an important parameter in the random forest model, is used as the standard to evaluate the characteristics that have the greatest impact on the market acceptance of a car. According to the experimental results, the prediction accuracy of random forest prediction model is 98%, which is higher than other machine learning algorithms such as support vector machine. In addition, through the quantitative analysis of Gini importance index of different vehicle characteristics, we can finally conclude that safety has the greatest impact on vehicle market acceptance.

Actions (Repository Staff Only)

Item Control Page