Evaluation model construction of automobile appearance design based on random forest algorithm

Abstract

Random forest algorithm is a nonlinear supervised classification algorithm, which is based on the idea of ensemble learning and consists of multiple decision tree classifiers. The algorithm has strong generalization ability, fault tolerance ability and nonlinear fitting ability, and can learn the deep-seated laws in the sample system according to a small number of samples using information entropy as the criterion. In the form of questionnaire survey, this paper collects the main evaluation factors of automobile appearance modeling design for 100 consumers or potential consumers. After selecting the evaluation factors, 50 consumers or potential consumers score a car according to these evaluation factors, to collect the original data. Experimental results show that the accuracy of the algorithm is as high as 84%, which shows that the model has such a high accuracy that it can be applied to the evaluation of automobile appearance modeling design. At the same time, this method can also be transferred to the appearance modeling design of other models.