New Energy Vehicle Customer Mining Model Based on Machine Learning Algorithm

The new energy automobile industry is a strategic emerging industry, and accurately finding the customer targets of different types of new energy automobiles as well as improving the customer experience of different types of new energy automobiles are the main parts to promote the development of the new energy automobile industry. Firstly, This paper analyzes the main indicators affecting customer satisfaction of three types of new energy vehicles: joint venture brands, independent brands, and new power brands. Secondly, based on different new energy vehicle brands, each of them establishes three types of classification models, namely Random Forest, XGboost, and LightGBM, and divides the customer types into two types: purchasing and non-purchasing, and optimizes them using Bayesian parameterization, so as to make the three brands get their own optimal customer mining models. In addition, based on the customer mining models of different brands, this paper uses the collected customer information and the satisfaction of new energy vehicle experience to predict the possibility of customers to buy the car, and all of them get more than 90% accuracy. This paper provides theoretical support for the sales direction of new energy vehicles.