Application of Multiple Linear Regression and Time-Series Models for Forecasting Sales of New Energy Vehicles

As one of the important means to reduce carbon dioxide emissions, new energy vehicles are developing rapidly in the Chinese market. In order to evaluate the future development situation, this paper predicts the sales volume of new energy vehicles by establishing a multiple linear regression model and time series based on the monthly data from 2016 to 2021. According to the fitting results, the multiple linear regression model can better reflect the sales of NEV than the ARIMA model. The ARIMA model predicts that sales of NEVs will continue to grow in the future. The multiple linear regression model makes an in-depth analysis of different influencing factors. In terms of economic factors, the rise in production costs caused by inflation may have a negative impact on sales. As for product factors, the improvement of supporting charging pile facilities is conducive to the increase in NEV sales. Regarding to competitive product analysis, the rise in oil prices is the main reason for purchase intention of NEV. However, they are still far less competitive than conventional cars while NEVs are growing fast. These results shed light on guiding further exploration of sales prediction for NEV.