Driven by the “dual carbon” goal, the development of new energy vehicles is the trend. Facing the complex and changeable market situation, only by understanding the trend and grasping the user demand, can we grasp the development opportunity. This paper uses data mining and empirical analysis to study the new energy vehicle companies in which subdivisions are more promising, how to optimize products and reasonable pricing to obtain higher profits. The SARIMA model and exponential smoothing method are used to fit the sales data of new energy vehicles from 2011 to 2019 through python, and the SARIMA model with better fitting effect is used to predict the sales in 2025. The LASSO regression is used to determine the parameters that have a greater impact on the sales of new energy vehicles, and then the K-means clustering analysis and multiple linear regression are used for correlation analysis. The prediction formula of sales and eight product parameters is fitted to provide support for enterprise production.