Forecasting of New Energy Vehicle Sales and Evaluation of Regional Development Based on BP Neural Network and EWM-TOPSIS

This paper focuses on the new energy vehicle market, utilizing big data technology and artificial intelligence algorithms to perform statistics, analysis, and forecasting in both temporal and spatial dimensions. In the time dimension, the sales volume is forecasted by piecewise cubic Hermite interpolation, polynomial fitting, ARIMA model and BP neural network forecasting model, and the forecasting results between different models are compared and analyzed. Meanwhile, the factors affecting this market are analyzed using the entropy weight method. In the spatial dimension, the development level of each province is assessed using the TOPSIS comprehensive evaluation method, and the development stage in which different provinces are located is classified using K-means cluster analysis. The results show that this new energy vehicle market is developing rapidly, but there is still the problem of uneven development in some regions. At the same time, the study also found that BP neural network has higher credibility in sales prediction, the method of EWM-TOPSIS can effectively assess the market development level of each province and city, and K-means cluster analysis can intuitively show the differences in the development stage. The research of this paper can provide technical support and theoretical support for the industrial development of China's new energy vehicle market in the era of big data.