Forecasting of Automobile Sales Based on Support Vector Regression Optimized by the Grey Wolf Optimizer Algorithm

With the development of Internet and big data, more consumer behavior data are used in different forecasting problems, which greatly improve performance prediction. As main travel tool, sales automobiles will change with variations market external environment. Accurate prediction automobile can not only help dealers adjust their marketing plans dynamically but also economy transportation sector make policy decisions. The is a product high value involvement, its purchase decision be affected by own attributes, economy, other factors. Furthermore, sample have characteristics various sources, great complexity large volatility. Therefore, this paper uses Support Vector Regression (SVR) model, has global optimization, simple structure, strong generalization abilities suitable for multi-dimensional, small to predict monthly automobiles. In addition, parameters optimized Grey Wolf Optimizer (GWO) algorithm accuracy. First, grey correlation analysis method analyze determine factors that affect sales. Second, it build GWO-SVR model. Third, experimental carried out using from Suteng Kaluola Chinese car segment, proposed model compared four commonly methods. results show best mean absolute percentage error (MAPE) root square (RMSE). Finally, some management implications put forward reference.