Modeling and application of the sales of automobile enterprise based on combination forecasting theory

The basic principle of combination forecasting is to give the proper weight combination into a single composite model from the results of each single forecasting model. Therefore, in the process of combination, each single model´s advantages strengthened, and disadvantages weaken. Combination forecasting model has higher accuracy and reliability by integrating useful information of each single model losing in the each single forecasting model. According to the historical data of an automobile enterprise, the paper respectively makes use of self-adaptive filtering, multiple regression, triple exponential smoothing and grey system to establish single forecasting model, and allocate the proper weight by using standard deviation method. Based on combination forecasting theory, the Sales Combination Forecasting Model of the enterprise has been established and we apply this kind of model to forecast the sales during the following 6 years.