基于时间序列模型与灰色模型的组合预测模型的研究

摘要

In order to effectively improve the accuracy of the prediction model, the combined forecasting model is proposed. Firstly, ARIMA model is used to distinguish and fit the time series data in the paper. And then the fitting and predictive effect of the opti-mizedGM (1, 1) model is better than the GM (1, 1) model. Finally, the ARIMA-GM combined forecasting model is obtained by giving reasonable weights. The results show that prediction accuracy of the combined forecasting model is higher than other single prediction models, which takes advantage of the superiority of single models.%为了能有效地提高预测模型的精度,提出了组合预测模型.本文首先利用APdMA模型对时间序列数据进行模型的识别和拟合,然后由比较可知优化后的GM(1,1)模型拟合和预测效果好于GM(1,1)模型,最后通过赋予合理权重结合ARIMA模型和优化后的GM(1,1)模型两种方法得到ARIMA-GM的组合预测模型.预测结果表明:组合模型的预测准确性高于各个模型单独使用时的准确性,组合模型发挥了各个单一模型的优势.