论文部分内容阅读
根据中国统计年鉴公布的数据,建立基于时间序列ARIMA模型和BP神经网络组合模型对旅游需求进行预测。首先,建立ARIMA模型对浙江省旅游需求进行分析预测。然后,将得到的预测误差序列作为BP神经网络模型的输入值,进一步减小相对误差,综合ARIMA模型的预测结果和BP模型得到的预测误差,获得精确度较高的旅游需求预测模型。最后,与灰色系统GM(1,1)的预测结果进行比较。
According to the data released by China Statistical Yearbook, the time series ARIMA model and BP neural network combined model are established to forecast the tourism demand. First, the ARIMA model is established to analyze and predict the tourism demand in Zhejiang Province. Then, the prediction error sequence obtained is used as the input value of BP neural network model to further reduce the relative error. The prediction results of ARIMA model and the prediction error obtained by BP model are combined to obtain the prediction model of tourism demand with high accuracy. Finally, the result is compared with the gray system GM (1,1).