基于混频数据模型的北京旅游需求短期预测

Short-term forecast of Beijing tourism demand based on mixed frequency data model

百度指数数据反映了用户的搜索行为与需求,为旅游需求的预测提供了数据基础。本文以北京市为例,构建基于百度指数月度数据的混频数据模型,开展对北京市季度旅游需求的短期预测。分析了高频北京美食百度指数月度数据滞后阶数和权重的变化对低频北京旅游人数的影响。实证结果表明,指数Almon权重的混频数据模型比其它不同权重形式的混频数据模型预测精度高。

Baidu index data reflects the search behavior and demand of users,and provides a data basis for the prediction of tourism demand.Taking Beijing as an example,this paper constructed a mixed frequency data model based on monthly data of Baidu Index to make short-term forecasts of quarterly tourism demand in Beijing.The influence of the change of lag order and weight of monthly data of high-frequency Baidu index of Beijing cuisine on the number of tourists in low-frequency Beijing is analyzed.The empirical results show that the mixed frequency data model of the index Almon weight is more accurate than other mixed frequency data models with different weight forms.