In view of the tourism market characteristics influenced by many factors, nonlinear and small-sample data, this paper combines grey theory with Elman neural network to set up a multi-factor estimation model. On the basis of analyzing and selecting the related factors of domestic tourism demand,the per capita disposable income, net income of the rural residents and number of lodging and catering enterprises were determined as the key influence factors with a grey relation method, meanwhile, taking the number of domestic tourism as the characteristic variables, a GM(1,4) model was built. In order to improve the prediction performance of theGM(1,N) model for nonlinear dynamic system, Elman neural network was used to search for the nonlinear mapping relationship between input and output variables. The experimental results show that the combined forecasting model has higher prediction accuracy than the single model, and is applicable to domestic tourism demand prediction.%针对旅游市场具有影响因素多、非线性、样本数据少的特点,将灰色理论与Elman神经网络相结合建立多因素组合预测模型,并将其应用于国内旅游需求的预测.在分析选取影响国内旅游需求的相关因素的基础上,采用灰色关联度法确定城镇居民人均可支配收入、农村居民纯收入、住宿餐饮企业数量为主要影响因素,同时以国内旅游人数为特征变量,建立了GM(1,4)模型.为提高GM(1,N)模型对非线性动态系统的预测能力,利用Elman神经网络寻找输入输出变量之间的非线性映射关系.实验结果表明组合预测模型比单一模型有更高的预测精度,可以用于国内旅游需求预测.
展开▼