论文部分内容阅读
在详细调查海南旅游相关数据的前提下,先建立模型对海南旅游需求进行了预测,然后分析了影响旅游需求的主要因素.先用GM(1,1)灰色模型对海南省旅游人数进行预测,并用马尔科夫链修正误差,在灰色模型的基础上进行了优化.进一步,我们将灰色模型与BP神经网络模型结合起来进行预测,并针对BP网络输入层提供了2种方法:三年滚动预测、多因素预测.得出结论:海南旅游人数还将会逐年递增.同时,通过比较相对误差发现,对于问题的预测精度:BP神经网络>灰色模型.最后,我们利用灰色关联度模型得出各因素对旅游需求的影响:服务>交通>景观发展>消费>环境.
Based on a detailed survey of tourism-related data in Hainan Province, we first establish a model to forecast Hainan’s tourism demand, and then analyze the main factors that affect tourism demand.Firstly, we forecast the number of tourists in Hainan Province by GM (1,1) gray model, And the errors are corrected by using Markov chain to optimize the model based on the gray model.Furthermore, we combine the gray model with the BP neural network model to predict and provide two methods for the BP network input layer: three-year rolling forecast , Multivariate prediction.Conclusion: Hainan’s tourism population will increase year by year.Meanwhile, the relative accuracy of the prediction of the problem is found by comparing the relative error: BP neural network> gray model.Finally, we use the gray relational model Impact of Factors on Tourism Demand: Services> Transportation> Landscape Development> Consumption> Environment.