The Influence Factors Analysis And Forecasting Methods Comparison About Jiangxi Tourism Revenue

Along with the rapid development of modern society as well as the increase of people’s income and leisure time, tourism industry which is known as smokeless industry has risen suddenly. Since tourism industry only needs relatively few resources to invest, and increases employment opportunities for the local, what’s more, it can also promote the development of other sectors of the local economy, many regions pay attention to the development of the tourism industry, even some places have regarded tourism industry as one of their leading industries. So tourism revenue which is a comprehensive indicator of measuring the economic development of the tourism industry has a certain research value.This paper describes the overview of recent tourism economy in Jiangxi, Jiangxi tourism economic data reflects that Jiangxi tourism economy is growing, and Jiangxi tourism revenue is increasing as well. In1991, tourism revenues still accounted for only0.9%of GDP in Jiangxi province, while in2010, this proportion rose to8.66%, and in2012, this value was even reached10.83%.So we can see that the tourism economy is very important to economic development in Jiangxi Province, its contribution to the total economy in Jiangxi is gradually increasing, and Jiangxi society can also get promotion and help from their tourism economy. In order to maintain rapid growth momentum of Jiangxi tourism economy, it is necessary to do some research about the Jiangxi tourism revenue seriously.This paper is divided into five chapters. The first chapter introduces the background about tourism economic research and development, then organizes domestic and foreign references, generalizes the method and the idea used to complete the paper, and the frame chart of the paper etc. The second chapter introduces some basic methods and theories, including connotation of tourism revenue factors, connotation of tourism revenue, gray correlation analysis, gray forecast theory, BP neural network and gray-BP neural network theory. These theories will play a role in foreshadowing for the following. The third chapter is an analysis chapter. After introducing recent tourism economy of Jiangxi, selected ten indicators as influencing factors, they are per capita disposable income of urban residents and per capita net income of rural residents in China and Jiangxi, GDP of China and Jiangxi, national level of consumption and the number of employees of Jiangxi tourist hotels, the per capita green area as well as Passenger transport volume of Jiangxi Province. Use them to carry on gray correlation analysis about Jiangxi tourism revenue. The results show the Grey Correlation Degree between Jiangxi tourism revenue and per capita disposable income of urban residents in China is0.7280, in Jiangxi it is0.7337.and that value is0.7231between Jiangxi tourism revenue and per capita net income of rural residents in China,0.7328in Jiangxi. The value is0.7855between Jiangxi tourism revenue and GDP of China,0.8133between Jiangxi tourism revenue and GDP of Jiangxi,0.7335between Jiangxi tourism revenue and National level of consumption,0.6988between Jiangxi tourism revenue and Passenger transport volume of Jiangxi Province,0.6840between Jiangxi tourism revenue and the per capita green area,0.6683between Jiangxi tourism revenue and the number of employees of Jiangxi tourist hotels. So if we want to develop the tourism economy in Jiangxi and improve Jiangxi tourism revenue, firstly, we should develop the local economy for contributing to the national economy; secondly, we must improve the capacity of Jiangxi tourism traffic; after that, we need enhance tourism environmental governance and tourism services. The fourth chapter introduces the comparison among Jiangxi tourism revenue forecasting methods. Using GM (1,1) prediction model, univariate BP neural network model and multivariate BP neural network model as well as the gray-BP neural network model to forecast Jiangxi tourism revenue, then using MAD,MAPE and MSE to compare and evaluate each model. The empirical results mean that the combination model of gray-BP neural network has better accuracy and it is more suitable for forecasting Jiangxi tourism revenue. The fifth chapter is a summary which is based on the third and fourth chapters. It has summarized shortage and further research of this paper, and given some advice to the next research about Jiangxi tourism revenue.