Researches On Financial Expenditure Based On SARIMA And Elman Models And Its Combination Model

With the development of economy, the people's living standard has been significantly improved, China has become the world's second largest economy, the annual GDP grows year after year. The national financial expenditure also shows a rising trend year by year. The financial expenditure is an effective means for the government to implement macro-control and optimize the allocation of resources. In recent years, the proportion of national financial expenditure on people's livelihood has been increasing, and the people have truly felt the benefits of financial expenditure. Because the financial expenditure data has obvious seasonal characteristics, the original sequence should be seasonal adjusted in the data modeling. In order to predict the trend of financial expenditure growth,this thesis firstly applies the seasonal differential autoregressive moving average model(SARIMA)and Elman neural network model to the data. The results show that the SARIMA model is superior to the Elman model. Secondly, we introduce a combined model of SARIMA model and Elman model, and make the further forecast of national expenditure data. In the combined model, we use the Particle Swarm Optimization(PSO) algorithm to minimize the prediction error of the combined model with the average relative percentage error (MAPE) as the objective function to find the optimal combined coefficients. Finally, we analyze the financial expenditure series from January 2000 to December 2015, and forecast the national financial expenditure in 2016. The experimental results show that the combined model is superior to the effect of the single model, which provides a scientific basis for China's financial expenditure budget.