Application Of ARIMA Model And Genetic Algorithm For Optimization Of Neural Network In The Prediction Of GDP

GDP is often regarded as an economic indicator of a country’s economy, GDP can not only reflect the development of a country’s economy, but also can reflect a country’s power and wealth So the tendency of GDP also reflects the development situation of our country and the development trend of the future. We used two kinds of prediction method to forecast the GDP. First, we predict the GDP time series data by using ARIMA time series model. Then according to the characteristics of BP neural network to optimize the parameters of the neural network by genetic algorithm, combining the two algorithms to predict the GDP data. Finally, to predict the results of two methods and compared them.Our results show that, through genetic algorithm optimizing the neural network, the advantages of the two algorithms has been developed, greatly improves the prediction accuracy of neural network. The comparison of the results of predicted by BP neural network optimized by genetic algorithm and the prediction of the traditional ARIMA model proved that artificial intelligence is more accurate than the ARIMA model. Therefore this study shows that the neural network optimized by genetic algorithm has the superiority and better application in dealing with time series data.