Simulation research of industrial enterprise total profits based on the neural network of ARIMA

摘要

Industrial enterprise total profit is the important indicator to measure the status of industrial economic sentiment over a given period of time, and also the first indicator for researching the macroeconomic early-warning. In this paper, the ARIMA neural network model is built, through the ARIMA theory combined with neural network theory, using 1997-2015 monthly time series data of the industrial enterprise total profit, to carry out the simulation research of the industrial enterprise total profit. First of all, make the seasonal adjustment for industrial enterprise total profit, to get rid of the seasonal factors of industrial enterprise total profit in the time series. Secondly, to emulate the 1997 ~ 2015 monthly industrial enterprise total profit by ARIMA neural network model, the simulation results show a good simulation training effect. Finally, using ARIMA neural network model to carry on the simulation of the industrial enterprise total profit from January to June in 2016, finally get the simulation values of industrial enterprise total profit from January to June in 2016.