Enterprise Economic Forecasting Method Based on ARIMA-LSTM Model

Enterprise economic forecast is an important part of the development of enterprises, which can help the government to judge the development of enterprises quickly and effectively so as to make scientific decisions of China. With the development of Internet of Things (IOT) technology, enterprise's IOT data can bring strong data basis to enterprise's economic forecast. In order to obtain more accurate results of enterprise economic forecasting, a method of enterprise economic forecasting based on Auto regressive Integrated Moving Average and Long Short Term Memory networks (ARIMA-LSTM) model is proposed, which solves the problem that a single forecasting algorithm can only predict according to a single economic development data. The model uses ARIMA model to predict the linear data of time series such as IOT data, and LSTM to predict the nonlinear relationship. Combined with the historical economic data of enterprises, ARIMA-LSTM model is used to predict the future economic development of enterprises. Comparing the prediction results with ARIMA model and ARIMA-LSTM model without IOT data, it is found that the model has the smallest RMSE, MAE and MAPE. The results show that the model can effectively predict the economic situation of enterprises.