Optimizing Time-series Prediction on China's Green Trade Economy

Abstract

With the impact of green trade barriers in recent years, China's green trade economy is facing enormous challenges. Using data from the website of the General Administration of Customs of the People's Republic of China (GACC), this paper aims to employ Seasonal Autoregressive Integrated Moving Average (SARIMA) model and Long Short Term Memory (LSTM) model to forecast the total import and export volume of China's green trade, and error analysis is made according to the forecasting result. Considering that inflation is an important influence factor in forecasting economics, the models are optimized by eliminating inflation through consumer price index (CPI) and the following results are obtained. Firstly, the LSTM model obtains better performance than the SARIMA model. Secondly, forecasting accuracy of the optimized models is improved. Thirdly, China's green trade economy shows a steady trend in the near future.