China Coastal Bulk (Coal) Freight Index Forecasting Based on an Integrated Model Combining ARMA, GM and BP Model Optimized by GA

Abstract

The China Coastal Bulk Coal Freight Index (CBCFI) is the main indicator tracking the coal shipping price volatility in the Chinese market. This index indicates the variable performance of current status and trends in the coastal coal shipping sector. It is critical for the government and shipping companies to formulate timely policies and measures. After investigating the fluctuation patterns of the shipping index and the external factors in light of forecasting accuracy requirements of CBCFI, this paper proposes a nonlinear integrated forecasting model combining ARMA (Auto-Regressive and Moving Average), GM (Grey System Theory Model) and BP (Back-Propagation) Model Optimized by GA (Genetic Algorithms). This integrated model uses the predicted values of ARMA and GM as the input training samples of the neural network. Considering the shortcomings of the BP network in terms of slow convergence and the tendency to fall into local optimum, it innovatively uses a genetic algorithm to optimize the BP network, which can better exploit the prediction accuracy of the combined model. Thus, establishing the combined ARMA-GM-GABP prediction model. This work compares the short-term forecasting effects of the above three models on CBCFI. The results of the forecast fitting and error analysis show that the predicted values of the combined ARMA-GM-GABP model are fully consistent with the change trend of the actual values. The prediction accuracy has been improved to a certain extent during the observation period, which can better fit the CBCFI historical time series and can effectively solve the CBCFI forecasting problem.