The Dynamic Analysis of Baltic Exchange Dry Index

Baltic Exchange Dry Index (BDI) is an independent response of maritime market information for the trading and settlement of physical and derivative contracts. In this paper, we propose fuzzy set theory and grey system for modeling the prediction of BDI, and employ the ARIMA model for the calibration of the data structure to depict the trend. The empirical results indicate that for both short-term and long-term BDI data, the fuzzy time series model has the lowest prediction error; the structural change ARIMA model fits better for prediction in the long term, while the GM (1,1) model compared to proposed models has the greatest prediction error. Moreover, the relationship between current BDI and previous BDI is highly significant. In addition, the external interference is negatively related to the current BDI index. The conclusion of this paper provides the bulk shipping industry with a beneficial reference for market and risk assessment.