A novel hybrid approach to Baltic Dry Index forecasting based on a combined dynamic fluctuation network and artificial intelligence method

作者：

Highlights：

• A novel hybrid approach (DFN-AI) integrating complex network theory and AI algorithms is proposed to enhance the accuracy of the Baltic Dry Index (BDI) forecasting.

• DFN-AI models outperform their corresponding single AI forecasting models with lower absolute value, variance of errors, and also higher directional matching rates.

• The accuracy improvements of DFN-AI models are robust for different time-scale BDI datasets as well as in the respect of random sampling cases and challenging situations.

摘要

•A novel hybrid approach (DFN-AI) integrating complex network theory and AI algorithms is proposed to enhance the accuracy of the Baltic Dry Index (BDI) forecasting.•DFN-AI models outperform their corresponding single AI forecasting models with lower absolute value, variance of errors, and also higher directional matching rates.•The accuracy improvements of DFN-AI models are robust for different time-scale BDI datasets as well as in the respect of random sampling cases and challenging situations.

论文关键词：Artificial intelligence algorithm,Complex network,Dynamic fluctuation network,Baltic Dry Index prediction

论文评审过程：Received 26 December 2018, Revised 27 March 2019, Accepted 27 May 2019, Available online 14 June 2019, Version of Record 14 June 2019.

论文官网地址：https://doi.org/10.1016/j.amc.2019.05.043