A Hybrid LSTM-Based Ensemble Learning Approach for China Coastal Bulk Coal Freight Index Prediction

Table 6

Predictive performance of hybrid LSTM-EL over three time scales.

	Forecasting accuracy			Improvement percentage
	Daily forecasting	Weekly forecasting	Monthly forecasting	Daily forecasting	Weekly forecasting	Monthly forecasting
	6.25%	4.26%	4.65%	23.53%	47.05%	57.56%
	0.1450	0.1354	0.1021	33.14%	21.95%	54.08%

Note. and represent the average values of MAPE and RMSE. Each average MAPE/RMSE is calculated by the average MAPE/RMSEs of LSTM-GBRT and LSTM-RF from Table 5.