Thermal coal price prediction based on optimized VMD and BiGRU-Attention
YU Shuchao
SHAO Bilin
Abstract：In view of the nonlinearity and non-stationarity characteristics of the coal price series,this paper proposes a combined prediction model for thermal coal prices based on BWO-VMD-BiGRU-Attention.Firstly,the Pearson correlation coefficient is combined with the XGBoost algorithm to screen out features with high correlation.Secondly,BWO is used to optimize the parameters of VMD,and the original price series is decomposed into multiple stationary components.Then,the features and each component are input into the BiGRU-Attention model for prediction.Finally,the predicted values of each component are superimposed to obtain the final prediction result.Verified by multiple comparison models,this model has better prediction effects and accuracy,good interpretability and rationality,and can effectively improve the prediction accuracy of thermal coal prices.
Keywords：VMD algorithmBiGRU-Attention modelthermal coalprice predictionBWO algorithmprediction effects
Publication Date：2025-07-28
Online Publishing Date：2025-09-26(First online date of this platform, not the publication date of the document)
Pages：9( 29-37 )