A novel hybrid model for freight volume prediction based on the Baidu search index and emergency.

Accurate freight volume forecasts play a crucial role in supporting regional economies and transportation systems. Nevertheless, the majority of previous studies rely on historical data, which poses challenges in promptly capturing the influence of market changes and emergency situations. To address this challenge, a novel prediction model based on the Baidu search index (BSI) and emergency is proposed, which comprises four distinct stages. In the first stage, we gathered the Baidu search index data and the COVID-19 index to furnish comprehensive, interactive, and timely information for the primary freight volume dataset. In the second stage, seasonal-trend decomposition procedures based on loess (STL) and empirical mode decomposition (EMD) are used to reduce data complexity. Additionally, we utilized boxplot to identify outliers in the remainder component. In the third stage, we employed seasonal naive prediction to forecast the seasonal component, while utilizing a genetic algorithm optimized backpropagation neural network (GABP) to predict other sub-sequences. To improve the prediction accuracy, we applied BPNN for error correction. Finally, to evaluate the performance of the proposed model, China's freight volume is selected as the subject of the study. The results demonstrate that the model incorporating BSI and COVID-19 information can effectively establish a dynamic forecasting system for freight volume. Furthermore, the data preprocessing techniques employed in this study successfully reduce data complexity and enhance the accuracy of prediction. In comparative experiments, the proposed model has been demonstrated to outperform all the contrasted models in terms of forecasting accuracy. [ABSTRACT FROM AUTHOR]