Accurate prior information of passenger flow demand on high‐speed railway is of great significance for the operation and the management of transportation systems. Various factors in modern social life have caused uncertainty at demand. Recently, individuals are increasingly depending on the online search results when choosing among different transportation modes, services, and destinations, which provide important basic information for forecasting the travel demand. This study employs Baidu search index to assist in capturing volatility of high‐speed railway passenger demands, offering insights into the travel inclinations and travelers' actions. Furthermore, we have given more in‐depth attention and analysis to their residual term accounting for the random nature caused by various factors. To this end, a sophisticated deep analysis mechanism based on data decomposition has been devised to extract and analyze the valuable information concealed within the residuals, so as to enhance the comprehension of the variability inherent in the high‐speed railway passenger flow. Meanwhile, an error correction strategy is implemented for all residual terms to improve further their forecasting accuracy. Experimental results from two real‐world datasets demonstrate the effectiveness and robustness of the developed hybrid approach across several popular evaluation indicators. Therefore, this study can function as a reliable instrument, provide sensible data‐driven guidance for resource allocation and make scientific decisions in the railway industry.

中文翻译：

---

基于百度搜索指数残差项及误差修正的高铁客运需求多变量预测方法

准确的高铁客流需求先验信息对于交通系统的运行和管理具有重要意义。现代社会生活中的各种因素造成了需求的不确定性。近年来，人们在选择不同的交通方式、服务和目的地时越来越依赖在线搜索结果，这为预测出行需求提供了重要的基础信息。本研究利用百度搜索指数来帮助捕捉高铁旅客需求的波动性，从而深入了解旅客的出行倾向和行为。此外，我们对它们的残差项给予了更深入的关注和分析，以解释由各种因素引起的随机性。为此，设计了一种基于数据分解的复杂深度分析机制，以提取和分析残差中隐藏的有价值的信息，从而增强对高铁客流固有变化性的理解。同时，对所有残差项实施误差修正策略，进一步提高预测精度。两个现实世界数据集的实验结果证明了所开发的混合方法在多个流行评估指标上的有效性和鲁棒性。因此，本研究可以作为可靠的工具，为铁路行业的资源配置和科学决策提供明智的数据驱动指导。