旅游需求预测的一种新的分解包络方法--来自主要客源国的证据
A New Decomposition Ensemble Approach for Tourism Demand Forecasting: Evidence from Major Source Countries
摘要：
亚太地区是全球主要的国际旅游需求市场，其旅游需求深受多种因素的影响。以往的研究表明，不同的市场因素在不同的时间尺度上影响旅游市场需求。在此基础上，提出了分解集成学习方法，分析了不同市场因素对市场需求的影响，并进一步探讨了该方法在亚太地区旅游需求预测中的潜在优势。本研究通过噪声辅助的多元经验模式分解，对各月入境游客数量进行分解，探讨了旅游目的地与主要客源国之间的多尺度关系。以中国和马来西亚为例进行实证研究，结果表明，分解集成方法在水平预测精度和方向预测精度方面明显优于统计模型、机器学习和深度学习模型。
英文摘要：
The Asian-pacific region is the major international tourism demand market in the world, and its tourism demand is deeply affected by various factors. Previous studies have shown that different market factors influence the tourism market demand at different timescales. Accordingly, the decomposition ensemble learning approach is proposed to analyze the impact of different market factors on market demand, and the potential advantages of the proposed method on forecasting tourism demand in the Asia-pacific region are further explored. This study carefully explores the multi-scale relationship between tourist destinations and the major source countries, by decomposing the corresponding monthly tourist arrivals with noise-assisted multivariate empirical mode decomposition. With the China and Malaysia as case studies, their respective empirical results show that decomposition ensemble approach significantly better than the benchmarks which include statistical model, machine learning and deep learning model, in terms of the level forecasting accuracy and directional forecasting accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
