Free reading is over, click to pay to read the rest ... pages
0 dollars,0 people have bought.
Reading is over. You can download the document and read it offline
0people have downloaded it
Document pages: 27 pages
Abstract: The Asian-pacific region is the major international tourism demand market inthe world, and its tourism demand is deeply affected by various factors.Previous studies have shown that different market factors influence the tourismmarket demand at different timescales. Accordingly, the decomposition ensemblelearning approach is proposed to analyze the impact of different market factorson market demand, and the potential advantages of the proposed method onforecasting tourism demand in the Asia-pacific region are further explored.This study carefully explores the multi-scale relationship between touristdestinations and the major source countries, by decomposing the correspondingmonthly tourist arrivals with noise-assisted multivariate empirical modedecomposition. With the China and Malaysia as case studies, their respectiveempirical results show that decomposition ensemble approach significantlybetter than the benchmarks which include statistical model, machine learningand deep learning model, in terms of the level forecasting accuracy anddirectional forecasting accuracy.
Document pages: 27 pages
Abstract: The Asian-pacific region is the major international tourism demand market inthe world, and its tourism demand is deeply affected by various factors.Previous studies have shown that different market factors influence the tourismmarket demand at different timescales. Accordingly, the decomposition ensemblelearning approach is proposed to analyze the impact of different market factorson market demand, and the potential advantages of the proposed method onforecasting tourism demand in the Asia-pacific region are further explored.This study carefully explores the multi-scale relationship between touristdestinations and the major source countries, by decomposing the correspondingmonthly tourist arrivals with noise-assisted multivariate empirical modedecomposition. With the China and Malaysia as case studies, their respectiveempirical results show that decomposition ensemble approach significantlybetter than the benchmarks which include statistical model, machine learningand deep learning model, in terms of the level forecasting accuracy anddirectional forecasting accuracy.