Answers are grounded in this paper and cite their sources.
Purpose Tourism demand forecasting is vital for the airline industry and tourism sector. Combination forecasting has the advantage of fusing several forecasts to reduce the risk of inappropriate model selection for analyzing decisions. This paper investigated the effects of a time-varying weighting strategy on the performance of linear and nonlinear forecast combinations in the context of tourism. Design/methodology/approach This study used grey prediction models, which did not require that the available data satisfy statistical assumptions, to generate forecasts. A quality-control technique was applied to determine when to change the combination weights to generate combined forecasts by using linear and nonlinear methods. Findings The empirical results showed that except for when the Choquet fuzzy integral was used, forecast combination with time-varying weights did not significantly outperform that with fixed weights. The Choquet integral with time-varying weights significantly outperformed that with fixed weights for all model combinations, and had a superior forecasting accuracy to those of other combination methods. Practical implications The tourism sector can benefit from the use of the Choquet integral with time-varying weights, by using it to formulate suitable strategies for tourist destinations. Originality/value Combining forecasts with time-varying weights may improve the accuracy of the predictions. This study investigated incorporating a time-varying weighting strategy into combination forecasting by using CUSUM. The results verified the effectiveness of the time-varying Choquet integral for tourism forecast combination.
No takes yet. Share an insight, caveat, or question.
Yi‐Chung Hu (2023) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: