Tourism combination forecasting using a dynamic weighting strategy with change-point analysis

Yi-Chung Hu

Current Issues in Tourism, 2023, vol. 26, issue 14, 2357-2374

Abstract: Combination forecasting is an important in the literature on tourism. This study considers three important issues to develop a more accurate combination forecasting method for tourism forecasting. We address the unrealistic requirement related to the statistical properties of the collected data for model fitting, assign changing rather than fixed weights to single models, and incorporate nonlinear relationships among single-model forecasts into forecast combinations. This leads us to develop a three-stage procedure for combination forecasting that consists of generating single-model forecasts with grey prediction models, detecting significant changes in the time series to determine when to update the weights for combining the forecasts, and nonlinearly combining individual forecasts based on a dynamic weighting strategy. In contrast with commonly used fixed weighting, the dynamic weighting used here involves the use of change points to identify the period for which the weights need to be re-estimated. The inbound demand for tourism in Taiwan was used as an empirical case to assess the performance of the proposed framework for forecast combinations. The results show that the nonlinear fuzzy integral with the proposed dynamic weighting strategy significantly outperforms that with the fixed weighting strategy, and has a superior forecasting accuracy than other combined models.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/13683500.2022.2120797 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:rcitxx:v:26:y:2023:i:14:p:2357-2374

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/rcit20

DOI: 10.1080/13683500.2022.2120797

Access Statistics for this article

Current Issues in Tourism is currently edited by Jennifer Tunstall

More articles in Current Issues in Tourism from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().