Tourism Forecasting and Tackling Fluctuating Patterns: A Composite Leading Indicator Approach

Abstract

A growing interest is surfacing toward the non-linearities in tourism demand forecasting. This paper aims to construct a tourism composite indicator to anticipate the cyclical movement for the tourism demand in Fiji. The time duration tackled in the current study is under the span of approximately two decades from 2000 to 2017. Apart from an indicator construction approach and turning point dating algorithm, we proposed a two regime Markov switching model to analyse the Fijian tourism cycle. The empirical results revealed the composite leading indicator accorded a signalling approach for Fijian tourism demand with an average lead time of 2.75 months. Furthermore, the prior-recognition of the tourism economic transition with adequate dating evaluation of the tourism cycle is obtained from the filtered probabilities through the Markov switching models.

Keywords

• fijian tourism demand forecasting
• composite leading indicator approach
• turning point dating
• near-term forecasting
• non-parametric approach