Tourism Forecasting and its Relationship with Leading Economic Indicators

Research output: Journal article publicationJournal articleAcademic researchpeer-review

89 Citations (Scopus)


This article investigates the application of three time-series forecasting techniques, namely, exponential smoothing, univariate Autoregressive Integrated Moving Average (ARIMA), and adjusted ARIMA to predict travel demand (i.e., the number of arrivals) from different countries to Hong Kong. The third approach, adjusted ARIMA, is an enhancement of univariate ARIMA. This uses influential economic indicators that are highly correlated with travel demand to adjust univariate ARIMA. According to the analysis, adjusted ARIMA with economic indicators seems to be the best forecasting method for Japan, whereas univariate ARIMA is the best predictor for the United States and United Kingdom. Univariate ARIMA and adjusted ARIMA behave similarly for countries like Taiwan, Singapore, and Korea. Among the three forecasting methods, exponential smoothing is the least accurate. This shows that univariate ARIMA and adjusted ARIMA are more suitable and can be applied to forecast the fluctuating series of visitor arrivals.
Original languageEnglish
Pages (from-to)399-420
Number of pages22
JournalJournal of Hospitality and Tourism Research
Issue number4
Publication statusPublished - 1 Jan 2001


  • time series
  • tourist forecast

ASJC Scopus subject areas

  • Education
  • Tourism, Leisure and Hospitality Management


Dive into the research topics of 'Tourism Forecasting and its Relationship with Leading Economic Indicators'. Together they form a unique fingerprint.

Cite this