A neural network model to forecast Japanese demand for travel to Hong Kong

Apart from simple guesswork, time-series and regression techniques have largely dominated forecasting models for international tourism demand. This paper presents a new approach that uses a supervised feed-forward neural network model to forecast Japanese tourist arrivals in Hong Kong. The input layer of the neural network contains six nodes: Service Price, Average Hotel Rate, Foreign Exchange Rate, Population, Marketing Expenses, and Gross Domestic Expenditure. The single node in the output layer of the neural network represents the Japanese demand for travel to Hong Kong. Officially published annual data in the period of 1967 to 1996 were used to build the neural network. Estimated Japanese arrivals were compared with actual published Japanese arrivals. Experimental results showed that using the neural network model to forecast Japanese arrivals outperforms multiple regression, naive, moving average, and exponent smoothing.