Forecasting Dynamic Tourism Demand Using Artificial Neural Networks

Abstract

Planning tourism development means preparing the destination for coping with uncertainties as tourism is sensitive to many changes. This study tested two types of artificial neural networks in modeling international tourist arrivals recorded in Ohrid (North Macedonia) during 2010-2019. It argues that the MultiLayer Perceptron (MLP) network is more accurate than the Nonlinear AutoRegressive eXogenous (NARX) model when forecasting tourism demand. The research reveales that the bigger the number of neurons may not necessarily lead to further performance improvement of the model. The MLP network for its better performance in modelling series with unexpected challenges is highly recommended for forecasting dynamic tourism demand.