187. FORECASTING DYNAMIC TOURISM DEMAND USING  ARTIFICIAL NEURAL NETWORKS

Cvetko  Andreeski; Biljana Petrevska

doi:10.51466/JEEIT2162187079a

Cvetko Andreeski Faculty of Tourism and Hospitality – Ohrid, University “St. Kliment Ohridski” – Bitola, Kej Makedonija 95, 6000 Ohrid, Macedonia
Biljana Petrevska Faculty of Tourism and Hospitality – Ohrid, University “St. Kliment Ohridski” – Bitola, Kej Makedonija 95, 6000 Ohrid, Macedonia

DOI: https://doi.org/10.51466/JEEIT2162187079a

Keywords: time series, tourism demand, tourism plannin, , modeling, COVID-19

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 reveals that the bigger the number of neurons may not necessarily lead to further perfor- mance improvement of the model. The MLP network for its better performance in modeling series with unexpected challenges is highly recommended for forecasting dynamic tourism demand