Resumen de Forecasting tourist arrivals atattractions: Search engineempowered methodologies
Katerina Volchek, Anyu Liu, Haiyan Song, Dimitrios Buhalis
Tourist decision to visit attractions is a complex process influenced by multiple factors of individualcontext. This study investigates how the accuracy of tourism demand forecasting can be improvedat the micro level. The number of visits to five London museums is forecast and the predictivepowers of Naı ̈ve I, seasonal Naı ̈ve, seasonal autoregressive moving average, seasonal auto-regressive moving average with explanatory variables, SARMAX-mixed frequency data samplingand artificial neural network models are compared. The empirical findings extend understanding ofdifferent types of data and forecasting algorithms to the level of specific attractions. Introducing theGoogle Trends index on pure time-series models enhances the forecasts of the volume of arrivalsto attractions. However, none of the applied models outperforms the others in all situations.Different models’ forecasting accuracy varies for short- and long-term demand predictions. Theapplication of higher frequency search query data allows for the generation of weekly predictions,which are essential for attraction- and destination-level planning.
