The increasing interest aroused by more advanced forecasting techniques, together with the requirement for more accurate forecasts of tourism demand at the destination level due to the constant growth of world tourism, has lead us to evaluate the forecasting performance of neural modelling relative to that of time series methods at a regional level. Seasonality and volatility are important features of tourism data, which makes it a particularly favourable context in which to compare the forecasting performance of linear models to that of nonlinear alternative approaches. Pre-processed official statistical data of overnight stays and tourist arrivals from all the different countries of origin to Catalonia from 2001 to 2009 is used in the study. When comparing the forecasting accuracy of the different techniques for different time horizons, autoregressive integrated moving average models outperform self-exciting threshold autoregressions and artificial neural networks models, especially for shorter horizons. These results suggest that the there is a trade-off between the degree of pre-processing and the accuracy of the forecasts obtained with neural networks, which are more suitable in the presence of nonlinearity in the data. In spite of the significant differences between countries, which can be explained by different patterns of consumer behaviour, we also find that forecasts of tourists arrivals are more accurate than forecasts of overnight stays.Key words: forecasting; time series models; neural networks; tourism demand; Catalonia.JEL classification: C53; C42; C45; L83. IntroductionMany stationary phenomena can be approximated by linear time series models. Nevertheless, it is generally believed that the nonlinear methods outperform the linear methods in modelling economic behaviour. Artificial intelligence techniques have become an essential tool for economic modelling and forecasting, as they are far better able to handle nonlinear behaviour. Neural networks have been applied in many areas, but only recently for tourism demand forecasting. Tourism data is characterized by strong seasonal patterns and volatility, thus original series require significant preprocessing in order to be used with forecasting purposes. While eliminating the existing outliers and adjusting the seasonal component of the series, this filtering process ends up conditioning the forecasting performance of the models. Therefore, tourism demand is a particularly interesting field in which to analyze the effects of data pre-preprocessing on forecast accuracy and to compare the forecasting performance of neural networks relative to that of time series models.There has been a growing interest in tourism research over the past decades. Some of the reasons for this increase in the number of studies of tourism demand modelling and forecasting are: the constant growth of world tourism, the utilization of more advanced forecasting techniques in tourism research and the requirement for more accurate forecasts of tourism demand at the desti...

Abstract:Business and consumer surveys have become an essential tool for gathering information about different economic variables. While the fast availability of the results and the wide range of variables covered made them very useful for monitoring the current status of the economy, there is no consensus on their utility for forecasting macroeconomic developments.The objective of the paper is to analyse the possibility of improving forecasts for selected macroeconomic variables for the euro area using the information provided by these surveys. After analyzing the potential presence of seasonality and the issue of quantification, we have tested if these indicators provide useful information to improve forecasts of the macroeconomic variables. With this aim, different sets of models have been considered (AR, ARIMA, SETAR, Markov switching regime models and VAR) to obtain forecasts for the selected macroeconomic variables. Then, information from surveys has been considered to forecast these variables in the context of the following models: autoregressive, VAR models, Markov Switching Regime models and leading indicators models. In both cases, the Root Mean Square Error (RMSE) has been computed for different forecast horizons.The comparison of the forecasting performance of the two sets of models permit to conclude that in most cases, models that include information from the survey obtain lower RMSE than the best model without survey information. However, this reduction is only significant in a limited number of cases. In this sense, the obtained results extend the results of previous research that have considered information from business and consumer surveys to explain the behaviour of macroeconomic variables, but are not conclusive about its role.

This paper aims to compare the performance of three different artificial neural network techniques for tourist demand forecasting: a multi-layer perceptron, a radial basis function and an Elman network. We find that multi-layer perceptron and radial basis function models outperform Elman networks. We repeated the experiment assuming different topologies regarding the number of lags used for concatenation so as to evaluate the effect of the memory on the forecasting results. We find that for higher memories, the forecasting performance obtained for longer horizons improves, suggesting the importance of increasing the dimensionality for long-term forecasting.

Purpose – This study aims to apply a new forecasting approach to improve predictions in the hospitality industry. To do so, the authors developed a multivariate setting that allows the incorporation of the cross-correlations in the evolution of tourist arrivals from visitor markets to a specific destination in neural network models.\ud Design/methodology/approach – This multiple-input-multiple-output approach allows the generation of predictions for all visitor markets simultaneously. Official data of tourist arrivals to Catalonia (Spain) from 2001 to 2012 were used to generate forecasts for one, three and six months ahead with three different networks.\ud Findings – The study revealed that multivariate architectures that take into account the connections between different markets may improve the predictive performance of neural networks. Additionally, the authors developed a new forecasting accuracy measure and found that radial basis function networks outperform the rest of the models.\ud Research limitations/implications – This research contributes to the hospitality literature by developing an innovative framework to improve the forecasting performance of artificial intelligence\ud techniques and by providing a new forecasting accuracy measure.\ud Practical implications – The proposed forecasting approach may prove very useful for planning purposes, helping managers to anticipate the evolution of variables related to the daily activity of the\ud industry.\ud Originality/value – A multivariate neural network framework has been developed to improve forecasting accuracy, providing professionals with an innovative and practical forecasting approachPeer ReviewedPostprint (author's final draft

No abstract