What is it about?

The main objective of this study is to improve forecasts of tourism demand by using machine learning techniques based on artificial intelligence. We evaluate the forecasting performance of three different artificial neural network (ANN) models: the multi-layer perceptron (MLP), the radial basis function (RBF) and the Elman network. Each architecture represents a different learning paradigm and therefore deals with data in a different manner. We also evaluate the effect of the memory on the forecasting results by repeating the experiment assuming different topologies regarding the number of input neurons, which determines the number of prior time points to be used in each forecast.

Featured Image

Why is it important?

We assess the out-of-sample forecasting accuracy of each ANN to predict inbound international tourism demand to Catalonia. We find that MLP and RBF models outperform Elman networks. RBF significantly outperform MLP networks when no additional lags are introduced in the networks. On the contrary, when the input has a context of the past, MLP networks show a better forecasting performance. We also find that as the amount of previous months used for concatenation increases, the forecasts obtained for longer horizons improve, suggesting the importance of increasing the dimensionality of the input to networks for long-term forecasting.


This is the first study to compare MLP, RBF and Elman architectures for tourism demand forecasting. The research contributes to the tourism literature by highlighting the most suitable neural networks for tourism demand forecasting.

Oscar Claveria
AQR-IREA, Univeristy of Barcelona

Read the Original

This page is a summary of: Tourism Demand Forecasting with Neural Network Models: Different Ways of Treating Information, International Journal of Tourism Research, July 2014, Wiley, DOI: 10.1002/jtr.2016.
You can read the full text:



The following have contributed to this page