What is it about?
This is the first study that assesses the forecasting performance of a Multiple-input Multiple-output (MIMO) approach versus univariate predictions generated with Single-input Single-output (SISO) specifications. We evaluate whether modelling the existing common trends in tourist arrivals from all visitor markets to a specific destination can improve tourism predictions.
Featured Image
Photo by Clay Banks on Unsplash
Why is it important?
We use three different Artificial Neural Networks (ANN) in a multivariate setting that takes into account the correlations in the evolution of inbound international tourism demand to Catalonia (Spain). On the one hand, we find that hybrid models such as RBF NN outperform MLP and the Elman networks. On the other hand, we find that a MIMO approach proves useful when the evolution of tourist arrivals form visitor markets share a common trend.
Perspectives
This is the first study in tourism that compares the forecasting accuracy of MIMO predictions to that of univariate forecasts. This research contributes to the forecasting literature by assessing the forecasting performance of an alternative way to model cointegrated variables. The proposed forecasting approach provides tourist managers and practitioners with a new way of using the common trends from different markets to generate predictions.
Oscar Claveria
AQR-IREA, Univeristy of Barcelona
Read the Original
This page is a summary of: Common trends in international tourism demand: Are they useful to improve tourism predictions?, Tourism Management Perspectives, October 2015, Elsevier,
DOI: 10.1016/j.tmp.2015.07.013.
You can read the full text:
Contributors
The following have contributed to this page
