Modelling tourism demand to Spain with machine learning techniques. The impact of forecast horizon on model selection

Abstract

This study assesses the influence of the forecast horizon on the forecasting performance of several machine learning (ML) techniques. We compare the forecast accuracy of Support Vector Regression (SVR) to Neural Network (NN) models, using a linear model as a baseline. We focus on international tourism demand to all seventeen regions of Spain. The SVR with a Gaussian radial basis function kernel outperforms the rest of the models for the longest forecast horizons. We also find that ML methods improve their forecasting accuracy with respect to linear models as forecast horizons increase. This results shows the suitability of SVR for medium and long term forecasting.