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

TL;DR

This paper compares machine learning models for forecasting tourism demand in Spain, highlighting how Support Vector Regression excels at longer forecast horizons and outperforms linear models in accuracy.

Contribution

It demonstrates the effectiveness of SVR over neural networks and linear models for medium and long-term tourism demand forecasting in Spain.

Findings

SVR outperforms NN and linear models at longer horizons

Machine learning models improve accuracy with longer forecast horizons

SVR is suitable for medium and long-term tourism demand forecasting

Abstract

This study assesses the influence of the forecast horizon on the forecasting performance of several machine learning techniques. We compare the fo recast accuracy of Support Vector Regression (SVR) to Neural Network (NN) models, using a linear model as a benchmark. 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 machine learning methods improve their forecasting accuracy with respect to linear models as forecast horizons increase. This result shows the suitability of SVR for medium and long term forecasting.