Modelling cross-dependencies between Spain's regional tourism markets with an extension of the Gaussian process regression model

TL;DR

This paper extends Gaussian process regression to model and forecast the interconnected regional tourism demands in Spain, leveraging cross-dependencies to improve accuracy over traditional neural network benchmarks.

Contribution

It introduces a novel extension of Gaussian process regression for multivariate forecasting that captures cross-dependencies between regional tourism markets.

Findings

The extended model outperforms neural network benchmarks in forecasting accuracy.

Incorporating inter-market connections enhances regional demand predictions.

The approach effectively models the correlations among Spain's 17 regional tourism markets.

Abstract

This study presents an extension of the Gaussian process regression model for multiple-input multiple-output forecasting. This approach allows modelling the cross-dependencies between a given set of input variables and generating a vectorial prediction. Making use of the existing correlations in international tourism demand to all seventeen regions of Spain, the performance of the proposed model is assessed in a multiple-step-ahead forecasting comparison. The results of the experiment in a multivariate setting show that the Gaussian process regression model significantly improves the forecasting accuracy of a multi-layer perceptron neural network used as a benchmark. The results reveal that incorporating the connections between different markets in the modelling process may prove very useful to refine predictions at a regional level.