A new forecasting approach for the hospitality industry

What is it about?

This study aims to apply a new forecasting approach to improve predictions in the hospitality industry. To do so, the authors developed a multivariate setting that allows the incorporation of the cross-correlations in the evolution of tourist arrivals from visitor markets to a specific destination in neural network models. This multiple-input-multiple-output (MIMO) approach allows the generation of predictions for all visitor markets simultaneously.

Featured Image

Photo by Alfred Quartey on Unsplash

Photo by Alfred Quartey on Unsplash

Why is it important?

The main aim of this study is to develop a new forecasting framework to improve the forecasting performance of artificial neural network (ANN) models. The results of the forecasting multiple-step ahead comparison show that: - The predictive performance of ANN models can be improved by taking into account the connections between the different markets by means of multivariate MIMO architectures. - Hybrid models, which combine supervised and non-supervised learning, are more indicated for tourism demand forecasting than models using supervised learning alone. - Radial basis function (RBF) ANN models outperform the rest of the models. Additionally, the authors developed a new forecasting accuracy measure to compare the forecasting performance between two competing models. This statistic consists on a ratio that calculates the proportion of periods in which the model under evaluation obtains a lower absolute forecasting error than the benchmark model. This measure of forecast accuracy is referred to as the percentage of periods with lower absolute error (PLAE).

Perspectives