Artificial Neural Networks versus Multiple Regression in Tourism Demand Analysis

The results revealed that the use of ANNs in tourism demand studies may result in better estimates in terms of prediction bias and accuracy.

Abstract

This study explores and demonstrates the usefulness of artificial neural networks (ANNs) as an alternative approach to the use of multiple regression (MR) in tourism demand studies. The study uses Canadian tourism expenditures in the United States as a measure of demand to demonstrate its application. The results revealed that the use of ANNs in tourism demand studies may result in better estimates in terms of prediction bias and accuracy. Further applications of ANNs in the context of tourism demand analysis are needed to establish and confirm the results.