Estimation of ecological footprint based on tourism development indicators using neural networks and multivariate...

The ecological footprint has attracted a lot of attention in the top tourism destination countries, and this issue may be worrying. This study aims to estimate the ecological footprint, using such indicators as economic growth, natural resources, human capital, and the number of tourists in top tourism destination countries. For this purpose, artificial neural network models and multivariate regression were used for a period of 24 years (1995-2019). The results of the study showed a significant positive correlation between economic growth and ecological footprint. Multivariate regression estimation (R = 0.75) is weaker than neural network models (R = 96.3). Regarding predicting the ecological footprint, neural network models have better performance in comparison with the multivariate regression statistical methods. Accordingly, one can say that for planning ecological footprint, deeper look at neural networks can be more effective in predicting top tourism destination countries.