Assessing the future influence of tourism-related factors on economic growth in selected south Asian countries through a random forest approach

The study applies sophisticated machine learning techniques to measure the effect induced by important tourism indicators upon the GDP of six South Asian countries from 2001 to 2019. Among the models tested, the Random Forest model demonstrated the highest predictive accuracy, making it the most effective approach for analyzing GDP determinants in the region. It was determined from a World Development Indicators dataset analysis through the use of a Random Forest model what the main determinants behind GDP growth were for all countries in the area. Tourist arrivals and international tourism expenditure are good indicators of economic growth, while the unemployment rate and population growth have only minor effects. Other tourism-related factors contribute very significantly toward explaining any possible variation in GDP growth. Therefore, these results are important from the standpoint of the formulation of policies related to tourism toward maximizing its contribution to the economies of South Asia. For such policies to result in maximizing contributions from tourism, investments need to focus on the development of tourism infrastructure and international marketing to effect sustainable tourism development environments. Such policies are also very important with respect to unemployment and demographics. This work offers an evidence-based perspective to inform policymakers in developing investment in tourism infrastructure, international tourism promotion, and sustainable tourism practices. Such investment will greatly empower the South Asian economies to reconfigure tourism as a key driver of sustained economic growth and globally improved competitiveness.