Effects of Age Dependency and Urbanization on Energy Demand in BRICS: Evidence From the Machine Learning Estimator

Abstract

This paper examines the effects of age dependency ratio (the young age, old-age and overall age) and urbanization on renewable and non-renewable energy consumption in Brazil, India, China, and South Africa, considering the panel data from 1990 to 2019. We control economic growth and foreign direct investment inflows as key factors in the energy demand function using the Stochastic Impacts by Regression on Population, Affluence and Technology approach. Empirical analysis has been implemented using the Kernel Regularized Least Squares machine learning method to solve possible classification problems in the traditional regressions without relying on the linearity assumption. It is observed that the young age dependency, overall age dependency, and urbanization negatively affect both renewable and non-renewable energy demand. On the contrary, old-age dependency and economic growth are positively associated with renewable and non-renewable energy demand. The mixed effects of foreign direct investment inflows on renewable and non-renewable energy demand patterns are also found. Thus, the findings suggest that environment policymakers in the BRICS economies should prioritize urbanization, young age, and overall age population to improve energy efficiency.