The role of electricity access in promoting industrialization in developing countries: Utilizing machine learning algorithms

This study investigates the influence of industrial employment and access to electricity on manufacturing value-added (MVA) in five emerging economies: Brazil, Nigeria, Egypt, Pakistan, and India. It aims to assess the relative importance of these two factors in driving industrial output, with a focus on identifying patterns that can inform policy development. The study relies on five machine learning algorithms: Random Forest, Gradient Boosting, K-Nearest Neighbors, Decision Trees, and Support Vector Machines to model and investigate the relationship between manufacturing value-added, industrial employment, and electricity access. Correlation studies are carried out by country to better understand the results. According to the study, in each of the five countries, manufacturing value-added is far more impacted by power availability than by industrial employment. Industrial employment only contributed 0.7% to 36.8% of the influence on manufacturing value-added, but availability to power accounted for 63.2% to 99.3%. Strong negative correlations between electricity access and manufacturing value-added were found in Brazil (r = -0.803), Nigeria (r = -0.722), and India (r = -0.682), whereas Pakistan showed a weak positive correlation (r = 0.22) and Egypt a weak inverse correlation (r = -0.382). The correlation between MVA and industrial employment varied: weak positive in Brazil (r = 0.384) and Pakistan (r = 0.11), strong negative in India (r = -0.568), and weak negative in Egypt (r = -0.097) and Nigeria (r = -0.031). The results imply that increasing industrial employment or extending access to electricity does not ensure increased manufacturing production. The impacts vary from nation to nation and are probably influenced by more general sectoral and structural factors, including rival industries, legal systems, and the standard of infrastructure. Emerging country policymakers should prioritize investments in grid resilience, worker skill development, and supply chain modernization. Governments can strengthen evidence-based policy planning by using machine learning as an evaluation and forecasting tool to better match industrial strategy with actual performance indicators.