Business Analytics for Green Electricity Transition Planning:
Explainable Forecasting of Renewable Electricity Shares
from Cross-Country Energy Indicators
Saad Metawea1,∗ , Maha Metawea2
1Professor of Finance, Faculty of Commerce, Mansoura University, Egypt
2Associate Professor of Finance, Faculty of Business Administration, Delta University for Science and
Technology, Egypt
Emails: s Metawa@Yahoo.com; Maha.mtawea@Deltauniv.edu.eg
Abstract
Renewable electricity growth is central to sustainable development, decarbonization, and green-technology
planning. However, much of the forecasting literature remains focused on plant-level or narrow-horizon technical
prediction, with limited attention to country-level decision support for investment screening, transition
monitoring, and strategic benchmarking. This study develops a business analytics framework to forecast the
renewable share of electricity generation and classify countries by renewable-transition level using a crosscountry
panel based on the Our World in Data Energy database. The empirical sample comprises 5,162
country-year observations from 213 countries over the period 2000–2025 and includes measures of electricity
demand, electricity generation, primary energy use, greenhouse-gas emissions, and energy-system structure.
Three regression models and three classification models were evaluated using a fixed train–test de sign. The
random-forest regressor achieved the best continuous forecasting performance, with MAE = 3.536, RMSE =
6.466, and R2 = 0.960, while the random-forest classifier delivered the best tier-classification performance,
with 93.998% accuracy and macro-F1 = 0.940. Feature-importance analysis identified greenhouse-gas emissions,
energy intensity, electricity generation, electricity demand, and per-capita electricity consumption as the
most influential p redictors. The findings indicate that renewable-transition benchmarking can be framed as a
managerial analytics problem, extending sustainability research beyond descriptive monitoring toward practical
decision support for business and policy planning.
Keywords: Renewable electricity; Green technology; Sustainable development; Business analytics; Machine
learning; Energy transition; Explainable forecasting