<![CDATA[This study explores the predictive modeling of the Education Index (EI) using a dual approach using Random Forest and Multiple Linear Regression (MLR). The data, obtained from "Our World in Data" spanning 1990–2022, integrates socio-economic and infrastructure indicators, including GDP per capita, government spending on education, and access to electricity. This study includes 20 countries that are categorized by income level: Low-Income (Vietnam, Nepal, Myanmar, Pakistan, Zimbabwe), Lower-Middle-Income (Ghana, Bolivia, Cambodia, Egypt, Bangladesh), Upper-Middle-Income (Argentina, Brazil, Peru, Russia, Mexico) and High-Income (Germany, Italy, Portugal, Iceland, Greece). The analysis reveals that Random Forest outperforms MLR in terms of accuracy and lower error rates, while MLR provides better interpretability of variable relationships. With R2 of 99.34% by Random Forest Regression and 94% by Multiple Linear Regression (MLR). Key findings reveal that GDP per capita, primary and secondary completion rates, and internet usage significantly influence EI, underscoring the importance of economic conditions and infrastructure for educational outcomes. This study contributes to the field by offering comparative insights into machine learning and traditional statistical methods for educational analytics, providing a robust basis for policy development to enhance global education standards.]]>
Copyrights © 2026
