This study develops a machine learning–optimized framework for evaluating socioeconomic and environmental factors to enhance sustainable development in the Philippines. As one of the most climate-vulnerable nations, the country faces compounding challenges, including economic inequality, environmental degradation, and resource scarcity. These issues require data-driven strategies that integrate environmental, economic, and social dimensions. This research applies Random Forest and Gradient Boosting ensemble algorithms to overcome the limitations of traditional sustainability evaluation methods based on linear analyses. By capturing nonlinear relationships, handling multicollinearity, and processing high-dimensional datasets, the proposed framework identifies and prioritizes key sustainability indicators that most significantly influence policy and technology outcomes. The study utilizes historical datasets from national and international sources, encompassing metrics such as GDP growth, energy production, CO2 emissions, HDI, Gini coefficient, unemployment rates, and access to clean water. Model performance was evaluated using R2 and RMSE, with results of R2 = 0.915534 and RMSE = 0.566654, demonstrating strong predictive validity. Findings reveal that the integration of machine learning enables the synthesis of complex datasets into actionable, forward-looking insights that can guide evidence-based policy formulation, resource allocation, and sustainable technology adoption. These insights support balanced decision-making that fosters environmental stewardship, economic resilience, and social equity. Beyond the Philippine context, the framework offers scalability and adaptability for application in other developing nations confronting similar sustainability challenges. The study contributes to the global discourse on leveraging artificial intelligence for sustainable development by demonstrating its capacity to support the United Nations Sustainable Development Goals (SDGs) through enhanced data-driven governance and resilient socio-environmental systems.

Keywords: Machine Learning, Ensemble Learning, Sustainability Assessment, Socioeconomic Modelling, Environmental Indicators, Sustainable Development Goals, Policy Evaluation Random Forest, Gradient Boosting