Universal Basic Income (UBI) has been considered a potential policy tool for reducing poverty and improving financial security particularly during times of crisis. The COVID-19 pandemic underscored the fragility of financial systems, prompting mechanisms like UBI. In Bangladesh, a country facing significant wealth inequality and economic challenges, assessing the long-term fiscal feasibility of UBI is critical. This study examines the fiscal feasibility of implementing Universal Basic Income (UBI) in Bangladesh through machine learning techniques. By applying XGBoost regression to analyze Bangladesh’s macroeconomic indicators under varying UBI scenarios (1%, 3%, and 5% of GDP). This analysis demonstrates robust predictive capability, achieving 90% accuracy and R2 score of 0.78. SHAP (SHapley Additive exPlanations) analysis further identifies GDP growth, tax revenue, and debt-to-GDP ratio as critical determinants of UBI sustainability. This study represents a pioneering application of machine learning for UBI feasibility assessment in Bangladesh, providing a framework for similar analyses in developing economies.