<![CDATA[The effectiveness of social assistance programs depends heavily on the accuracy and transparency of beneficiary identification. In many urban areas, including Medan, challenges such as incomplete data, administrative bias, and inefficient targeting often lead to inclusion and exclusion errors in determining beneficiaries of the MBG (Makan Bergizi Gratis) program. This study aims to develop an explainable data-driven machine learning model to improve the accuracy and transparency of identifying eligible MBG program beneficiaries. The research employs a quantitative approach using socio-economic and demographic datasets collected from local government records, including variables such as household income, employment status, education level, household size, housing conditions, and access to public services. Several machine learning algorithms, including Random Forest, Gradient Boosting, and Logistic Regression, are implemented to classify potential beneficiaries. To enhance transparency and interpretability, the model integrates Explainable Artificial Intelligence (XAI) techniques, such as SHAP (Shapley Additive Explanations), to identify the most influential factors affecting eligibility predictions. The results demonstrate that the proposed data-driven model significantly improves the accuracy of beneficiary classification while providing interpretable insights into key socio-economic indicators influencing eligibility. The findings indicate that income level, employment status, household dependency ratio, and housing conditions are among the most critical determinants in identifying eligible recipients. The implementation of explainable machine learning models supports more transparent and accountable decision-making in social assistance programs. This research contributes to the development of data-driven governance by providing a robust analytical framework for improving the targeting efficiency of social welfare programs in urban areas. Practically, the proposed framework can assist policymakers and local government agencies in designing fairer and more efficient beneficiary identification systems for the MBG program in Medan City, ultimately supporting better resource allocation and improved social welfare outcomes.]]>
Copyrights © 2026
