Hypertension is a major health issue in DKI Jakarta requiring efficient resource distribution to overcome inter-regional access inequalities. This research aims to design and implement a web-based decision support system (DSS) integrating Geographic Information System (GIS) to optimize health worker allocation and determine hypertension priority areas precisely. The novelty lies in integrating a Random Forest machine learning model to predict service coverage until 2030 with Content-Based Filtering (CBF). The CBF method utilizes intrinsic regional features, including service percentages, geographical locations, and prediction trends, to generate objective health worker quota recommendations. The Random Forest model was validated using 5-Fold Cross Validation with excellent performance, showing an average R² value of 0.86 and an accurate Mean Absolute Error (MAE) of 6.7%. The system is implemented using Streamlit and Folium frameworks for geographical visualization. Research results provide contributions through priority area maps, adaptive health worker quota recommendations, and Mobile Health Clinic route simulations supporting data-driven decision-making. Through this system, policymakers can perform strategic planning to improve hypertension intervention effectiveness in Jakarta. With an integrated predictive and recommendation approach, this study is expected to become a reference in the digital transformation of public health resource allocation more equitably and accurately.