This study aims to analyze the utilization of big data in regional development planning as a strategy to strengthen evidence-based policy in local government. The research focuses on how big data can support development program planning, poverty reduction, social assistance targeting, and basic-service improvement. This study uses a qualitative method with an exploratory-descriptive approach and conceptual framework development. Data were collected from secondary and documentary sources, including recent peer-reviewed journal articles, policy documents, institutional reports, regional planning materials, and regulatory documents related to big data, digital governance, evidence-based policy, local development planning, poverty alleviation, and public services. The data were analyzed using thematic analysis by classifying the findings into several themes: data integration, evidence-based program formulation, poverty and vulnerability mapping, social assistance targeting, basic-service improvement, institutional readiness, data governance, and public accountability. The findings show that big data can improve regional planning by integrating population records, poverty databases, social assistance data, geospatial information, public-service indicators, village-level data, citizen complaints, and digital feedback. The study contributes by proposing an evidence-based local development planning framework consisting of five dimensions: data integration, analytical interpretation, program prioritization, accountable implementation, and continuous evaluation. This framework emphasizes that big data must be supported by institutional coordination, analytical capacity, ethical safeguards, public participation, and accountable governance to produce more accurate, inclusive, and responsive local development policies.