A Data-Informed, Rule-Based Decision-Support Framework for School Complex Facility Planning: Integrating Demographics, Surrounding Facilities, and Local Context

This study develops a data-informed, rule-based decision-support framework for the preliminary planning of school complex facilities in response to demographic changes and spatial imbalances in public facility provision. Rather than predicting actual facility demand, the framework integrates administrative-unit-level demographic indicators with school-centered information on surrounding facilities to compare and screen potentially suitable facility types. Facility types already present within the school or meeting a predefined local-duplication threshold within the 500 m catchment are excluded from the preliminary candidate set, while facility types associated with comparatively high demographic need and limited surrounding provision are given higher priority. The framework was implemented using Python and Streamlit. The proposed framework was applied to all 81 school complex facility projects designated in 2023 and 2024. Among these, six cases—two urban schools, two rural schools, and two closed-school sites—were selected to illustrate the analytical process and results in greater detail. The application results indicate that schools within the same administrative district may yield different facility priorities because of differences in their school-centered surrounding-facility conditions, while variations across districts reflect both demographic and facility-related conditions. These findings highlight the limitations of relying solely on uniform, district-based planning criteria and illustrate the potential value of supplementing administrative-unit-level demographic indicators with school-centered assessments of surrounding facility conditions. This study contributes to school complex facility planning by providing a transparent and systematic rule-based decision-support framework for preliminary screening and comparative prioritization at the school level.