Abstract
Urban mobility systems are rapidly evolving, compelling government transport operations to adopt digital technologies that meet increasing demands for efficiency, reliability, and transparency. Persistent challenges such as monitoring Public Utility Vehicle (PUV) availability, managing franchise and route data, and forecasting commuter demand highlight the need for an integrated, data-driven solution. This study presents the Government Service Transport & Mobility Management System with Predictive Analytics for PUV Demand Forecasting, developed to enhance transport governance and operational efficiency. The study employed a mixed-methods approach, incorporating stakeholder interviews with transport officers and Local Government Unit (LGU) personnel to capture operational requirements and implementation insights. System development followed the Agile Scrum methodology, enabling iterative cycles of planning, design, development, testing, and deployment to ensure adaptability and responsiveness. The system provided real-time monitoring, centralized reporting, predictive-demand functions, and tools for vehicle deployment and route management. The platform illustrates how predictive analytics may support proactive transport planning and integrated mobility management. Training and technology-adoption barriers remain relevant. Claims of reduced waiting time, congestion mitigation, and improved trust require operational data and comparative evaluation.
