A university has experienced persistent inefficiencies in its vehicle reservation system, with operational efficiencies of only 72.91% and 68.39% over the past two years, falling short of the 90% target. These inefficiencies, coupled with a driver shortage (driver-to-vehicle ratio of 4:11), have led to suboptimal resource allocation and increased operational costs. Specifically, the total cost of rented vehicle trips (₱12,128,223.00) was 162.02% higher than that of in-house trips (₱4,627,952.00), primarily due to manual vehicle and driver assignment processes. This study employed a mixed-method research approach integrating quantitative data analysis and qualitative insights to guide a data-driven solution. Three linear programming (LP) models were developed and embedded into a decision support system (DSS) using Excel VBA to optimize vehicle and driver allocation. Seasonal demand forecast revealed an optimal driver-to-vehicle ratio to minimize reliance on rented vehicles. Simulation results demonstrated that implementing the proposed DSS can significantly enhance system performance. The optimized model achieved full reservation processing (100% efficiency), reduced average trip reservation cycle time by 70.85%, improved vehicle utilization by 17.52%, and is projected to generate annual cost savings of ₱509,181.71. Overall, the integration of optimization modeling and decision automation effectively streamlines the reservation process, reduces user workload, and enhances operational efficiency.

Keywords

Linear Programming, Vehicle Reservation, Decision Support System, Monte Carlo Simulation