SMS 4: FACULTY MANAGEMENT SYSTEM WITH ADAPTIVE SCHEDULING USING MACHINE LEARNING

Abstract

This capstone project presents the development of SMS 4: Faculty Management System with Adaptive Scheduling Using Machine Learning. The system addresses ongoing challenges in academic scheduling and faculty resource allocation at Bestlink College of the Philippines. Traditional manual scheduling methods often result in conflicts, inefficiencies, and limited flexibility in accommodating faculty preferences and institutional requirements. SMS 4 integrates machine learning algorithms to analyze historical data—such as faculty availability, course demand, and enrollment trends—to generate conflict-free schedules that adapt to real-time changes. The study adopted the Agile Scrum methodology to guide the iterative development of the system. Its adaptive framework enabled continuous feedback from stakeholders and division of work into multiple development sprints. Each sprint focused on delivering key features, including faculty profile management, adaptive scheduling algorithms, real-time notifications, and system integration. This approach ensured flexibility, responsiveness, and alignment with user needs throughout the development process. The Faculty Management System, powered by machine learning, significantly improved scheduling efficiency by generating conflict-free timetables. It reduced administrative workload, resolved scheduling conflicts, and improved adaptability to shifting academic demands. The inclusion of real-time updates and notifications, along with consideration of faculty preferences, enhanced overall user satisfaction and operational responsiveness. The implementation of SMS 4 addressed longstanding issues in academic scheduling by replacing manual processes with an automated, intelligent system. The integration of machine learning enabled dynamic adaptation to real-time faculty availability, course requirements, and institutional constraints, resulting in fairer and more accurate schedules. This not only optimized resource allocation but also minimized administrative effort. Moreover, the user-friendly interface allowed faculty members to input preferences, which the system actively considered, leading to increased faculty satisfaction and engagement. The system demonstrates the potential of machine learning in educational management and paves the way for broader adoption of intelligent scheduling solutions.