ABSTRACT

Technology has been driving digitalization and automation across various domains, including educational institutions. This study utilized data mining techniques, specifically Association Rule Mining and Cluster Analysis, to enhance strategic planning and event management practices within the Paulinian Student Government (PSG) of St. Paul University System schools in the Philippines. By analyzing evaluation data from 2018 to 2023, the research uncovered patterns and trends associated with event success, highlighting logistical strengths, skilled facilitation, and alignment between event objectives and outcomes. Methods included descriptive and developmental research, with clustering and association rule analysis providing actionable insights into attendee satisfaction. Key findings revealed that highly rated events shared characteristics such as effective communication and logistical coordination, while poorly rated activities often suffered from inadequate planning and engagement. Cluster analysis categorized events into low, moderate, and high satisfaction groups, guiding targeted recommendations for improvement. Evaluations against ISO 25010 Software Quality Standards confirmed the developed system’s high compliance, ensuring reliability, usability, and scalability. The study concluded that data mining effectively optimizes event management, fostering a more impactful PSG program. It recommends addressing logistical weaknesses in low-rated events, enhancing interactive elements for moderately rated activities, and institutionalizing best practices from high-rated events. Visual analytics and continuous data monitoring are encouraged for sustained improvement and alignment with student needs.

Keywords: Data mining; student activities; educational institutions; teaching enhancement; machine learning; student development programs; educational management; predictive analysis;
https://doi.org/10.57180/gpde2791