Utilizing Descriptive and Predictive Analytics in Student Disciplinary Infractions at St. Paul University Philippines

Maintaining institutional discipline is a critical aspect of fostering a positive and values-oriented academic culture. However, traditional approaches to student conduct tracking are often reactive and descriptive at best. This research explores how descriptive and predictive analytics can be leveraged to evaluate and anticipate student disciplinary infractions at St. Paul University Philippines. The primary aim is to identify patterns and behavioral trends using historical data, then apply predictive models to support proactive interventions and improve decision-making in the Office of Student Affairs and Academic Support Services (SAASS). The study uses a combination of descriptive statistical tools and predictive modeling techniques, including decision trees and logistic regression, to analyze anonymized discipline records. These models will help forecast the likelihood of future infractions based on variables such as type of offense, frequency, academic year level, and department. The outcomes are expected to reveal behavioral risk indicators and generate visual dashboards that enable dynamic data interpretation for policy enhancement. The use of analytics in managing student behavior introduces a transformative strategy for higher education institutions. It not only supports early detection and prevention but also equips school administrators with actionable insights. The study ultimately aims to contribute to a more intelligent and data-informed student discipline framework within the university setting.