Abstract
Outcome-based Education (OBE) is a student-centered strategy that focuses on students' performance in terms of knowledge, skills, and attitude to address academic gaps. Educational Data Mining (EDM) utilizes artificial intelligence and machine learning to analyze student data and boost academic achievements. Experimenting with student academic data of 397 first-year students of Mehran University of Engineering and Technology, covering nine courses and spanning two semesters, this research proposes a prediction mechanism to help anticipate student academic outcomes at an early stage during their university degree. The aim of this research is threefold. First, an exploration of EDM-based classification to predict OBE-based Program Learning Outcome (PLO) attainment. Second, the investigation of imbalanced class distribution and the benefits of using the Synthetic Minority Over-Sampling Technique on educational data. Third, a comprehensive performance evaluation of eleven classifiers is explored in this research. The evaluation entailed the use of accuracy, Kappa, recall, and precision to assess classifier performance on both balanced and unbalanced class distributions. Although several classifiers were found to be competent in handling educational data for OBE-PLO prediction, the Random Forest exhibited superior performance with an accuracy of 76.88% and a Kappa score of 0.727.