Exploring the Learning Analytics of Skill-Based Course using Machine Learning Classification Models

This study explores learning analytics of a skill-based course using various machine learning classification models, including Random Forest, Logistic Regression, CatBoost, Support Vector Classification (SVC), and Naïve Bayes. The objective is to categorize student outcomes into four classes: Pass, Distinction, Withdrawn, and Fail. These models are trained and validated using historical data from students who previously enrolled in the course, encompassing their engagement levels, assessment scores, and other relevant features that influence learning outcomes. Comparative analysis reveals that each model exhibits unique strengths in predicting different outcome classes, providing valuable insights into student performance and the efficacy of the instructional design. The findings from this investigation offer educators and academic institutions a robust framework for early identification of students at risk of underperformance or withdrawal, thereby enabling timely intervention to enhance student success in skill-based courses. Furthermore, the research contributes to the growing body of knowledge in learning analytics and machine learning applications in education, showcasing the potential of these technologies in fostering a supportive and adaptive learning environment for diverse student populations. 

 Keywords: Random Forest, Logistic Regression, CatBoost, Support Vector Classification (SVC), and Naïve Bayes.