Leveraging Recommender Systems to Tailor Moocs for Student Needs: A Data-Driven Approach

Abstract

Massive Open Online Courses (MOOCs) have revolutionized education by providing widespread access to diverse learning opportunities. However, the vast array of available courses poses a challenge for students in selecting the most suitable ones. This research leverages recommender systems to understand students' requirements and recommend appropriate MOOCs programs. Using an open dataset from the Open University Learning Analytics Dataset (OULAD), we develop a model incorporating student demographics, past performance, and engagement metrics to predict and recommend suitable MOOCs. We implement and compare two classification algorithms—Random Forest and Support Vector Machine (SVM)—to assess their predictive accuracy. Results indicate that the recommender system significantly enhances course selection by aligning recommendations with student profiles, thus improving educational outcomes.