Open University Learning Analytics Dataset Project

• keywords: Supervised Learning, Learning Analytics, Machine Learning Models, Educational Data Mining
• Github URL: Project Link

This individual project was a midterm project for coursework STAT542(Statistical Learning) at UIUC(SP2024). The original datasets consist of seven datasets used in this project, containing information about courses, students, and their interactions with the virtual learning environment (VLE) across seven selected courses (modules). Specifically, the datasets include demographic information about students (gender, age, IMD, region, highest education, disability), behavioral data (number of clicks and views by material), and assessment data (homework submission dates, scores). The goal of this project is to predict the students’ success and failure in online courses and identify those who are at risk of failure or withdrawal, using the supervised learning models.