Academic Performance Prediction Using a Hybrid Machine Learning Framework

Abstract

The fast-paced growth in educational technology and data science has paved the way for machine learning methods to assess student performance. Educational data mining (EDM) combines data mining, machine learning, and deep learning to improve the learning experiences of students. This paper delves into how we can categorize students based on their performance and suggests a tailored recommendation system for personalized learning. Using historical academic data from the UC Irvine Machine Learning Repository, the study identifies crucial factors that contribute to student success. By examining learning patterns, the research seeks to forecast student academic performance and offer valuable insights for enhancing educational outcomes.