Student Performance Analysis based on Machine Learning Algorithms

Abstract

This research paper presents a rule-based recommender system for analyzing and forecasting student performance in education. The proposed framework utilizes demographic data, academic abilities, and psychological characteristics of the students to identify areas for improvement and provide helpful recommendations for optimizing their academic outcomes. The study focuses on popular machine learning algorithms and evaluates their effectiveness in predicting student performance based on multiple criteria. The findings demonstrate that the proposed framework has better performance in comparison to those currently in use in terms of predictive power.