Machine Learning System for Predicting Student Suitability for University Courses

Abstract

The accuracy of student-course predictions determines both university learning success and career guidance process. When selecting students for courses using conventional methods universities fail to weigh all important factors which results in mismatching student-enrollment decisions. This research constructs a web-based machine learning framework to assess which university classes students would succeed in through fundamental attributes. The research conducts its analysis using background and academic data obtained from 2000 Taraba Secondary School students. The primary targets of this project involve understanding the course suitability determinants among students followed by building a machine learning model and creating a web-based interface and conducting a test on model effectiveness. Three machine learning algorithms—Random Forest, Decision Tree, and Support Vector Machine (SVM). A 95% accuracy emerged as the best outcome from using Random Forest whereas Support Vector Machine (SVM) achieved 93% accuracy and Decision Tree produced 92%. The predictive abilities for matching students to academic courses improve significantly through implementing machine learning algorithms. Students obtain automatic recommendations immediately after entering their student data on the platform. The new student guidance system shows students to proper courses ahead of time thus reducing curricular mismatches and boosting their academic outcomes. Future researchers must build adaptive learning models and real-time data updating functions to enhance accuracy and scalability levels in their work.