Student Performance Prediction Using Machine Learning

Student performance prediction is an important application of machine learning that can help educational institutions identify factors affecting academic achievement and provide timely support to students. This study, titled “Student Performance Prediction Using Machine Learning,” aims to develop and evaluate machine learning models for predicting students’ academic performance based on academic, personal, and learning-related factors. The study utilizes the open-source UCI Student Performance Dataset, collected from secondary school student reports, supplemented with custom-generated mock features representing online Learning Management System (LMS) engagement. The input features include age, gender, attendance, study hours, previous scores, sleep hours, tutoring, internet access, parent education, extracurricular activities, study time, past class failures, absences, and LMS login frequency. The study considers two possible target variables: final grade, represented as a continuous score from 0 to 100, and student status, classified as Pass or Fail. Four machine learning algorithms—Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine (SVM)—will be implemented and compared to determine their predictive performance. The models will be evaluated using appropriate performance metrics to identify the most effective approach for student performance prediction. The expected outcome is to demonstrate how machine learning can utilize student-related data to predict academic outcomes and support early identification of students who may require additional academic assistance. This research contributes to the use of data-driven techniques in education and provides a foundation for developing more effective student monitoring and academic support systems.

17 Aug 2026 0 98