Students Performance Prediction Web Application

Student performance prediction is essential for early identification of struggling students and personalized learning interventions. This research presents a Machine Learning (ML)-based approach to predict student performance using factors like attendance, previous exam grades, study hours, motivation, and assignment completion. We implemented Decision Tree, Random Forest, and Logistic Regression models to classify students into performance levels (Low, Medium, High) or Pass/Fail categories. The dataset was collected through Google Forms and pre-processed to handle missing values and normalize numerical data. The results indicate that Random Forest provides the best accuracy, and attendance and previous exam scores are the most influential factors. The findings demonstrate how ML can help educators track student progress and offer personalized academic support. 2.