Academic Performance Prediction from Study Habits and Lifestyle using Linear Regression

Academic performance is a critical indicator of student success in higher education, influenced by factors such as study habits, sleep patterns, and extracurricular engagement. This study presents a web-based application developed using the Streamlit framework and a linear regression model to predict students’ academic Performance Index based on key predictors, including previous grades, study hours, sleep duration, practice question engagement, and extracurricular activities. Utilizing a dataset from Kaggle with 10,000 student entries, the model achieved a high R-squared (R²) value of 0.9890 and a low Mean Squared Error (MSE) of 4.0826, indicating robust predictive accuracy. The application provides interactive visualizations of factor contributions and performance categories (High, Medium, Low) to support students in identifying strengths and weaknesses in their learning strategies. This study contributes to educational technology by offering a practical, data-driven tool for personalized academic improvement.