Machine Learning

Student Dropout Prediction Using Machine Learning

The Student Dropout Prediction Using Machine Learning system is a comprehensive machine learning solution that predicts student dropout risk using demographic, academic, and socioeconomic factors. This project is ideal for B.Tech, MCA, CSE, and engineering students as their final year project. It uses advanced algorithms like Logistic Regression and Naive Bayes with SMOTE to achieve 82.3% accuracy.

The system leverages 36 features including demographic information, academic performance indicators, and economic factors. It provides interactive visualizations, feature importance analysis, model comparison, and real-time dropout prediction to help educational institutions identify at-risk students early and implement proactive intervention strategies.

• Multi-Class Dropout Prediction
• Logistic Regression (82.3% Accuracy)
• Naive Bayes (76.8% Accuracy)
• SMOTE for Class Imbalance
• Feature Importance Analysis
• Real-time Risk Prediction
• Model Performance Comparison
• Interactive Visualizations
• 5-Fold Cross-Validation
• Flask Web Application