Advanced Student Performance Predictive Analytics Pipeline

Design a comprehensive Python-based machine learning pipeline using pandas and scikit-learn that predicts student academic performance across multiple dimensions. The system should integrate historical grade data, attendance records, extracurricular involvement, and socioeconomic indicators. Create a modular architecture that allows dynamic feature engineering, handles missing data gracefully, and generates interpretable model insights with SHAP values. Include a Flask-based dashboard for administrators to interact with predictive outputs and confidence intervals.