Student Performance Predictive Model with Machine Learning

Design a comprehensive predictive analytics pipeline using scikit-learn that forecasts individual student academic performance based on multidimensional input features. Develop a model that integrates historical academic records, demographic data, engagement metrics, and learning platform interactions. The solution should include feature engineering techniques, handle multicollinearity, implement cross-validation, and produce interpretable predictions with confidence intervals. Include a Flask-based dashboard that allows educators to input student data and receive real-time performance probability estimates.