Automated Student Performance Risk Detection System

Design a Python-based predictive analytics pipeline using pandas and scikit-learn that automatically identifies students at academic risk by analyzing multiple data sources: gradebook entries, attendance records, learning management system interaction logs, and assessment scores. The system must generate weekly risk reports, categorize students into risk tiers (low/medium/high), and automatically trigger personalized intervention recommendations. Include machine learning models that can predict potential dropout probabilities with at least 85% accuracy.