Enterprise Student Analytics & Anomaly Detection Engine Overview This platform is a decoupled, highly scalable analytics engine designed to identify "at-risk" students and institutional anomalies using advanced Association Rule Mining (ARM). ��️ Technical Architecture  Frontend: Streamlit interactive UI.  Backend Processing: Python, Pandas, NumPy.  Algorithmic Engine: Mlxtend (Dynamic switching between FP-Growth and Apriori based on dataset load).  Visualizations: Plotly Express for multi-dimensional data mapping. �� Key Engineering Features

1. Dynamic Anomaly Detection: Identifies "Uncovered Students" (those escaping all rule sets) and "Exception Records" (those breaking predicted conditional logic).
2. Regex Column Normalization: An adaptive ingestion layer that standardizes messy CSV headers using regular expressions.
3. Scalable Mining: Automatically shifts to FP-Growth tree structures for datasets exceeding 2,500 rows to bypass the O(2^d) bottleneck of standard Apriori matrix scans. �� How to Run Locally
4. pip install -r requirements.txt
5. py -m streamlit run student_web_app.py