Welcome to Attendance AI
Monitor student attendance, identify academic risk, and support data-driven decisions using Neon PostgreSQL and machine learning.
Loading live data...
AI Risk Distribution
Live prediction categories from Neon PostgreSQL.
Priority Risk Alerts
Students currently requiring attention.
Recent Student Records
| ID | Student | Department | Attendance | Risk |
|---|
Student Management
| ID | Student | Department | Attendance | Internal | Assignment | Risk | Confidence | Actions |
|---|
AI Risk Prediction Engine
Random Forest classification using attendance, internal marks, assignment performance, and previous-performance input.
| ID | Student | Attendance | Internal | Assignment | Prediction | Confidence | History |
|---|
Department-wise Average Attendance
Calculated from current student records.
Risk Category Breakdown
Academic Performance Insights
Attendance Improvement Simulator
Calculate how many consecutive future classes a student must attend to reach a target attendance percentage.
Smart Risk Monitoring
Students with HIGH or MEDIUM predictions are listed below. These are current risk indicators, not automatic notifications.
Technology Stack
Backend: Python Flask
Database: Neon PostgreSQL
Machine Learning: Random Forest
ML Library: Scikit-learn
Frontend: HTML, CSS, JavaScript
Containerization: Docker
Backend Hosting: Railway
Frontend Hosting: Cloudflare Pages
Prediction Categories
LOW Lower predicted risk
MEDIUM Moderate predicted risk
HIGH Higher predicted risk
Predictions come from a demonstration ML model and are not validated academic outcomes.
This dashboard requires administrator authentication. Protected API requests use an expiring Bearer token.