🆔 UIDAI Aadhaar Analytics Dashboard

AI-Powered Analytics Platform for UIDAI Aadhaar Data with Predictive Insights

Features • Installation • Usage • Architecture • Team

---

📋 Overview

UIDAI Aadhaar Analytics is an intelligent dashboard designed for analyzing Aadhaar enrollment and update data across India. The platform combines Machine Learning predictions with Google Gemini AI to provide actionable insights for decision-makers at UIDAI.

✨ Features

📊 Interactive Dashboard

• Real-time visualization of Aadhaar statistics
• State-wise and district-wise analytics
• Trend analysis with interactive charts (Plotly)
• Dark/Light theme support

🤖 Predictive Analytics

• ML Model: Random Forest Regressor for demand prediction
• Model persistence (.pkl format) for reuse
• Prediction statistics with state-wise breakdown
• R² score and MAE metrics display

💬 AI-Powered Insight Chat

• Natural language query interface
• Dynamic Insights: Finding → Impact → Recommendation format
• Powered by Google Gemini AI
• Actionable suggestions generation

🎯 Smart Features

• Intent classification for relevant responses
• Auto-generated insights from predictions
• Context-aware AI analysis
• Responsive and modern UI

🚀 Installation

Prerequisites

• Python 3.9 or higher
• Google Gemini API Key

Setup

1. Clone the repository

   git clone https://github.com/Durvesh-dev/UIDAI_11297_NEXORA.git
   cd UIDAI_11297_NEXORA

2. Create virtual environment

   python -m venv venv

3. Activate virtual environment

   Windows:

   .\venv\Scripts\Activate.ps1

   Linux/Mac:

   source venv/bin/activate

4. Install dependencies

   pip install -r requirements.txt

5. Set Gemini API Key

   Windows PowerShell:

   $env:GEMINI_API_KEY = "your-api-key-here"

   Linux/Mac:

   export GEMINI_API_KEY="your-api-key-here"

6. Run the application

   streamlit run app.py

📖 Usage

Getting Started

1. Upload Dataset: Use the sidebar to upload your Aadhaar CSV file
2. Explore Dashboard: View interactive visualizations and statistics
3. Train Model: Navigate to "Predictive Model" page and click "Train Prediction Model"
4. Generate Predictions: Click "Generate Predictions" to see forecasts
5. Chat with AI: Ask questions in the "Insight Chat" page

Sample Questions for AI Chat

• "What do predictions show for high-activity states?"
• "What trends are predicted for next quarter?"
• "Which states need more enrollment centers?"
• "Analyze the update patterns in southern states"

🏗 Architecture

┌─────────────────────────────────────────────────────────────┐
│                      STREAMLIT APP (app.py)                  │
└─────────────────────────────────────────────────────────────┘
                              │
        ┌─────────────────────┼─────────────────────┐
        ▼                     ▼                     ▼
┌──────────────┐    ┌──────────────────┐    ┌──────────────┐
│  DASHBOARD   │    │ PREDICTIVE MODEL │    │ INSIGHT CHAT │
└──────────────┘    └──────────────────┘    └──────────────┘
                            │                      │
                            ▼                      ▼
                    ┌───────────────┐      ┌───────────────┐
                    │ model_utils.py│      │chat_engine.py │
                    └───────────────┘      └───────────────┘
                            │                      │
                            └──────────┬───────────┘
                                       ▼
                            ┌──────────────────────┐
                            │  gemini_helper.py    │
                            │    (Gemini AI)       │
                            └──────────────────────┘

📁 Project Structure

UIDAI_11297_NEXORA/
├── app.py                    # Main Streamlit application
├── model_utils.py            # ML model training & predictions
├── chat_engine.py            # AI chat query handler
├── gemini_helper.py          # Gemini AI integration
├── insights.py               # Analytics & insight generation
├── requirements.txt          # Python dependencies
├── ARCHITECTURE.md           # Detailed architecture docs
├── IMPLEMENTATION_SUMMARY.md # Implementation details
├── QUICK_START.md            # Quick start guide
└── README.md                 # This file

🛠 Tech Stack

Component	Technology
Frontend	Streamlit
Visualization	Plotly
ML Model	scikit-learn (RandomForest)
AI Engine	Google Gemini AI
Data Processing	Pandas, NumPy

👥 Team NEXORA

Team ID: 11297

Contributor	Role
Durvesh Bhadgaonkar	Developer
Swapnil Surendra Kasare	Developer
Hassaan Tole	Developer
Vansh Jindam	Developer
Sarvesh Deshmukh	Developer