AI Expense Tracker & Financial Advisor

An intelligent expense tracking system that uses OCR technology and AI-powered analysis to extract insights from receipts and provide personalized financial recommendations.

Features

Receipt Processing

• OCR text extraction from images and PDFs
• Multi-format support (JPG, PNG, PDF, WebP)
• Intelligent expense parsing and categorization
• Confidence scoring for data accuracy

AI-Powered Analysis

• Automatic expense categorization
• Spending pattern recognition
• Anomaly detection for unusual expenses
• Trend analysis across time periods

Financial Insights

• Personalized budget recommendations
• Money-saving opportunity identification
• Spending health assessment
• Goal tracking and progress monitoring

Interactive Dashboard

• Real-time expense visualization
• Category and merchant breakdowns
• Interactive charts and graphs
• Data export functionality

Installation

1. Clone the repository:

git clone https://github.com/chintanparekh2510/ai-expense-tracker.git
cd ai-expense-tracker

2. Install dependencies:

pip install -r requirements.txt

3. Set up environment variables:

cp .env.example .env
# Edit .env with your OpenAI API key

4. Install Tesseract OCR:

• Windows: Download from GitHub
• macOS: brew install tesseract
• Linux: sudo apt-get install tesseract-ocr

Quick Start

1. Run the web application:

streamlit run src/app.py

2. Open your browser to http://localhost:8501

3. Upload receipt images and view AI-generated insights

Project Structure

ai-expense-tracker/
├── src/
│   ├── ocr/              # Receipt processing and text extraction
│   ├── analysis/         # Expense analysis and pattern recognition
│   ├── advisor/          # AI budget recommendations and insights
│   ├── utils/            # Data handling and visualization utilities
│   └── app.py            # Main Streamlit application
├── data/
│   ├── sample/           # Sample data for testing
│   ├── receipts/         # User uploaded receipts
│   └── statements/       # Bank statements
├── tests/                # Unit tests
└── docs/                 # Documentation

Configuration

Environment Variables

OPENAI_API_KEY=your_openai_api_key_here
TESSERACT_PATH=/usr/bin/tesseract
OCR_LANGUAGE=eng
MAX_FILE_SIZE_MB=10

Supported File Formats

• Images: JPG, JPEG, PNG, WebP, BMP, TIFF
• Documents: PDF

Usage Examples

Command Line Analysis

from src.ocr.receipt_processor import ReceiptProcessor
from src.analysis.expense_analyzer import ExpenseAnalyzer

# Process receipt
processor = ReceiptProcessor()
results = processor.process_file("receipt.jpg")

# Analyze expenses
analyzer = ExpenseAnalyzer()
analyzer.add_expenses_batch(results)
summary = analyzer.get_spending_summary()

Web Interface

The Streamlit application provides:

• File upload interface
• Real-time processing feedback
• Interactive visualizations
• Export functionality

API Reference

OCR Module

• ReceiptProcessor: Main OCR processing class
• TextParser: AI-powered text parsing and structuring

Analysis Module

• ExpenseAnalyzer: Core analysis engine
• SpendingInsight: Insight data structure
• SpendingTrend: Trend analysis results

Advisor Module

• BudgetAdvisor: AI budget recommendations
• InsightsGenerator: Personalized financial tips

Testing

Run the test suite:

python -m pytest tests/

Run demo analysis:

python demo.py

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests for new functionality
5. Submit a pull request

License

This project is licensed under the MIT License. See the LICENSE file for details.

Technical Requirements

• Python 3.11+
• OpenAI API access (for AI features)
• Tesseract OCR installation
• 4GB+ RAM recommended
• CUDA GPU (optional, for enhanced processing)

Performance

• OCR Processing: ~2-5 seconds per receipt
• AI Analysis: ~1-3 seconds per expense
• Batch Processing: Supports multiple files
• Memory Usage: ~200MB base, +50MB per 1000 expenses

Support

For technical support or questions about implementation, please open an issue on GitHub.

Author

Created by Chintan Parekh - X | GitHub

Acknowledgments

• OpenAI for GPT-4 API
• Tesseract OCR project
• Streamlit framework
• Python data science ecosystem