This is a WhatsApp Expense Tracker chatbot built using Rasa that allows users to record and query their expenses efficiently. The bot uses NLP techniques, a database for expense storage, and integrates with Twilio for WhatsApp messaging.

📌 Expense Recording: Users can log their expenses with categories, amounts, and descriptions.
🏷 Category Classification: Uses NLP (Zero-shot learning & NER) to categorize expenses.
🔍 Expense Querying: Retrieve expenses based on date, category, or both.
📊 Insights & Summaries: Provides a breakdown of expenses by category.
💾 SQLite Database: Persistent storage for expense records.
📡 Twilio Integration: Send and receive messages via WhatsApp.

• Rasa: NLP-powered chatbot framework
• Twilio API: WhatsApp messaging
• SQLite: Lightweight database
• Transformers (Hugging Face): Zero-shot classification & NER
• Python: Core backend logic
• Logging: Debugging and monitoring

bash git clone https://github.com/your-repo/whatsapp-expense-tracker.git cd whatsapp-expense-tracker

Create a virtual environment and install required Python packages. bash python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate pip install -r requirements.txt

• Sign up at Twilio
• Get your Account SID, Auth Token, and WhatsApp Number
• Update credentials.yml with Twilio credentials

bash rasa train

In separate terminals, run: bash rasa run --enable-api rasa run actions

Send a message like: plaintext I spent $20 on Starbucks coffee yesterday.

💾 The bot extracts amount, category, and date automatically.

Ask questions like: plaintext How much did I spend on coffee this week? Show me my expenses for yesterday.

📊 The bot fetches relevant data from the database.

📌 Dashboard for visualization
📉 Expense trend analysis
🗣 Voice-based interaction support
🏦 Bank statement auto-categorization

👨‍💻 Your Name - GitHub

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