A smart bookkeeping system leveraging AI to extract financial insights and forecast demand dynamically.
This project is an AI-powered bookkeeping and demand forecasting system designed to automate financial record-keeping and optimize inventory management. It extracts key financial entities from transactions and predicts product demand based on historical sales data.
- Automatic entity extraction from transaction statements
- Demand forecasting based on sales trends
- Real-time alerts for low stock levels
- Simple API endpoints for seamless integration
Here are some images related to the project:
-
Transaction Data Extraction
Extracts key details like customer names, item quantities, and prices from financial records.curl -X POST http://127.0.0.1:5000/extract -H "Content-Type: application/json" -d "{\"text\": \"John Doe bought 2 apples for $5\"}"
{"CustomerName":"John Doe","ItemName":"apples","ItemQuantity":"2","Price":"5"}
-
Natural Language Processing for Entity Recognition
Recognizes actionable insights from textual inputs.curl -X POST "http://127.0.0.1:5000/extract_entities" -H "Content-Type: application/json" -d "{\"text\":\"apples less than 50 rs\"}"
{"action":"less","object":"apples","range":"50"}
-
Demand Forecasting
Uses historical data to predict when stock levels are running low and suggests reorder points.
- Docker installed on your system
docker-compose up --build
docker-compose up
# Replace with actual endpoint and input data
curl -X POST <api_endpoint> -H "Content-Type: application/json" -d '<input_data>'
Souvik Mahanta |
Made with ❤ by GDSC-VIT