Skip to content

This gold price prediction system is a web app for pawning centers to forecast future gold prices and manage pawned items. Using Facebook Prophet, it predicts prices in USD and LKR for 3, 6, and 12 months. Built with React, Node.js, and Flask, it supports user authentication, interest calculations, expiry tracking, and efficient pawn management.

Notifications You must be signed in to change notification settings

prashankulathunga/GOLD_PRICE_PREDICT-SYSTEM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Gold Market Price Prediction System for Pawning Centers

A full-stack web application designed for pawning shops to predict future gold prices and manage pawned items efficiently. This system leverages machine learning for price forecasting and offers features tailored to the pawning industry.


🚀 Project Overview

The GOLD PRICE PREDICT SYSTEM integrates a React.js frontend with two backend APIs:

  • Node.js API: Handles user interactions, authentication, and database operations.
  • Python Flask API: Loads a pre-trained Prophet model (serialized using Pickle) to provide gold price predictions.

The application supports both USD and LKR currencies and offers predictions for 3, 6, and 12 months.


🧠 Machine Learning Model

  • Model Used: Facebook Prophet
  • Performance: Achieved a Mean Absolute Error (MAE) of 19.68.
  • Functionality: The model forecasts future gold prices based on historical data, aiding users in making informed decisions.

🛠️ Technologies Used

  • Frontend: React.js
  • Backend:
    • API 1: Node.js (Express)
    • API 2: Python Flask
  • Database: MySQL
  • Machine Learning: Facebook Prophet
  • Serialization: Pickle (for model storage)

🔑 Key Features

  • Gold Price Predictions:
    • 3-month forecast
    • 6-month forecast
    • 12-month forecast
  • Advanced Pawning Mechanism:
    • Automated interest calculations
    • Expiry date tracking
    • Redemption status updates
  • Currency Support:
    • Toggle between USD and LKR
  • User Management:
    • Authentication and authorization
    • User roles and permissions

🏦 Target Audience

This system is tailored for pawning shops seeking to:

  • Predict future gold prices to set competitive rates.
  • Automate and manage pawned items efficiently.
  • Offer customers insights into potential future valuations.

📂 Project Structure

GOLD_PRICE_PREDICT-SYSTEM/
├── FullProject/
│   ├── frontend/          # React.js application
│   ├── backend-node/      # Node.js API
│   └── backend-flask/     # Python Flask API
└── OtherThings/           # Additional resources and documentation

⚙️ Installation & Setup

  1. Clone the Repository:

    git clone https://github.com/prashankulathunga/GOLD_PRICE_PREDICT-SYSTEM.git
    cd GOLD_PRICE_PREDICT-SYSTEM/FullProject
  2. Setup Backend (Node.js):

    cd backend-node
    npm install
    npm run dev
  3. Setup Backend (Flask):

    cd ../backend-flask
    pip install -r requirements.txt
    python main.py
  4. Setup Frontend (React.js):

    cd ../frontend
    npm install
    npm run dev

Ensure that MySQL is installed and running. Update the database configuration in the Node.js backend as needed.


📈 Usage

  • Access the application via http://localhost:3000.
  • Navigate through the dashboard to view predictions and manage pawned items.
  • Use the currency toggle to switch between USD and LKR.

🤝 Contributing

Contributions are welcome! Please fork the repository and submit a pull request for any enhancements or bug fixes.


For more details, visit the GitHub Repository.

About

This gold price prediction system is a web app for pawning centers to forecast future gold prices and manage pawned items. Using Facebook Prophet, it predicts prices in USD and LKR for 3, 6, and 12 months. Built with React, Node.js, and Flask, it supports user authentication, interest calculations, expiry tracking, and efficient pawn management.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published