🛒 Sales Forecasting Web App

A machine learning-powered web application that forecasts sales using XGBoost and ARIMA and Django

---

🚀 Features

• ML-Powered: Predicts sales using a trained XGBoost Regressor and ARIMA
• Django Web App: Backend powered by Django framework
• Feature Importance: Used Mysql to store the values predicted values generated by the model
• Feature Importance: Auto-generated plots of feature impact
• Sales Denormalization: Uses pre-saved scalers to return original sales values
• Modern UI: Responsive interface (supports Dark Knight theme 😎)

---

🧠 Model Details

• Model: XGBoost Regressor
• Scaler: MinMaxScaler or StandardScaler (via joblib)
• Target: Item_Outlet_Sales
• Features: Encoded and cleaned dataset columns

---

📁 Project Structure

sales_forecasting/
├── app/
│   ├── templates/
│   │   └── view/
│   │       └── predict.html
│   ├── views.py
│   ├── urls.py
│   └── ...
├── static/
│   └── images/
│       └── dark_knight.jpg
├── model/
│   ├── xgboost_model.pkl
│   ├── sales_scaler.pkl
│   └── data.csv
├── train.py
├── utils.py
├── requirements.txt
└── README.md

---

⚙️ Setup Instructions

1. Clone the Repository

   git clone https://github.com/yourusername/sales-forecasting-app.git
   cd sales-forecasting-app

2. Create & Activate Virtual Environment (optional)

   python -m venv venv
   source venv/bin/activate   # On Windows: venv\Scripts\activate

3. Install Dependencies

   pip install -r requirements.txt

4. Run the App

   python manage.py runserver

   Visit: http://127.0.0.1:8000/

---

🖼️ UI Preview

---

🤝 Contributing

Pull requests are welcome! For major changes, open an issue to discuss what you'd like to improve.

---

📬 Contact

📧 Email: shubhrai598@gmail.com
💻 GitHub: github.com/shubh-gitpush