OperationalCostForecasting

Overview Link to heading

This project focuses on creating a robust demand forecasting system for the retail industry. Using time series data, the solution identifies trends, seasonality, and other influential factors to optimize inventory management and reduce costs.

Dataset Link to heading

• Source: Walmart Store Sales Dataset
• Description: Weekly sales data from Walmart stores with additional features like holidays and weather information.

Features Link to heading

• Time series modeling with seasonal decomposition.
• Feature engineering for external variables like holidays and promotions.
• Deployment-ready forecasting dashboard using Streamlit.

Tools and Libraries Link to heading

• Python
• Pandas, NumPy
• Scikit-learn
• Statsmodels
• Plotly
• Streamlit

How to Run Link to heading

1. Clone the repository:
   git clone https://github.com/Sharma-Pranav/Portfolio.git
2. Navigate to the project directory:
   cd RetailDemandForecaster
3. Install dependencies:
   pip install -r requirements.txt
4. Run the Streamlit app:
   streamlit run app.py

Results Link to heading

• Enhanced forecasting accuracy through feature engineering.
• Visualization of key trends and seasonality.