An end-to-end Machine Learning web application and data analysis project built on the Superstore Sales dataset. This project has been transformed from a static EDA notebook into a live, interactive Streamlit application featuring predictive forecasting and customer segmentation.

• 🟢 Live Interactive Dashboard: https://sales-dashboard-123dars.streamlit.app/

• Interactive Executive Dashboard: Dynamic KPI tracking, monthly revenue trends, and dynamic filtering by region and segment using Streamlit.
• Predictive Sales Forecasting (Machine Learning): Leverages statsmodels (Holt-Winters Exponential Smoothing) to predict the next 12-24 months of revenue based on historical seasonality.
• Customer RFM Segmentation: An automated algorithm that calculates Recency, Frequency, and Monetary value to categorize customers into actionable business tiers ("Champions", "At Risk", "Loyal").
• Geographic Revenue Heatmap: Interactive United States choropleth maps built with Plotly, highlighting exact revenue and profit generation by state.

Python · Streamlit · Scikit-Learn · Statsmodels (Time Series) · Plotly Express · Pandas

Sales-Analytics-Dashboard/
├── app.py                # Main Streamlit ML Web Application
├── requirements.txt      # Python dependencies for Cloud Deployment
├── analysis.ipynb        # Original Jupyter notebook with full EDA
├── superstore.csv        # Dataset
└── README.md

Darshan B | github.com/123dars

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