retail-sales-analysis

🚀 Retail Sales Analysis — Business Insights from Superstore Data

📌 Summary

End-to-end exploratory data analysis on 4 years of retail sales data to uncover seasonal trends, profitability, customer segment behavior, and loss-making areas. Built in a reproducible notebook with clean structure, exportable outputs, and dashboard-ready visualizations.

Live Links

• GitHub Pages: https://litla8.github.io/retail-sales-analysis/
• Kaggle Notebook: https://www.kaggle.com/code/lalitraos/sales-dashboard

🎯 Objectives

• Identify peak sales periods and seasonality
• Analyze the impact of discounting on profitability
• Extract time-based features such as Year, Month, and Quarter
• Compare performance across region, state, category, sub-category, and segment
• Detect outliers, loss-making products, and underperforming regions
• Generate actionable business recommendations

📊 Dataset

• Dataset Name: Sample Superstore Sales Dataset
• Recommended Source: vivek468/superstore-dataset-final
• Other Good Options:
  • rohitsahoo/sales-forecasting
  • laibaanwer/superstore-sales-dataset
• Expected File Name: Sample - Superstore.csv

🧠 Approach

• Data loading and cleaning using Pandas
• Missing-value handling and duplicate removal
• Datetime conversion and feature engineering
• Exploratory data analysis for sales, profit, quantity, and order value
• Advanced analysis for seasonality, discount-profit relationship, and outliers
• Visualization using Matplotlib and Seaborn
• Export of processed files, summaries, and business insights

📈 Key Insights

• Sales fluctuate across months, showing clear seasonality and peak demand periods
• Heavy discounting is associated with lower profitability
• Some products and regions consistently generate losses
• The Consumer segment contributes a major share of total sales
• Category and sub-category performance varies significantly and requires targeted strategy

🖼️ Visuals

Add your screenshots or generated dashboards in the project root and reference them like this:

Included dashboard files:

• retail_sales_dashboard.png
• retail_sales_additional_insights.png

🗂️ Project Structure

retail_sales_analysis/
├── README.md
├── .gitignore
├── LICENSE
├── requirements.txt
├── p2_retail_sales_analysis.ipynb
├── p2_retail_sales_analysis.py
├── p2_retail_sales_analysis.html
├── Sample - Superstore.csv
├── retail_sales_processed.csv
├── retail_sales_monthly_summary.csv
├── retail_sales_yearly_summary.csv
├── retail_sales_product_performance.csv
├── retail_sales_insights.txt
├── retail_sales_dashboard.png
└── retail_sales_additional_insights.png

▶️ Run Locally

pip install -r requirements.txt
jupyter notebook p2_retail_sales_analysis.ipynb

🧪 Reproducibility

• Python 3.9+
• Deterministic aggregations and reproducible data pipeline
• Kaggle-compatible notebook version available for cloud execution

🛠️ Tech Stack

• Python
• Pandas
• NumPy
• Matplotlib
• Seaborn
• Jupyter Notebook

🚀 Extensions (next steps)

• Build a Streamlit dashboard for interactive exploration
• Add forecasting for future monthly sales
• Create region-wise KPI cards and filters
• Deploy a cleaner HTML landing page through GitHub Pages

👤 Author

Lalit Rao — https://github.com/Litla8

📜 Certificate

[View Certificate]C:\Users\Lalit Rao\OneDrive\Desktop\retail_sales_analysis\certificate

This site is open source. Improve this page.