A complete end-to-end data analysis project focused on consumer behavior and sales optimization using Python, SQL, Excel, and Tableau.
This project explores an eCommerce dataset to draw actionable insights, such as top-selling products, customer lifetime value, and sales trends. The workflow spans from data preprocessing in Python to PostgreSQL querying, Excel validation, and Tableau dashboard visualization.
- Python (Pandas, Matplotlib, Seaborn)
- PostgreSQL (data modeling and querying)
- Excel (intermediate analysis & exporting)
- Tableau (dashboard & storytelling)
| File | Description |
|---|---|
ecommerce-data.ipynb |
Data cleaning, preprocessing, and feature engineering |
data-visualization.ipynb |
EDA using Python visual libraries |
statistics-modeling.ipynb |
Trend analysis and basic statistical modeling |
erddesign.sql |
SQL schema and ERD creation for PostgreSQL |
queries.sql |
Business SQL queries (customer value, products, country) |
README.md |
Project overview |
- Sales increase steadily over the year with a peak in November–December, likely due to holiday shopping.
- The United Kingdom dominates sales by a wide margin.
- Netherlands and Germany follow with significantly less revenue.
- Products like "WORLD WAR 2 GLIDERS", "WHITE HANGING HEART T", and "POPORN HOLDER" are top contributors in quantity.
- Identified high-value customers with revenue above 250K.
- Segmented customers based on shopping behavior.
- Helps in targeting top-tier vs dormant customers.
How to Run Locally
- Clone the repository
git clone https://github.com/AdrikaPanwar/Consumer-Optimization.git
cd Consumer-Optimization
- Install necessary libraries
pip install pandas matplotlib seaborn jupyter
- Open and run notebooks
- Start with
ecommerce-data.ipynb - Proceed to
data-visualization.ipynbandstatistics-modeling.ipynb
- PostgreSQL Setup
- Use
erddesign.sqlto create schema - Execute
queries.sqlto extract insights
- Tableau Dashboard Import the cleaned/exported data into Tableau for dashboarding