An end-to-end Business Intelligence project that transforms raw retail sales data into actionable business insights using SQL, Python, and Power BI. The project focuses on identifying revenue drivers, profitability challenges, customer purchasing behavior, regional performance, and product performance to support data-driven business decision-making.
The Retail Profit Intelligence System simulates the workflow of a Business Intelligence Analyst by combining data analysis, feature engineering, customer segmentation, and dashboard development into a single analytics solution.
The project includes:
- SQL-based business analysis
- Python feature engineering
- RFM customer segmentation
- Product portfolio classification
- Interactive Power BI dashboards
- Executive business recommendations
| Technology | Purpose |
|---|---|
| SQL (MySQL) | Data cleaning, transformation, KPI creation, and business analysis |
| Python (Pandas, Matplotlib) | Feature engineering, exploratory analysis, RFM segmentation, and product portfolio classification |
| Power BI | Interactive dashboards and business storytelling |
| Git & GitHub | Version control and project documentation |
- Business generated $2.27M in sales across 4,931 orders.
- Sales and profitability increased consistently between 2014–2017.
- Furniture generated high revenue but recorded the lowest profit margin.
- Discounts above 30% consistently resulted in financial losses.
- Texas recorded the largest overall loss despite strong sales.
- Customer segmentation identified 106 Champion and 145 At Risk customers.
- Product portfolio analysis highlighted profitable Hidden Gems and loss-making Revenue Drivers. For a detailed breakdown of findings, check docs folders.
| Document | Description |
|---|---|
| docs/Project_Journal.md | Complete project workflow and development process |
| docs/Executive_Findings.md | Business findings, evidence, recommendations, and strategic insights |
| powerbi/retail_profit_intelligence.pbix | Interactive Power BI dashboard |
| sql/ | SQL scripts used for business analysis |
| python/ | Python notebooks for feature engineering and advanced analytics |
- Clone the repository.
- Import the dataset into MySQL.
- Execute the SQL scripts to reproduce the business analysis.
- Run the Python notebooks to perform feature engineering and customer segmentation.
- Open the Power BI (
.pbix) file to explore the interactive dashboards.