Welcome to the Blinkit Data Analysis project! This is a real-world business intelligence case study that uses SQL, Python, Excel, and Power BI to uncover valuable insights from Blinkit's grocery sales and outlet data. From sales patterns to customer ratings and outlet efficiency — this project covers it all!
The main goal of this project is to analyze Blinkit's sales data to discover:
- 🔍 Patterns in customer purchasing behavior
- 📉 Underperforming categories or outlets
- 📈 Opportunities to improve revenue and efficiency
This project simulates how a data analyst would present data-driven recommendations to business stakeholders.
| Tool | Purpose |
|---|---|
| SQL | Data extraction, transformation, and aggregation |
| Python | Data cleaning, EDA (Exploratory Data Analysis) using Pandas and Matplotlib |
| Excel | Initial data exploration and quick KPIs |
| Power BI | Interactive dashboard creation for KPI storytelling and visualizations |
- Items: Various grocery products sold by Blinkit
- Sales: Units sold, revenue generated
- Customer Ratings: Based on purchase satisfaction
- Outlet Details: Type, size, location, and year of establishment
📄 Format: Excel Workbook (.xlsx)
Here are the key insights and metrics we aimed to extract:
- Objective: Analyze how fat content (Low Fat, Regular) affects total revenue
- KPIs: Total Sales, Average Sales, Number of Items, Average Rating
- Chart: Donut Chart (Power BI)
- Objective: Identify which product categories contribute most to revenue
- KPIs: Same as above
- Chart: Bar Chart
- Objective: Compare total sales across different outlet types segmented by fat content
- Chart: Stacked Column Chart
- Objective: Explore how the outlet age impacts performance
- Chart: Line Chart
- Objective: Determine which outlet sizes generate the most revenue
- Chart: Donut / Pie Chart
- Objective: Discover the geographic distribution of Blinkit’s revenue
- Chart: Funnel Map
- Objective: Compare all KPIs (Sales, Ratings, etc.) across outlet types
- Chart: Matrix Card
The final dashboard is built using Power BI and provides an interactive and real-time view of all the insights, including:
- Dynamic filters and slicers
- Drill-down capability for deeper analysis
- Clean UI with bold visuals and a logical flow
✅ Each chart answers a specific business question
📊 KPIs are displayed in cards and matrix format for clarity
🌐 Geographic visuals help identify location-based performance trends
Using Pandas and Matplotlib, we:
- Handled missing values and duplicates
- Created grouped metrics like avg. sales and ratings
- Visualized trends and correlations in the dataset
- Initial data validation and transformation
- Quick pivot tables for checking metrics
- Manual KPI calculations for cross-verification
- Leveraged multiple tools to simulate real-world BI workflow
- Gained business insights that can drive marketing and inventory decisions
- Built a compelling and easy-to-navigate dashboard for stakeholders
- Strengthened hands-on skills in data storytelling and BI presentation
📦 Blinkit-Data-Analysis/ ├── 📊 PowerBI Dashboard (Blinkit.pbix) ├── 🐍 Python Scripts (EDA.ipynb / analysis.py) ├── 📈 Excel Files (BlinkIT Grocery Data.xlsx) ├── 📄 Documentation (Insights.pdf, README.md)
Snehal Nalawade
💼 Aspiring Data Analyst | Passionate about BI and storytelling
📧 snehalrnalawade2003@gmail.com
📍 India