Retail Sales & Inventory Analytics Dashboard built using SQL, Python, Power BI, and Excel.
This project presents an end-to-end Retail Sales & Inventory Analytics solution built using SQL, Python, and Power BI. It analyzes over 100,000 retail transactions to uncover sales trends, customer behavior, inventory performance, and future sales forecasts through interactive dashboards and data-driven insights.
- Analyze retail sales performance.
- Understand customer purchasing behavior.
- Segment customers using RFM Analysis.
- Perform ABC Inventory Analysis.
- Forecast future sales using Machine Learning.
- Build an interactive Power BI dashboard for business decision-making.
| Technology | Purpose |
|---|---|
| SQL | Database Design & Analysis |
| MySQL | Data Storage |
| Python | Data Cleaning & Analysis |
| Pandas | Data Manipulation |
| NumPy | Numerical Computing |
| Matplotlib | Data Visualization |
| Scikit-learn | Sales Forecasting |
| Jupyter Notebook | Development Environment |
| Power BI | Interactive Dashboard |
| DAX | KPI Measures |
| Excel / CSV | Dataset Storage |
Retail-Sales-Inventory-Analytics/
│
├── data/
│ ├── clean_sales_data.csv
│ ├── customers.csv
│ ├── inventory.csv
│ ├── products.csv
│ └── sales.csv
│
├── images/
│ ├── abc_analysis/...
│ ├── business_analysis/...
│ ├── dashboard_screenshots/...
│ ├── database/...
│ ├── forecasting/...
│ ├── python_eda/...
│ ├── rfm_analysis/...
│ ├── sql_advanced/...
│ └── sql_analysis/...
│
├── powerbi/
│ ├── Retail_Sales_Analytics.pbix
│ └── theme.json
│
├── python/
│ ├── abc_inventory_analysis.ipynb
│ ├── eda.ipynb
│ ├── generate_dataset.py
│ ├── rfm_analysis.ipynb
│ └── sales_forecasting.ipynb
│
├── reports/
│ ├── abc_inventory_analysis.csv
│ ├── business_summary.csv
│ ├── customer_rfm_analysis.csv
│ ├── database_schema.md
│ └── sales_forecast.csv
│
├── sql/
│ ├── queries.sql
│ └── schema.sql
│
├── README.md
├── requirements.txt
└── .gitignore
Dataset Generation
│
▼
MySQL Database
│
▼
SQL Analysis
│
▼
Python Data Cleaning
│
▼
EDA & Feature Engineering
│
▼
RFM Customer Segmentation
│
▼
ABC Inventory Analysis
│
▼
Sales Forecasting
│
▼
Power BI Dashboard
│
▼
Business Insights
The project is built on a relational database consisting of four primary tables:
- 📦 Products
- 👥 Customers
- 🛒 Sales
- 🏬 Inventory
The Sales table acts as the fact table and connects customer and product information, while Inventory stores warehouse stock details for each product.
The Power BI dashboard consists of four interactive pages.
Provides a high-level summary of business performance.
- 💰 Total Sales
- 🛒 Total Orders
- 👥 Total Customers
- 📦 Total Products
- Monthly Revenue Trend
- Revenue by Category
- Top 10 Cities by Revenue
- Top 10 Products
Analyzes customer purchasing behavior using RFM Segmentation.
- 👥 Total Customers
- 💰 Average Customer Spend
- 🛍 Average Order Value
- 📈 Customer Revenue
- Customer Segment Distribution
- Revenue by Customer Segment
- Top 10 Customers
- Customer Segment Summary
Provides inventory optimization insights using ABC Analysis.
- 📦 Total Inventory Value
- 🛍 Total Products
⚠️ Low Stock Products- 💚 Healthy Inventory
- 🏢 Warehouses
- ABC Category Distribution
- Inventory Value by ABC Category
- Current Stock by Category
- Top Inventory Products
Forecasts future sales using Linear Regression.
- 💰 Total Sales
- 📈 Total Profit
- 🛒 Average Order Value
- 📊 Forecast Growth
- 🔮 Average Forecast Sales
- Monthly Revenue Trend
- Six-Month Sales Forecast
- Forecast Table
- Model Evaluation
- Forecast Summary
- Generated over ₹1.09 Billion in total revenue.
- Revenue remained relatively stable throughout the analysis period.
- Electronics generated the highest revenue among all product categories.
- Top-selling products contributed significantly to overall sales.
- Nearly half of customers belong to the Regular Customers segment.
- Champions and Loyal Customers generated the highest average spending.
- A relatively small percentage of customers contributed disproportionately to revenue.
- Customer segmentation provides opportunities for targeted marketing campaigns.
- Category A products account for the majority of inventory value.
- Inventory value is highly concentrated among a small number of products.
- Multiple products fall below the reorder level, highlighting restocking priorities.
- Current stock levels vary across product categories.
- Monthly sales remain relatively stable with moderate fluctuations.
- Linear Regression achieved an R² Score of 0.008, indicating a weak linear relationship.
- The six-month forecast suggests a slight upward trend in expected sales.
- More advanced time-series models (ARIMA or Prophet) could improve forecast accuracy.
- Linear Regression
- R² Score: 0.008
- Prophet Forecasting
- ARIMA
- XGBoost Regression
- LSTM Time-Series Forecasting
The project includes automatically generated reports:
- Business Summary
- Customer RFM Analysis
- ABC Inventory Analysis
- Sales Forecast
- Database Schema Documentation
- SQL Query Writing
- Database Design
- Data Cleaning
- Exploratory Data Analysis
- Customer Segmentation
- Inventory Optimization
- Machine Learning
- Sales Forecasting
- Data Visualization
- Dashboard Design
- Power BI
- DAX
- Business Analytics
Clone the repository
git clone https://github.com/your-username/Retail-Sales-Inventory-Analytics.gitMove into the project directory
cd Retail-Sales-Inventory-AnalyticsInstall dependencies
pip install -r requirements.txtOpen the notebooks
jupyter notebookOpen Power BI dashboard
powerbi/Retail_Sales_Analytics.pbix
- Deploy dashboard online using Power BI Service.
- Integrate live SQL database.
- Build automated ETL pipeline.
- Implement Prophet forecasting.
- Add customer churn prediction.
- Perform demand forecasting using advanced ML models.
Abhishek
B.Tech Computer Science Engineering
Aspiring Data Analyst | Business Intelligence Analyst | Analytics Engineer