Skip to content

README.md

Latest commit

 

History

History
96 lines (69 loc) · 2.75 KB

README.md

File metadata and controls

96 lines (69 loc) · 2.75 KB
Raw

🛒 Superstore EDA Project (Fake Data Analysis)

📌 Project Overview

This project demonstrates a complete data analytics workflow starting from synthetic data generation to exploratory data analysis (EDA) and interactive dashboard creation.

A realistic Superstore Management System dataset was generated using Python (Faker library), followed by structured EDA in Jupyter Notebook and final visualization using Power BI.

⚙️ Workflow

1. 📊 Data Generation

  • Synthetic dataset created using:
    • Faker (for names, cities, companies, etc.)
    • random and numpy
  • Simulated real-world retail transactions
  • Dataset includes:
    • Orders, customers, products
    • Sales, profit, discount
    • Region-wise and category-wise data
    • Delivery status & payment modes
    • Inventory & reorder logic

2. 🧹 Exploratory Data Analysis (EDA)

Performed in Jupyter Notebook using:

pandas, numpy, matplotlib, seaborn


## 🔍 Key Analysis Steps

- Data importing and inspection  
- Data cleaning and preprocessing  
- Univariate analysis (distribution of variables)  
- Bivariate analysis (relationships between features)  
- Regional performance analysis  
- Customer segment analysis  
- Numerical variable analysis  
- Correlation matrix & heatmap  
- Advanced analysis of profit, sales, and discount impact  

---

## 📈 Insights Extracted

The analysis helped uncover key business insights such as:

- 🏆 Top-performing product categories in terms of sales and profit  
- 🌍 Region-wise sales distribution and performance comparison  
- 👥 Customer segments contributing highest revenue  
- 💸 Impact of discounting on profit margins  
- 📦 Stock-based reorder patterns and inventory behavior  
- 📊 Correlation between sales, profit, cost price, and discount  

These insights help simulate real-world business decision-making scenarios.

---

## 📊 Power BI Dashboard

The cleaned dataset was exported and used to build an **interactive Power BI dashboard**.

### 📌 Dashboard Features:
- Sales & Profit trend analysis  
- Region-wise performance map  
- Category-wise breakdown of sales  
- Customer segment analysis  
- KPI cards (Total Sales, Profit, Orders)  
- Interactive filters and slicers  

The dashboard transforms raw data into actionable business intelligence.

---

## 🧠 Key Learning Outcomes

- End-to-end data analytics pipeline creation  
- Synthetic data generation for real-world simulation  
- Advanced EDA techniques using Python  
- Business insight extraction from raw data  
- Data visualization and storytelling  
- Dashboard creation using Power BI  

---

## 🛠️ Tools & Technologies Used

- Python 🐍  
- Pandas & NumPy  
- Matplotlib & Seaborn  
- Faker Library  
- Jupyter Notebook  
- Power BI