🛒 E-Commerce Sales Analysis

A comprehensive Exploratory Data Analysis (EDA) project on a real-world E-Commerce Sales dataset using Python, NumPy, Pandas, Matplotlib, and Seaborn.

This project demonstrates an end-to-end data analytics workflow, including data cleaning, preprocessing, exploratory data analysis, business insights, and visualization.

📌 Project Overview

This project demonstrates a complete Data Analytics workflow, including:

• Data Loading
• Data Cleaning
• Data Preprocessing
• Exploratory Data Analysis (EDA)
• Business Insights
• Statistical Analysis
• Data Visualization

The objective is to uncover meaningful insights that can help businesses understand customer behavior, improve profitability, and optimize sales performance.

---

🛠 Technologies Used

• Python
• NumPy
• Pandas
• Matplotlib
• Seaborn
• Jupyter Notebook

---

📂 Dataset Information

The dataset contains over 51,290 e-commerce orders from different countries and regions.

Dataset Features

Column	Description
Order ID	Unique Order Identifier
Order Date	Date of Order
Ship Date	Shipping Date
Aging	Delivery Aging (Days)
Ship Mode	Shipping Method
Product Category	Product Category
Product	Product Name
Sales	Order Sales Amount
Quantity	Quantity Purchased
Discount	Discount Offered
Profit	Profit Earned
Shipping Cost	Shipping Charges
Order Priority	Priority Level
Customer ID	Customer Identifier
Customer Name	Customer Name
Segment	Customer Segment
City	Customer City
State	Customer State
Country	Customer Country
Region	Sales Region
Months	Order Month

---

🧹 Data Cleaning & Preprocessing

The following preprocessing steps were performed before analysis:

• Renamed corrupted column name (Order ID → Order ID)
• Converted Order Date and Ship Date into datetime format
• Removed currency symbols ($) from monetary columns
• Converted Sales, Profit, Shipping Cost into numeric values
• Converted Discount and Quantity into appropriate numeric data types
• Identified invalid values such as 0.xf and test
• Converted invalid values into NaN using pd.to_numeric(errors="coerce")
• Removed rows containing missing and corrupted values
• Verified duplicate records
• Performed final dataset validation

---

📊 Business Questions Addressed

The project answers several real-world business questions including:

• Overall Business Performance
• Top Selling Products
• Product Category Analysis
• Monthly Sales Trend
• Regional Sales Analysis
• Country-wise Revenue Analysis
• State-wise Profit Analysis
• Customer Segment Analysis
• Ship Mode Performance
• Discount vs Profit Analysis
• Order Priority Analysis
• Top Customers Analysis
• Loss Making Orders
• Delivery Aging Analysis
• Sales Distribution
• Profit Distribution
• Correlation Analysis
• High Value Orders
• Customer Purchase Frequency
• Executive Business Insights

---

📈 Visualizations

The project contains various visualizations using Seaborn and Matplotlib, including:

• Bar Charts
• Horizontal Bar Charts
• Count Plots
• Line Charts
• Scatter Plots
• Histograms
• Box Plots
• Violin Plots
• Correlation Heatmap

---

📸 Project Screenshots

Overall Business Performance

---

Seasonal Sales Patterns

---

Country Sales Performance

---

Region-wise Sales Analysis

---

Valuable Customers

---

Customer Purchase Frequency

---

Discount vs Profit Analysis

---

Profit Distribution by Category

---

Correlation Analysis

---

🔍 Key Insights

The analysis revealed the following business insights:

• Overall business revenue and profitability
• Best-selling products
• Highest revenue-generating product categories
• Monthly sales trends and seasonality
• Most profitable regions and countries
• Customer purchasing behavior
• Performance of different shipping modes
• Relationship between discount and profit
• High-value customer identification
• Loss-making transactions
• Delivery performance analysis
• Correlation among sales, profit, discount, quantity, shipping cost, and aging

---

📁 Project Structure

ecommerce-sales-analysis
│
├── ecommerce.csv
├── Ecommerce_data_analysis.ipynb
├── README.md
└── project_screenshots
    ├── average_delivery_time.png
    ├── correlation_analysis.png
    ├── country_sales_performance.png
    ├── customer_purchase_frequency.png
    ├── customer_segments.png
    ├── discount_vs_profit_analysis.png
    ├── high_value_orders.png
    ├── loss.png
    ├── overall_business_performance.png
    ├── product_category.png
    ├── profit_distribution_by_category.png
    ├── region_wise_sales.png
    ├── sales_distribution.png
    ├── sales_vs_priority.png
    ├── seasonal_sales_patterns.png
    ├── shipping_efficiency.png
    ├── state_sales_comparison.png
    └── valuable_customers.png

---

▶️ How to Run

Clone the repository

git clone https://github.com/Enthuasish/ecommerce-sales-analysis.git

Install dependencies

pip install pandas numpy matplotlib seaborn

Launch Jupyter Notebook

jupyter notebook

Run all notebook cells to reproduce the complete analysis and visualizations.

---

💡 Skills Demonstrated

• Data Cleaning
• Data Preprocessing
• Data Transformation
• Exploratory Data Analysis (EDA)
• Pandas Data Manipulation
• NumPy Operations
• GroupBy Analysis
• Statistical Analysis
• Business Analytics
• Data Visualization
• Correlation Analysis
• Analytical Thinking

---

🚀 Future Improvements

• Interactive Dashboard using Power BI
• Interactive Dashboard using Plotly Dash
• Sales Forecasting using Machine Learning
• Customer Segmentation using Clustering
• Profit Prediction Model
• Executive KPI Dashboard

---

👨‍💻 Author

Asish Amitansu Rout

Data Analyst Trainee | MCA Student | Python & Data Analytics Enthusiast

GitHub: https://github.com/Enthuasish

Linkedin: https://www.linkedin.com/in/asish-amitansu-rout

---

⭐ If you found this project useful, consider giving it a Star.