This project presents an end-to-end Amazon Sales Analysis using Python. The objective is to transform raw sales data into meaningful business insights through data cleaning, feature engineering, exploratory data analysis (EDA), and data visualization.
The analysis identifies revenue trends, profit performance, customer purchasing behavior, product performance, shipping efficiency, and regional sales patterns to support data-driven business decisions.
Amazon processes thousands of customer transactions across different products and regions. Without proper analysis, it becomes difficult to identify sales trends, profitable products, customer behavior, and regional performance.
This project answers important business questions such as:
- Which products generate the highest revenue?
- Which products generate the highest profit?
- Which states and cities contribute the most revenue?
- What are the seasonal sales trends?
- How does shipping performance affect customer orders?
- Which business strategies can improve revenue and profitability?
| Attribute | Value |
|---|---|
| Domain | Retail / E-Commerce |
| Dataset | Amazon Sales Dataset |
| Format | CSV |
| Analysis Tool | Python |
| Visualization | Matplotlib & Seaborn |
| Tool | Purpose |
|---|---|
| Python | Data Analysis |
| Pandas | Data Cleaning & Manipulation |
| NumPy | Numerical Computing |
| Matplotlib | Data Visualization |
| Seaborn | Statistical Visualization |
| Jupyter Notebook | Development Environment |
- Data Cleaning
- Data Quality Assessment
- Missing Value Analysis
- Duplicate Record Detection
- Feature Engineering
- Exploratory Data Analysis (EDA)
- Revenue Analysis
- Profit Analysis
- Product Performance Analysis
- Customer Behavior Analysis
- Shipping Analysis
- Regional Sales Analysis
- Business Insights
- Strategic Recommendations
- Import Libraries
- Load Dataset
- Data Inspection
- Data Cleaning
- Data Quality Checks
- Feature Engineering
- Exploratory Data Analysis
- Data Visualization
- Business Insights
- Business Recommendations
- Executive Summary
The project includes detailed analysis of:
- Revenue Distribution
- Profit Distribution
- Quantity Distribution
- Revenue by Category
- Profit by Category
- Shipping Speed Analysis
- Monthly Revenue Trend
- Yearly Revenue Trend
- Revenue by Season
- Weekday vs Weekend Sales
- Sales Category Analysis
- Profit Status Analysis
- Profit Margin Distribution
- Revenue vs Profit
- Quantity vs Revenue
- Top Revenue Products
- Top Profit Products
- Lowest Revenue Products
- Customer Purchase Analysis
- Average Revenue per Product
- State-wise Revenue
- State-wise Profit
- City-wise Revenue
- State-wise Orders
Insight
California generated the highest revenue among all states, highlighting it as the strongest regional market. A few states contributed a significant share of total sales, while many states generated comparatively lower revenue.
Recommendation
Prioritize marketing campaigns, inventory planning, and customer retention initiatives in high-performing states while developing targeted growth strategies for underperforming regions.
Insight
Revenue and profit show a positive relationship, indicating that higher sales generally lead to higher profitability. However, some high-revenue transactions delivered relatively lower profit, suggesting margin differences across products.
Recommendation
Focus on increasing sales of high-margin products and review pricing strategies for products with strong revenue but weaker profitability.
Insight
A small group of products generated a substantial portion of total profit. These products consistently outperformed others and played a major role in overall business profitability.
Recommendation
Maintain sufficient inventory, increase promotional efforts, and prioritize these high-profit products to maximize business returns.
Insight
Monthly sales followed a clear seasonal pattern, with revenue increasing toward the end of the year. November and December recorded the strongest sales performance.
Recommendation
Prepare inventory, staffing, and marketing campaigns ahead of the peak shopping season to fully capitalize on increased customer demand.
- Analyzed retail sales data using Python, Pandas, NumPy, Matplotlib, and Seaborn.
- Performed data cleaning, preprocessing, and exploratory data analysis (EDA).
- Identified California as the highest revenue-generating state.
- Observed a strong positive relationship between revenue and profit.
- Determined the top 10 most profitable products contributing significantly to overall profit.
- Identified seasonal sales trends, with peak performance during November and December.
- Generated business insights to support inventory optimization, marketing strategies, and revenue growth.
- Delivered data-driven recommendations to improve profitability and support informed business decision-making.
- Sales showed consistent year-over-year growth.
- November and December recorded the highest revenue.
- Most customers purchased between 2 and 6 products per order.
- Medium Shipping was the most frequently used shipping option.
- Chairs generated the highest revenue among product categories.
- Copiers generated the highest overall profit.
- Canon Camera products generated the highest revenue.
- Canon imageCLASS Copier generated the highest profit.
- California contributed the highest revenue, profit, and customer orders.
- Los Angeles generated the highest city-level revenue.
- Higher revenue generally correlated with higher profit.
- Increase inventory before seasonal demand peaks.
- Focus marketing on high-performing products and categories.
- Improve pricing strategies for low-profit products.
- Strengthen customer retention programs.
- Promote premium products with high average revenue.
- Launch weekend promotional campaigns to improve weekend sales.
- Optimize shipping performance to improve customer satisfaction.
- Invest more resources in high-performing states and cities.
- Pandas
- NumPy
- Matplotlib
- Seaborn
- Data Cleaning
- Data Validation
- Missing Value Handling
- Duplicate Detection
- Feature Engineering
- Exploratory Data Analysis (EDA)
- Statistical Analysis
- Data Aggregation
- Data Visualization
- Business Insight Generation
Amazon-Sales-Analysis/
│
├── Dataset/
│
├── Images/
│
├── Notebook/
│
├── README.md
│
└── Requirment.txt
- Build an interactive Power BI dashboard.
- Develop a sales forecasting model using Machine Learning.
- Implement customer segmentation techniques.
- Create an automated reporting pipeline.
- Deploy the project as an interactive web application.
Jatin Patidar
Aspiring Data Analyst
- 📧 Email: jatinpatidar606@gmail.com
- 💼 LinkedIn: https://www.linkedin.com/in/jatinpatidar09/
- 🐙 GitHub: https://github.com/09jatin
If you found this project useful, consider giving it a ⭐ on GitHub.
Feedback and suggestions are always welcome.