Customer Shopping Behavior Analysis is an end-to-end retail analytics project that analyzes customer purchasing behavior to uncover meaningful business insights using Python, SQL Server, and Power BI.
The project follows a complete analytics workflow beginning with data preprocessing and feature engineering, followed by SQL-based business analysis and interactive dashboard development.
The generated insights can help retailers understand customer behavior, improve marketing strategies, optimize inventory, personalize customer experiences, and increase overall business revenue.
Retail companies generate large volumes of customer transaction data every day.
However, raw transactional data alone does not help businesses answer important questions such as:
- Which customers generate maximum revenue?
- Do discounts actually increase sales?
- Which products perform the best?
- Are subscription customers more valuable?
- Which customer segment should be targeted?
This project answers these business questions through data analytics.
- Analyze customer purchasing behavior.
- Study customer demographics.
- Evaluate discount effectiveness.
- Compare subscribers and non-subscribers.
- Identify high-performing products.
- Perform customer segmentation.
- Build an interactive Power BI dashboard.
- Generate business recommendations.
| Tool | Purpose |
|---|---|
| Python | Data Cleaning & Analysis |
| Pandas | Data Manipulation |
| NumPy | Numerical Operations |
| Matplotlib | Visualization |
| SQL Server (SSMS) | Business Query Analysis |
| SQL | Data Retrieval |
| Power BI | Dashboard Development |
- Retail Customer Shopping Dataset
- 3900 Customer Records
- 18 Features
- Customer ID
- Age
- Gender
- Item Purchased
- Category
- Purchase Amount
- Review Rating
- Shipping Type
- Discount Applied
- Subscription Status
- Previous Purchases
- Frequency of Purchases
- Season
- Payment Method
- Location
Raw Dataset
⬇️
Python Data Cleaning
⬇️
Feature Engineering
⬇️
SQL Business Analysis
⬇️
Power BI Dashboard
⬇️
Business Insights
⬇️
Business Recommendations
The dataset was cleaned and preprocessed using Python.
Tasks performed:
- Missing value treatment
- Feature engineering
- Age Group creation
- Purchase Frequency conversion
- Data standardization
- Removing redundant columns
Business questions answered:
- Revenue by Gender
- Top Rated Products
- High Spending Customers
- Shipping Analysis
- Customer Segmentation
- Subscription Analysis
- Revenue by Age Group
- Top Products by Category
- Repeat Buyer Analysis
The interactive dashboard includes:
- Revenue Overview
- Customer Distribution
- Sales by Gender
- Revenue by Age Group
- Product Category Analysis
- Customer Segmentation
- Discount Analysis
- Shipping Analysis
- Subscription Analysis
- Interactive Filters
- Customer spending varies across demographics.
- Subscribers contribute significant revenue.
- Loyal customers account for most purchases.
- Certain products consistently receive high ratings.
- Discounts improve sales only for selected products.
- Customer segmentation helps improve targeted marketing.
- Expand subscription programs.
- Focus marketing on loyal customers.
- Promote highly rated products.
- Personalize offers by age group.
- Optimize inventory based on demand.
- Reduce unnecessary discounting.
Customer-Shopping-Behavior-Analysis
│
├── Dataset
├── SQL
├── Python
├── Power BI
├── Report
├── Presentation
├── Dashboard_Preview
└── README.md
- Customer Churn Prediction
- Recommendation System
- Market Basket Analysis
- Customer Lifetime Value Prediction
- Interactive Web Dashboard
Kesar Deaulkar
Computer Engineering Student
Aspiring Data Analyst
Mumbai, India
GitHub: https://github.com/Kesar13-git