This project analyzes customer churn behavior in a telecom company to identify key drivers of customer attrition and revenue loss.
- Python (Data Cleaning & Feature Engineering)
- SQL (Data Analysis)
- Power BI (Data Visualization)
Raw Data -> Data Cleaning (Python) -> Analysis (SQL) -> Dashboard (Power BI)
- Month-to-month customers have highest churn (~43%)
- New customers (0–1 year) are most likely to churn (~47%)
- Electronic check users show higher churn behavior
- ~$139K revenue is at risk due to churn
- Encourage long-term contracts
- Improve onboarding for new customers
- Target high-risk segments with retention strategies
- Cleaned dataset
- Python notebook
- SQL queries
- Power BI dashboard