Customer churn is a critical challenge in the telecom industry, where customers frequently switch service providers due to competitive pricing, service quality, and better offers. High churn rates directly impact revenue, profitability, and business growth.
This project analyzes telecom customer data to identify key factors driving churn and provide actionable insights to improve customer retention.
This project simulates a real-world business scenario where telecom companies use data analytics to identify high-risk customers and implement effective retention strategies.
- Source: IBM Telco Customer Dataset
- Total Records: 7,000+ customers
- Description: Includes customer demographics, service subscriptions, account details, and churn status
- Power BI – Data cleaning, transformation, and dashboard development
- Total Customers
- Total Churn
- Churn Rate
- Average Monthly Charges
- Calculated overall churn rate
- Analyzed churn by contract type
- Evaluated churn across internet service categories
- Performed customer segmentation based on tenure
- Analyzed monthly charges vs churn behavior
- Studied impact of payment methods on churn
- Problem: The dataset contained missing and inconsistent values, particularly in fields like TotalCharges, affecting data reliability
- Solution: Performed data cleaning and preprocessing using Power BI Power Query to handle missing values and ensure data consistency
- Problem: Certain numerical fields were stored as text, leading to incorrect aggregations and calculations
- Solution: Converted columns to appropriate data types to enable accurate analysis and reporting
- Problem: The dataset lacked explicit indicators explaining why customers churned
- Solution: Created derived features such as tenure groups and performed segmentation analysis to uncover hidden patterns
- Problem: Multiple variables influenced churn, making it challenging to isolate the most impactful factors
- Solution: Conducted comparative visual analysis across dimensions like contract type, tenure, and monthly charges to identify primary churn drivers
- Around 26% of customers have churned
- Month-to-month contract customers have the highest churn rate
- Customers with higher monthly charges are more likely to churn
- New customers (low tenure) show higher churn probability
- Fiber optic users have higher churn compared to DSL users
- Promote long-term contracts to reduce churn
- Offer targeted discounts for high monthly charge customers
- Improve service quality for high-risk customer segments
- Focus retention strategies on new customers
This project simulates a real-world telecom analytics scenario where identifying high-risk customers enables companies to take proactive measures, reduce churn, and improve customer lifetime value.
Telecom-Customer-Churn-Analysis │ ├── dataset/ ├── dashboard/ ├── README.md
These dashboards help analyze customer churn patterns, uncover key drivers of attrition, and provide actionable insights to enhance customer retention strategies and minimize revenue loss.
- LinkedIn: https://www.linkedin.com/in/saba-attar-9823aa183
- GitHub: https://github.com/SabaAttar
- Key Skills: MS Power BI, SQL, Tableau, MS Excel, Python etc..
⭐ If you found this project useful, feel free to star the repository!