📉 Telecom Customer Churn Analysis (City-wise Dissatisfaction)

📘 Project Overview

This project focuses on analyzing customer churn caused by dissatisfaction across various cities. The main objective is to identify which cities have the highest churn percentage due to dissatisfaction and visualize it using a pie chart.

🧩 Dataset Information

• Source: IBM Telco Customer Churn Dataset

• Key Features Used:

  • customerID – Unique customer identifier
  • City – Customer’s city or region
  • Churn Category – Reason for churn (e.g., Dissatisfaction, Competitor, etc.)
  • Churn – Indicates whether the customer left (Yes/No)

📊 Exploratory Data Analysis (EDA)

Key steps performed in the notebook:

1. Data Cleaning – Checked for missing values and corrected data types.
2. Filtering Data – Selected only customers who left due to dissatisfaction.
3. Grouping Data – Calculated total churn counts grouped by city.
4. Visualization: Pie Chart- Displayed city-wise churn percentage of customers who left due to dissatisfaction.

💡 Key Insights

• Identified top cities with the highest churn due to dissatisfaction.
• The pie chart provides a clear comparison of churn proportions across different cities.
• Insights can help businesses improve customer satisfaction and reduce churn in critical regions.

🧠 Technologies Used

• Language: Python 🐍

• Libraries:

  • pandas – Data analysis
  • matplotlib – Visualization

📈 Visualization

• Pie Chart – City-wise churn percentage due to dissatisfaction

🚀 Future Improvements

• Add state-level or regional churn analysis for broader insights.
• Include interactive dashboards for dynamic visualization.

👩‍💻 Author

ANKITHA N 📧 [email protected]