metadata

title: Customer Churn Analysis - Interactive EDA
emoji: 📊
colorFrom: blue
colorTo: red
sdk: streamlit
sdk_version: 1.28.0
app_file: streamlit_app.py
pinned: false
license: mit
tags:
  - data-analysis
  - customer-churn
  - telecommunications
  - streamlit
  - plotly
  - eda
  - data-visualization
  - business-intelligence

📊 Customer Churn Analysis - Interactive EDA

An interactive Streamlit application for comprehensive exploratory data analysis of telecommunications customer churn data. This tool provides business analysts and data scientists with powerful visualizations and insights to understand customer behavior patterns and identify churn risk factors.

🚀 Live Demo

Try the interactive application: Customer Churn EDA

✨ Features

📋 Dataset Overview

Comprehensive Data Summary: Key statistics, data types, and sample exploration
Missing Value Analysis: Complete data quality assessment
Dataset Description: Detailed explanation of telecommunications churn data

🎯 Churn Analysis

Interactive Churn Distribution: Pie charts and statistical breakdowns
Categorical Analysis: Churn rates by service plans and customer segments
Feature Comparison: Box plots and histograms comparing churned vs retained customers

📍 Geographic Analysis

Interactive US Choropleth Maps: State-wise churn rate visualization
Regional Patterns: Top states by churn rate with detailed metrics
Area Code Analysis: Geographic distribution insights

📞 Usage Patterns

Time-based Analysis: Day, evening, night, and international usage patterns
Call Frequency Patterns: Detailed call behavior analysis
Customer Service Interactions: Service call impact on churn rates

💰 Revenue Analysis

Revenue Impact Assessment: Financial implications of customer churn
Revenue Component Breakdown: Detailed analysis by service type
Customer Segmentation: Revenue distribution across different customer groups

🔗 Correlation Analysis

Interactive Heatmaps: Feature correlation visualization with Plotly
Churn Predictors: Features most correlated with customer churn
Statistical Insights: Positive and negative correlation analysis

📊 Advanced Insights

Customer Segmentation: Usage vs Revenue scatter plots
High-Risk Customer Identification: Patterns in churned customer behavior
Service Plan Analysis: Churn rates by plan combinations
Automated Key Insights: AI-generated business insights and recommendations

🛠️ Technology Stack

Frontend: Streamlit for interactive web interface
Visualization: Plotly for interactive charts and maps
Data Processing: Pandas and NumPy for data manipulation
Statistics: Comprehensive statistical analysis and correlation studies

📊 Dataset Information

About the Dataset

This telecommunications customer churn dataset contains 3,333 customer records with 21 features covering:

Demographics: State, account length, area code
Service Plans: International calling and voice mail plans
Usage Patterns: Detailed minute usage and call frequency
Billing Information: Charges breakdown by time period
Customer Service: Interaction frequency and service quality
Target Variable: Customer churn status (14.5% churn rate)

Data Quality

✅ No Missing Values: Complete dataset with 100% data coverage
✅ Geographic Coverage: All 51 US states represented
✅ Balanced Features: Mix of numerical, categorical, and boolean variables

📱 Usage Guide

Navigation

Sidebar Selection: Choose between Combined Dataset, Training Set (80%), or Test Set (20%)
Analysis Types: Select from 7 comprehensive analysis categories
Interactive Exploration: All charts are interactive with hover details and zoom capabilities

Key Interactions

Hover Information: Detailed tooltips on all visualizations
Dynamic Filtering: Real-time updates based on selections
Export Options: Download charts as images
Responsive Design: Works seamlessly on desktop and mobile

🔍 Key Insights Discovered

Churn Risk Factors

High Service Calls: Customers with 4+ service calls have significantly higher churn rates
International Plans: International plan subscribers show elevated churn risk
Usage Patterns: Specific usage behaviors correlate with churn likelihood
Geographic Patterns: Certain states show consistently higher churn rates

Business Applications

Customer Retention: Identify at-risk customers for proactive outreach
Service Improvement: Understand pain points leading to customer churn
Geographic Strategy: Target retention efforts in high-churn regions
Revenue Protection: Quantify financial impact and prioritize retention efforts

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

Dataset: Telecommunications customer churn data for educational and research purposes
Streamlit: For providing an excellent framework for data applications
Plotly: For powerful interactive visualization capabilities
Hugging Face: For hosting and sharing data science applications

📞 Contact & Support

Discussions: Hugging Face Discussions
Documentation: Comprehensive in-app help and tooltips

⭐ If you find this project useful, please give it a star!

Built with ❤️ for the data science community