An AI-powered Machine Learning dashboard that predicts whether a telecom customer is likely to churn based on customer demographics, subscription details, billing information, and service usage patterns.

This project helps telecom companies identify customers who are likely to leave the service (churn) using Machine Learning.

The dashboard allows business users to:

• Analyze customer profiles
• Predict churn probability
• Understand key churn drivers
• Generate retention recommendations
• Visualize feature importance

• Customer Churn Prediction
• Churn Probability Score
• Retention Probability Score
• Interactive Dashboard
• Customer Profile Analysis
• Service Usage Analysis
• Feature Importance Visualization
• Business Recommendations
• Executive Summary Generation

Model Used:

• Random Forest Classifier

Model Performance:

• Accuracy: 77.97%

prediction.png

• Gender
• Partner Status
• Dependents
• Senior Citizen
• Contract Type
• Payment Method
• Paperless Billing

• Phone Service
• Multiple Lines
• Internet Service
• Online Security
• Online Backup
• Tech Support
• Device Protection
• Streaming TV
• Streaming Movies

• Tenure
• Monthly Charges
• Total Charges

• Churn Risk Meter
• Churn Probability
• Retention Probability
• Feature Importance Chart
• Executive Summary
• Business Recommendations

• Python
• Streamlit
• Pandas
• NumPy
• Scikit-Learn
• Matplotlib
• Joblib

Clone the repository:

git clone https://github.com/yourusername/Telecom-Customer-Churn-Prediction.git