Skip to content

This interactive web application leverages machine learning to predict whether a telecom customer is likely to churn. Users can input customer details for real-time predictions or upload a CSV file for batch analysis.

Notifications You must be signed in to change notification settings

mirzayasirabdullahbaig07/Customer-Churn-Prediction-Model

Repository files navigation

📉 Customer Churn Prediction App

An AI-powered web application built with Streamlit that predicts whether a telecom customer will churn (leave the company) or stay, based on their profile and service usage details.


🚀 Demo

🔗 Live App on Streamlit

🚀 Short Video Demo

screen-capture.17.webm

📌 Features

  • Predicts Customer Churn Risk using a trained ML model.
  • Two modes:
    • 🧑 Single Customer Prediction
    • 📄 Batch Prediction (CSV upload)
  • Probability-based predictions with clear visualization.
  • User-friendly Streamlit interface with modern sidebar design.
  • Supports both categorical and numerical features.

🔍 Usage

  1. Open the app in your browser.
  2. Choose between Single Customer or Batch Prediction (CSV).
  3. For single prediction: Fill in customer details and click Predict Churn.
    • ⚠️ Yes → Customer WILL churn.
    • No → Customer will NOT churn.
  4. For batch prediction: Upload a CSV file with customer data and view predictions.

📊 Dataset

The app is trained using the Telco Customer Churn Dataset from IBM Sample Data.

  • Target Classes:

    • Yes → Customer will churn
    • No → Customer will stay
  • Features:

    • Demographics (Gender, SeniorCitizen, Partner, Dependents)
    • Account Info (Tenure, Contract, Payment Method, Paperless Billing)
    • Services (Phone, Internet, Online Security, Streaming, Tech Support, etc.)
    • Charges (MonthlyCharges, TotalCharges)

⚙️ Tech Stack

  • Python 3.9+
  • Streamlit (Frontend Web App)
  • Pandas & NumPy (Data Processing)
  • Matplotlib & Seaborn (EDA & Visualization)
  • Scikit-learn (Label Encoding, Model Training, Evaluation)
  • XGBoost & Random Forest (Machine Learning Models)
  • SMOTE (imblearn) (Handling Class Imbalance)
  • Pickle (Model & Encoder Serialization)

📸 Screenshots

🏠 Home Page

image

🧑 Single Customer Prediction

image

📄 Batch CSV Prediction

image

👨‍💻 Author

Mirza Yasir Abdullah Baig


❤️ Acknowledgements


⚠️ Disclaimer

This project is for educational purposes only and should NOT be used for real-world business decisions without further validation.


About

This interactive web application leverages machine learning to predict whether a telecom customer is likely to churn. Users can input customer details for real-time predictions or upload a CSV file for batch analysis.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages