Telecom Churn Prediction Streamlit App

This is a Streamlit web application for predicting Telecom Churn. The app uses a trained machine learning model to predict whether a customer is likely to churn or not based on certain input features.

View Demo · Documentation · Report Bug · Request Feature

📔 Table of Contents

• Dataset
• Dependencies
• Installation
• Usage
• Inputs
• Outputs
• Deployment and Notebook
• License
• Contact

📶 Dataset

The trained dataset is originally from the IBM Sample Datasets. The objective is to predict behavior to retain customers by analyzing all relevant customer data and developing focused customer retention programs. The dataset can be found on Kaggle. It includes following information:

• Customers who left within the last month – the column is called Churn
• Services that each customer has signed up for – phone, multiple lines, internet, online security, online backup, device protection, tech support, and streaming TV and movies
• Customer account information – how long they’ve been a customer, contract, payment method, paperless billing, monthly charges, and total charges
• Demographic info about customers – gender, age range, and if they have partners and dependents

Details

• Number of Rows: 7043 (Customers)
• Number of Columns: 21 (Features)
• Missing Attribute Values: Yes
• Class Distribution: (churn value Yes is interpreted as "customer churn")

🧰 Dependecies

streamlit

pandas==1.4.4

scikit-learn==1.2.1

⚙️ Installation

Clone the repository and install the required dependencies using the following commands:

git clone https://github.com/Priyanshu88/Telecom-Churn-Prediction-Streamlit-App.git

cd Telecom-Churn-Prediction-Streamlit-App

pip install -r requirements.txt

streamlit run app.py

⏯️ Usage

1. Open the app in your web browser.
2. Enter the required information in the input fields.
3. Click the 'Predict' button to generate the prediction.

🚧 Inputs

Click on the link and reboot the tool or run locally and enter following details:

• Tenure (months)
• Phone Service: 0 or 1
• Contract: 0 - Month-to-month, 1 - One year, 2 - Two year
• Paperless Billing: 0 or 1
• Payment Method: 0 - Bank transfer (automatic), 1 - Credit card (automatic), 2 - Electronic check, 3 - Mailed check
• Monthly Charges

🚀 Outputs

The app will display following messages:

• "The customer is likely to churn." or "The customer is unlikely to churn."
• "The probability of churn is: (X, Y)".

🚩 Deployment and Notebook

This tool has been deployed using Streamlit. Learn about streamlit deployment here. Checkout the notebook repository here from where the pickle file has been imployed in the tool.

⚖️ License

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

🤝 Contact

Your Name - @twitter_handle - 2040020@sliet.ac.in

Project Link: https://github.com/Priyanshu88/Telecom-Churn-Prediction-Streamlit-App.git

---

Don't forget to leave a star ⭐️