• Customer churn is a critical challenge faced by telecom companies. Identifying customers who are likely to churn can help businesses take proactive measures to retain them.

• Churn, in this context, refers to the situation where customers terminate their subscriptions or switch to a competitors telecom service.

• By predicting churn in advance, telecom companies can proactively implement strategies to retain at-risk customers and minimize revenue loss.

Download the dataset for custom training data.

The dataset consists of historical customer information, service usage, and churn status.

The project is organized into the following directories and files:

• Data: The data folder contains both raw and processed data used in this project.
• Notebooks: This folder contains Jupyter notebooks with code covering data exploration, model building, and evaluation.
• Models: This folder houses a collection of trained machine learning models.
• Reports: This folder contains project reports, such as a Power BI data analysis report.
• images: This folder contains all the relevant images used in this project, such as those used in document preparation, presentation materials, and visual aids to enhance understanding.
• Static: This folder includes static files used in the project, such as images, stylesheets.
• Templates: The templates folder contains HTML templates used for rendering web pages.
• app.py: This is the main application file that runs the project's web application.
• Requirements: This requirements text file contains all the required dependencies that we need to install to run the project.

To get started with the project, follow these steps:

1. Clone this repository to your local machine:

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

2. Install the project dependencies by running the following command:

pip install -r requirements.txt

3. Explore the project's directories and files to become familiar with its structure.

4. To run the project, execute follwoing commad:

python app.py

Once you've successfully installed and run the project, you can use it to predict customer churn. Here's how to get started:

1. Open your web browser and navigate to

http://127.0.0.1:5000/

2. You will be presented with a user-friendly web app interface. Explore the available features and prediction options.

3. Follow the on-screen instructions to input customer data and harness the prediction feature to anticipate future customer churn outcomes.

4. The web app should provide you with results based on your input.

5.After reviewing the results, you can take appropriate actions, make informed decisions, and apply the project to specific use cases, such as implementing attractive customer offers.

To deploy this project, follow these steps:

1. Choose a hosting platform or service for your web application. Popular choices include Heroku, AWS, Azure, or PythonAnywhere.

2. Set up an account on the selected hosting platform if you don't already have one.

3. Prepare your project for deployment by making sure it meets the requirements of the chosen hosting service. This may include adjusting configuration files, environment variables, or dependencies.

4. Deploy your project to the hosting platform using the platform's provided deployment tools or instructions.

5. Once deployed, you can access your project by navigating to the URL provided by the hosting platform.

For more detailed deployment instructions specific to your chosen hosting service, refer to their official documentation and guidelines.

Enjoy using the deployed version of the Telecom Churn Prediction project!

🚀 View Deployed Web App

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

The MIT License is a permissive open source license that allows you to use, modify, and distribute this project for both commercial and non-commercial purposes.

If you have any feedback, suggestions, or questions regarding the project, please create an issue in the repository or contact me at [email protected].

Your star is a great way to let us know you appreciate our work and find value in this project. Thank you! ⭐

Happy analyzing and predicting❤️!