Customer Churn Predictor

Customer Churn Predictor

Predicts whether a telecom customer is likely to leave, using a scikit-learn model in a small Gradio app. Suits analysts and students who want a working churn example to try or copy.

Made by Saryy77 on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Space predicts customer churn for a telecom company. A scikit-learn model sits behind a small Gradio page, so you enter details about a customer and read the model's guess about whether they will leave.

Who it suits: Analysts, retention teams and students who want a small, working churn example they can open in a browser or copy to their own machine.

Industry | Who uses it | How they use it | Example
Telecom | Retention analysts | Check which customers look likely to leave | Enter one customer's details and read the prediction
Subscription services | Product managers | Study how a churn model is presented to a team | Open the page and see which inputs it asks for
Education | Data science students | Learn how a trained model becomes an app | Download the three files and read app.py
Consulting | Data consultants | Show a client a simple demo | Share the Space page as a quick prototype

If you need a model trained on your own customer data, this demo is a starting point at best.

Where to use it: It runs in two places.

• A web browser, on the Space's page at Hugging Face with nothing to install
• A local copy on Windows, macOS or Linux, which needs Python 3.12

Use case | Who | What they get back
Score one customer | Retention analysts | A prediction on whether the customer may churn
Demo a model | Consultants | A page a client can open and try
Study the code | Students | A short app.py and a requirements.txt to read

How to set it up: Using it online needs nothing. A local copy needs a few things.

• Python 3.12 and pip
• The packages listed in requirements.txt

1. Install the Hugging Face tools.
2. Download the Space into a folder.
3. Move into that folder.
4. Install Gradio and the packages from requirements.txt.
5. Start the app.

pip install -U huggingface_hub
hf download Saryy77/customer-churn-predictor --repo-type space --local-dir customer-churn-predictor
cd customer-churn-predictor
pip install gradio==6.31.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space, fill in the customer fields the page shows and submit them. The page then shows the model's churn prediction for that customer. Run python app.py in a local copy to get the same page on your own computer.

Example: You enter the details of one phone customer and submit the form. The page replies with the model's prediction on whether that customer is likely to leave.

For newcomers and experts: Churn means a customer stops paying. Open the page, change one input at a time and watch how the prediction moves. That shows you which details the model leans on.

The model is a scikit-learn one, and Gradio wraps it in a web form. The repository is tiny, with a README, app.py and requirements.txt, so the whole pipeline is easy to read. It runs on zero-a10g hardware at Hugging Face.

You fill in the customer details
The Gradio page sends them to the model
The scikit-learn model predicts churn
The page shows the result

Good to know: The README says little, so details such as the training data and the accuracy are not documented.

• License: MIT
• Cost to run: none named
• Data it reaches: only what you type into the form

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/Saryy77/customer-churn-predictor
• Files: https://huggingface.co/spaces/Saryy77/customer-churn-predictor/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.