Customer churn (aka customer attrition) occurs when customers or subscribers stop doing business with a company or service.
It is a critical metric because it is much less expensive to retain existing customers than it is to acquire new customers.
This model predicts if a customer is likely to churn or not.
The dataset has been taken from Kaggle.
A neural network with 2 hidden layers has been implemented using Keras.
The model has been made into a Flask web application. Install flask (using, say pip install flask), and run the server by executing app.py file. Then open up port 5000 on a browser and proceed.
Please see Logistic-Regression.ipynb, NN-cat.ipynb for details. Reference : Coursera