Predicting Customer Churn

Recently I have done a project as part of Udacity MLops Nanodegree. The project goal was to refactor a jupyter notebook for building a customer churn prediction model by using clean code principles.

In the project, we identify credit card customers that are most likely to churn. The Project will include a Python package for a machine learning project that follows coding (PEP8) and engineering best practices for implementing software (modular, documented, and tested). The package also has the flexibility of being run interactively or from the command-line interface (CLI).

Below are the first few rows associated with the dataset for this project, which was pulled from Kaggle.

After doing the project, I have learned to work with Coding best practices, working with version control and production-ready code. It helped me to write python scripts, modular and reproducible code.

With the passage of time, The main goal of MLOps is to use ML models more efficiently to solve business problems. The smartest of companies are already on the move.