/customer-churn

Using a Telecom's dataset, this project develops both an analysis to understand possible correlations and a model for predicting customer churn.

Primary LanguageJupyter NotebookMIT LicenseMIT

Table of Contents

  1. Installation
  2. Project Motivation
  3. File Descriptions
  4. Results
  5. Licensing, Authors, and Acknowledgements

Installation

All the necessary libraries to run the code were already available in Anaconda distribution of Python. This script was written using Python version 3.*.

Project Motivation

For this project, my intention was to better undestand motivations and/or possible correlations affecting customer churn's rate, along with the creation of a predictive model capable of identifying whether a client is likely to cancel its relationship with the company or not.

File Descriptions

  1. Notebooks - Jupyter Notebook in Portuguese version with the script developed for creating the predictive model.
  2. Csv files - a copy of the .csv files used in the project, containing separated train and test data.

Results

The results are communicated in the notebook cells annotating insights and process decisions.

Licensing, Authors, Acknowledgements

Credits must give credit to Data Science Academy for making this data available as part of an optional project suggested for one of the courses offered in the company's platform. This project is under MIT License.