This project analyzes customer churn data to identify the factors that contribute to customer attrition and provides insights to help reduce churn.
The purpose of this project is to analyze customer churn data and identify the factors that contribute to customer attrition. By analyzing the dataset, we aim to provide insights that can help reduce churn and improve customer retention.
The dataset used in this project is the Telco_customer_churn_csv file. It contains customer information and churn data, including customer demographics, contract information, service usage, and churn reasons. The dataset is provided in a CSV format and can be found in the root directory of the project.
To run this project, you will need to have Python 3.x and several libraries installed, including pandas, matplotlib, and scikit-learn. You can install these libraries using pip, by running the following command:
To use this project, you can open the CustomerChurn.ipynb Jupyter Notebook file, which contains the code used for analyzing the dataset. The Notebook includes step-by-step instructions for loading the dataset, performing data preprocessing, and analyzing the data to identify factors that contribute to customer churn. The Notebook also generates several visualizations to help understand the data.
Based on our analysis, we found that the top three reasons for customer churn are competition, support or service issues, and dissatisfaction. We also found that customers who churn after the first period are more likely to be dissatisfied with the support or service they received.
Our machine learning model achieved an accuracy of 90%, and we identified the most important features for predicting churn, including contract type, tenure, and monthly charges.
If you would like to contribute to this project, please submit a pull request with your proposed changes.