Our task involves predicting customer behavior (churn, stay, or join) for a telecommunications company by analyzing demographic, location, and tenure data. The dataset consists of 6500 customer records alongside zip code population data.
By employing machine learning techniques, we aim to develop a predictive model that accurately forecasts customer behavior. This model will help identify key factors influencing customer decisions, enabling the company to tailor its strategies for retention, acquisition, and overall customer satisfaction.
Our approach will include data preprocessing, feature engineering, and the use of classification algorithms to achieve robust and actionable insights.
We are utilizing AI-ready datasets on YouData.ai platform.
-Link to the dataset from the YouData.ai platform
| Machine Learning Models Applied | Accuracy |
|---|---|
| Logistic Regression | 78.28% |
| Naive Bayes Gaussian | 36.77% |
| Decision Tree | 77.29% |
| XGB_Classifier | 80.86% |
The ability to predict churn before it happens allows businesses to take proactive actions to keep existing customers from churning. This could look like:
Customer success teams reaching out to those high-risk customers to provide support or to gauge
what needs may not be being met.
The advantage of calculating a company's churn rate is that it provides clarity on how well the business is retaining customers, which is a reflection on the quality of the service the business is providing, as well as its usefulness.
This project follows the MIT LICENSE.