Predicting Customer Churn in a Telecommunications Company

Using a dataset of at least 10,000 customers, including demographic information, service usage, payment history, and customer support interactions, develop a comprehensive predictive model to identify customers at risk of churn. Consider using machine learning algorithms such as logistic regression, decision trees, or random forests. Evaluate the model's performance using metrics such as accuracy, precision, recall, and F1 score. Provide recommendations for actionable steps the company can take to reduce churn among high-risk customers. Assume the given dataset has been pre-processed and is in a pandas dataframe format. As of 2026-05-20, provide a detailed analysis of the model's performance and its implications for the company's customer retention strategy.