Custоmer churn, which refers tо the lоss of customers who stop using а compаny's product or service, cаn significantly impact revenue. A company has developed a machine learning model to predict churn and evaluates its performance using metrics like accuracy, True Positive Rate (TPR), and the Area Under the ROC Curve (AUC): The model achieves 95% accuracy but has a TPR of only 60%. Its AUC is calculated to be 0.65. The business team is concerned about failing to identify customers at risk of leaving, which could lead to revenue loss. In predicting customer churn, why is TPR an important metric to consider alongside AUC?