A company has historical labels indicating whether customers required long-term support. They need an ML model to predict whether new customers will require long-term support. Which modeling approach is appropriate?

Logistic regression is appropriate because the problem involves predicting a binary outcome: whether a customer will or will not require long-term support. This is a classification task. Logistic regression models the probability of a binary outcome using a sigmoid function. Anomaly detection is for identifying unusual data points, not predicting a specific binary class. Linear regression is used for predicting continuous numerical values, not categorical outcomes. Semantic segmentation is a computer vision technique for classifying pixels in an image, which is irrelevant to this customer prediction problem.