A team is building a machine learning model to predict the risk of heart disease. The dataset includes input features (age, cholesterol, blood pressure, smoking, exercise) and a label indicating whether each patient has heart disease. Which ML approach is appropriate?

Supervised learning is appropriate because the dataset includes both input features (age, cholesterol, blood pressure, smoking, exercise) and a corresponding label (whether each patient has heart disease). This means the model can learn a mapping from inputs to outputs based on labeled examples. Unsupervised learning is used when there are no labels, focusing on finding patterns or structures in the data. Reinforcement learning involves an agent learning through trial and error with rewards and penalties in an environment, which doesn't fit this predictive task. Semi-supervised learning uses a small amount of labeled data with a large amount of unlabeled data, which is not indicated here as the dataset has a clear label for each patient.