Which ML algorithm is commonly used for predicting continuous outcomes?

Linear regression is primarily used for predicting continuous outcomes. This algorithm establishes a relationship between one or more independent variables and a dependent variable by fitting a linear equation to observed data. The goal is to model the relationship so that when new data points are introduced, predictions about the continuous outcome can be made accurately.

In linear regression, the output is a continuous value, which is ideal for scenarios like predicting sales revenue, temperature, or any measurable quantity. The model's simplicity and interpretability make it particularly useful in many applications involving regression tasks in machine learning.

Other algorithms mentioned, such as logistic regression, are typically used for classification tasks where the outcomes are categories rather than continuous values. Naive Bayes is also a classification algorithm that relies on applying Bayes' theorem with strong independence assumptions between features. While random forests can handle regression tasks and manage continuous outcomes, their primary application is in scenarios involving more complex relationships and interactions among variables. Linear regression's direct focus on continuous outcomes classifies it distinctly as the correct choice for this question.