In supervised learning, what does the model use to learn from?

In supervised learning, the model learns from labeled data. This means that the data used for training contains both the input features and the corresponding output labels. Each data point in the training set is paired with the correct answer, allowing the model to understand the relationship between the input and the desired output.

The presence of labels is crucial because it enables the model to make predictions on new, unseen data by recognizing patterns and correlations. The training process involves adjusting the model's parameters to minimize the difference between its predictions and the actual labels, which improves its accuracy over time.

While raw data and historical data can be used in various contexts, they do not inherently provide the labels necessary for supervised learning. Unlabeled data, on the other hand, does not include the output information needed for the model to learn effectively in this framework. Thus, the use of labeled data is fundamental to the supervised learning approach, making it the correct choice in this context.