What is a feature in machine learning?

• A. An input variable used by a model to make predictions.
• B. A model parameter updated during training.
• C. The final prediction of the model.
• D. A data visualization.

Answer: (A)

Features in machine learning are the input variables that describe each data instance and are used by the model to make predictions. They come from the data you observe about each example—things you measure or derive—that the model uses to infer the target outcome. Features can be numbers, categories (often encoded), text, or other observable attributes. During training, the model learns how to weigh these features to produce accurate predictions, but the features themselves are the information fed into the model, not the internal parameters or the output.

This distinguishes them from model parameters, which are the adjustable values like weights and biases learned during training; from the final prediction, which is the model’s output given the features; and from a data visualization, which is a tool for exploring data rather than a component used to make predictions. For example, in predicting house prices, features might include square footage, location, and number of bedrooms—the inputs the model uses to estimate the price.