Which technique is used to convert a categorical feature into a binary format, with each category represented as a separate binary feature?

One-hot encoding is the technique used to convert a categorical feature into a binary format, where each category is represented as a separate binary feature. This method creates new binary columns for each unique category in the original feature, where each column indicates the presence (1) or absence (0) of that category for a given observation.

For instance, if you have a categorical feature "Color" with the categories "Red," "Green," and "Blue," one-hot encoding will create three new columns: one for Red, one for Green, and one for Blue. Each row will have a value of 1 in one of these columns and 0s in the others, effectively transforming the single categorical feature into three binary features.

This technique is particularly useful in machine learning algorithms that require numerical input, ensuring that the model can learn patterns without implying any ordinal relationship between the categories, which is not the case with categorical data.