Caesar AI Atlas

Synthetic Feature

Caesar AI Atlas Definition

A synthetic feature is a feature created from one or more existing input features rather than directly observed in the raw data. Common methods include bucketing, feature crosses, mathematical transformations, and combinations of existing feature values.

Other Definitions

Synthetic Feature Source

A feature not present among the input features, but assembled from one or more of them. Methods for creating synthetic features include the following: - Bucketing a continuous feature into range bins. - Creating a feature cross. - Multiplying (or dividing) one feature value by other feature value(s) or by itself. For example, if and are input features, then the following are examples of synthetic features: - ab - a^2^ - Applying a transcendental function to a feature value. For example, if is an input feature, then the following are examples of synthetic features: - sin(c) - ln(c) Features created by normalizing or scaling alone are not considered synthetic features.

Related Terms