For what kind of targets is the Auto Classifier node used to create and compare models?

The Auto Classifier node is specifically designed for creating and comparing models that predict categorical targets. In predictive analytics, a categorical variable is one that can take on a limited, fixed number of possible values, which can be symbols or categories but not a continuous range of values.

When building classification models, the goal is to assign observations to one of several predefined classes based on the input features. This makes categorical targets the perfect fit for the Auto Classifier node, as it processes the data to derive models that can accurately predict these class memberships.

While nominal categories (a subset of categorical) involve categories with no inherent order, categorical as a broader term encompasses both nominal and ordinal categories. Thus, saying that the Auto Classifier node is used for categorical targets captures its intended function and avoids the narrower scope of nominal classifications. This distinguishing feature of the Auto Classifier node is essential for users looking to understand its application in predictive modeling.