Decision tree

A decision tree shows a connected hierarchy of boxes to represent the values of records.

Records are segmented into groups, which are called nodes. Each node contains records that are statistically similar to each other with respect to the target field. For example, a node might contain the records for males who have more than 18 years of education. Nodes can then be used to predict a target's field value. For example, the node about males and education might be used to predict salary.

Each branch in a decision tree corresponds to a decision rule. For more info about decision rules, see Viewing decision rules

To improve performance, due to number of rows in the data source, the analysis is based on a representative sample of the entire data.

For example, a decision tree visualization can look like this:

For more information, see Exploring a decision tree visualization.