Decision tree model. Grey nodes are called internal nodes and the orange ones, which represent the tree predictions, leaf nodes. Features are indicated with x1,  x2,  x3, or x4 and predictions with ỹ. Every internal node is labelled with an input feature. The arcs coming from a node labelled with an input feature (for example x4) to a leaf node (orange) are labelled with each of the possible values of the target feature (for example ỹ = 2.5 or $\stackrel{\sim }{y}=5.4$); otherwise the arc leads to a subordinate decision node on a different input feature. For example the arcs starting from the node labelled x2 lead to decisions based on the value of x4 and x1.