The HPFOREST Procedure
Overview: HPFOREST Procedure
The HPFOREST procedure is a high-performance procedure that creates a predictive model called a forest that consists of several decision trees. A predictive model defines a relationship between input variables and a target variable. The purpose of a predictive model is to predict a target value from inputs. The HPFOREST procedure trains the model; that is it creates the model using training data in which the target values are known. The model can then be applied to observations in which the target is unknown. If the predictions fit the new data well, the model is said to generalize well. Good generalization is the primary goal for predictive tasks. A predictive model might fit the training data well but generalize poorly.
A decision tree is a type of predictive model that has been developed independently in the statistics and artificial intelligence communities. The HPFOREST procedure creates a tree recursively. An input variable is chosen and used to create a rule to split the data into two segments. The process is then repeated in each segment, and then again in each new segment, and so on until some constraint is met. In the terminology of the tree metaphor, the segments are nodes, the original data set is the root node, and the final unpartitioned segments are leaves or terminal nodes. A node is an internal node if it is not a leaf. The data in a leaf determine the estimates of the value of the target variable. These estimates are subsequently applied to predict the target of a new observation assigned to the leaf.
The HPFOREST procedure creates decision trees that differ from each other in two ways. First, the training data for a tree is a sample, without replacement, from the original training data of the forest. Second, the input variables considered for splitting a node are randomly selected from all available inputs. Among these variables, the HPFOREST procedure considers only a single variable when forming a splitting rule. The chosen variable is the one that is most associated with the target.
PROC HPFOREST runs in either single-machine mode or distributed mode. In distributed mode, PROC HPFOREST trains decision trees in parallel, and accesses all the data for every tree. Note: Distributed mode requires SAS High-Performance Data Mining .
Copyright © SAS Institute Inc. All rights reserved.