Predictive Analytics with Microsoft Azure Machine Learning by Roger Barga Valentine Fontama & Wee Hyong Tok

Author:Roger Barga, Valentine Fontama & Wee Hyong Tok
Language: eng
Format: epub
Publisher: Apress, Berkeley, CA

Decision Trees

Decision tree algorithms are hierarchical techniques that work by splitting the dataset iteratively based on certain statistical criteria. The goal of decision trees is to maximize the variance across different nodes in the tree and minimize the variance within each node. Figure 6-3 shows a simple decision tree created with two splits of the data. The root node (Node 0) contains all the data in the dataset. The algorithm splits the data based on a defined statistic, creating three new nodes (Node 1, Node 2, and Node 3). Using the same statistic, it splits the data again at Node 1, creating two more leaf nodes (Nodes 4 and 5). The decision tree makes its prediction for each data row by traversing to the leaf nodes (one of the terminal nodes: Node 2, 3, 4, or 5).

Figure 6-3.A simple decision tree with two data splits

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.