Decision Tree Learning

What is Decision Tree Learning?

Decision Tree Learning is a technique used in machine learning. Decision trees are a widely used way of regression or classification over a large, diverse data set. Areas of application are the classification of the creditworthiness of bank customers or a function for the prediction of purchasing power.

Decision trees are a popular tool in computer science and mechanical engineering for design structures. In data science, algorithms are used that Automatically generate tree structures from a set of known data and an automatic Classification or regression can make. Decision trees are used in supervised machine learning to form hierarchical structures with as few decision paths as possible.

Elements of a decision tree

A decision tree consists of nodes, edges and leaves. The nodes are used to test for a value of a certain attribute. The edges correspond to a final result of a test and they connect to the next node or leaf. The leaves are end nodes that predict the result. A classification then goes as follows.

  1. Start at the root node
  2. Perform the test
  3. Sequence of the corresponding edge to the result
  4. As long as it is not a leaf, go back to 2. and repeat the process
  5. Make a prediction for the outcome associated with the leaf

In decision tree learning, a new example is classified and sent through a series of tests to obtain a class label for the example. These tests are organised in a hierarchical structure called a decision tree. The training examples are used to select appropriate tests in the decision tree. The tree is built from top to bottom, with tests that maximise the information gain about the classification being selected first.

What is Decision Tree Learning used for?

A decision tree is used as a predictive model to reach conclusions about the corresponding target value of an element represented in the branches by making observations about the element represented in the leaves. Decision Tree Learning is one of the predictive modelling approaches for statistics, machine learning and Data mining. The tree models where the target variable assumes a certain discrete range of values are called classification trees. The leaves of the tree structures represent class labels and the branches represent connections of the features and these lead to class labels. If target variables lead to continuous values (real numbers), these decision trees are called regression trees

What are Random Forests?

Random forests are decision forests that consist of a large number of decision trees. A decision tree is a tree-like and directed diagram for decision-making. A decision tree is a mathematical model and diagram for determining decisions.

Data Navigator Newsletter