## Decision Tree Machine Learning

Decision tree learning is one of the predictive model approaches used in statistical data mining and machine learning. It uses the decision tree as a predictive model to move from observations of an item represented in industries to conclusions regarding the target value of the item represented by an owner.

Models of trees in which the target variable can take a separate set of values ​​are called trees for classification in these tree structures Leaves represent class labels and branches represent attribute combinations leading to the same class characters.

Decision trees where the target variable can take consecutive values ​​are usually real numbers called regression trees. Decision trees are among the most popular algorithms of decision tree machine learning given their understanding and simplicity.

Learning gradient boosted decision trees is a common method in data mining. The goal is to create a model that predicts the value of a target variable based on several input variables.

A decision tree is a simple representation for classifying examples. For this section let’s assume that each input attribute has finite separate domains and there is one target attribute called “classification”. Each component in the classification field is called a class. A decision tree python or classification tree is a tree where each internal node that is not a leaf is tagged in an input attribute algorithm.

The arcs coming from a node labeled input attribute are tagged with each of the possible values ​​of the target attribute or the arc leads to a decision node subject to another input attribute.

Each leaf of the tree is labeled with a class or probability distribution across the classes indicating that the data set has been classified by the tree into a specific class or specific probability distribution that if the decision tree machine learning is well constructed is biased. Towards certain subgroups of lessons.

A tree is built by splitting the source array that forms the root junction of the tree into subgroups - which constitute the inheriting children.

The split is based on a set of split rules based on classification properties. This process is repeated in each recursive subgroup called a recursive partition. The recursion is completed when the node subunit includes all those values ​​of the target variable or when a split no longer adds value to predictions.

This process of top-down induction of gradient boosted decision trees TDIDT is an example of a greedy algorithm and is without a doubt the most common strategy for learning machine decision trees from data.

In data mining trees can be described as a combination of mathematical and computational techniques that help classify the description and generalize a given data set.

#### Decision Tree Classification Algorithm

• The decision tree python is a supervised learning algorithm technique that can be used for both classification problems and regression problems but is mostly preferred for solving classification problems. It is a tree-built classifier where internal nodes represent the properties of data array branches representing the decision rules and each leaf node represents the result.

• In the boosted decision tree machine learning there are two nodes which are the decision junction and the leaf junction. Decision nodes are used to make each decision and have multiple branches whereas leaf nodes are the output of these decisions and do not contain additional branches.

• Decisions or testing are made based on the characteristics of the given data set.

• This is a graphical representation for making all possible solutions to a problem/decision based on given conditions.

• It is called a decision tree machine learning because like a tree it starts at the root junction that expands on additional branches and builds a tree-like structure.

• To build a learning decision tree we use the CART algorithm which represents a classification and regression tree algorithm.

• A boosted decision tree machine learning simply asks a question and based on the answer yes/no it splits the tree into subtrees.