Decision trees are the type of supervised machine learning algorithm where decision-making is done using trees. The data is split between the states according to the given parameter.

The leaf node decides the final decision for the given branch of the tree.

For example, Consider a loan provider company that has the data of the customer and asks you to create a model that can tell them whether they should give the loan to the person or not.

Decision trees are fairly easy to understand, After analyzing the above tree you can easily understand the total process of the decision tree.

The above tree is a binary tree as the decision can either be Yes or it can be No. These trees are known as Classification Trees as you are trying to classify the input data into one of the categories.

We also have Regression Trees where the output is not binary. For example, a model to detect the salary of a soccer player using the data present for many soccer players.

We are going to discuss a lot about the decision trees in the upcoming days and this is the page that will be updated whenever a new post is available.

Regression Trees

As already discussed, regression tree based models gives the output (leaf nodes) as a real value.

For example a model which try to predict the salary of baseball players according to the data like, years of experience and number of hits that the hitter made in the last season. Read more about Regression Trees in the post below.

Classification Trees

Classification Trees are the trees in which we classify the values as the output of the model.

For example, predicting whether you want to give loan to the incoming customer or not.