Decision Tree in AI: Introduction, Types & Creation

A Decision tree is the denotative representation of a decision-making process. Decision trees in artificial intelligence are used to arrive at conclusions based on the data available from decisions made in the past. Further, these conclusions are assigned values, deployed to predict the course of action likely to be taken in the future.

Decision trees are statistical, algorithmic models of machine learning that interpret and learn responses from various problems and their possible consequences. As a result, decision trees know the rules of decision-making in specific contexts based on the available data. The learning process is continuous and based on feedback. This improves the outcome of learning over time. This kind of learning is called supervised learning. Therefore, decision tree models are support tools for supervised learning.

Thus, decision trees provide a scientific decision-making process based on facts and values rather than intuition. In business, organizations use this process to make significant business decisions.

Must Read: How to Create Perfect Decision Tree 

Type of Decision Tree Models

These models can be used to solve problems depending upon the kind of data that requires prediction. They fall into the following categories:

  1. Prediction of continuous variables
  2. Prediction of categorical variables

1. Prediction of Continuous Variables

The prediction of continuous variables depends on one or more predictors. For instance, the prices of houses in an area may depend on many variables such as an address, availability of amenities like a swimming pool, number of rooms, etc. In this case, the decision tree will predict a house’s price based on various variable values. The predicted value will also be a variable value. 

The decision tree model used to indicate such values is called a continuous variable decision tree. Continuous various decision trees solve regression-type problems. In such cases, labeled datasets are used to predict a continuous, variable, and numbered output.

2. Prediction of Categorical Variables

The prediction of categorical variables is also based on other categorical or continuous variables. However, instead of predicting a value, this problem is about classifying a new dataset into the available classes of datasets. For example, analyzing a comment on Facebook to classify text as negative or supportive. Performing diagnosis for illness based on a patient’s symptoms is also an example of a categorical variable decision tree model. Categorical variable decision trees solve classification-type problems where the output is a class instead of a value.

Check out: Decision Tree in R

How Decision Trees in Artificial Intelligence Are Created

As the name suggests, the decision tree algorithm is in the form of a tree-like structure. Yet, it is inverted. A decision tree starts from the root or the top decision node that classifies data sets based on the values of carefully selected attributes.

The root node represents the entire dataset. This is where the first step in the algorithm selects the best predictor variable. It makes it a decision node. It also classifies the whole dataset into various classes or smaller datasets.

The set of criteria for selecting attributes is called Attribute Selection Measures (ASM). ASM is based on selection measures, including information gain, entropy, Gini index, Gain ratio, and so on. These attributes, also called features, create decision rules that help in branching. The branching process splits the root node into sub-nodes, splitting further into more sub-nodes until leaf nodes are formed. Leaf nodes cannot be divided further.

Determining whether a given picture is that of a cat or a dog is a typical example of classification. Here, the features or attributes could be the presence of claws or paws, length of ears, type of tongue, etc. The dataset will be split further into smaller classes based on these input variables until the result is obtained.

Also Read: Classification in Decision Tree


Decision trees are classic and natural learning models. They are based on the fundamental concept of divide and conquer. In the world of artificial intelligence, decision trees are used to develop learning machines by teaching them how to determine success and failure. These learning machines then analyze incoming data and store it.

Then, they make innumerable decisions based on past learning experiences. These decisions form the basis for predictive modeling that helps to predict outcomes for problems. In business, organizations use these techniques to make innumerable small and big business decisions leading to giant gains or losses.

If you’re interested to learn more about machine learning, check out IIIT-B & upGrad’s PG Diploma in Machine Learning & AI which is designed for working professionals and offers 450+ hours of rigorous training, 30+ case studies & assignments, IIIT-B Alumni status, 5+ practical hands-on capstone projects & job assistance with top firms.

Lead the AI Driven Technological Revolution

Apply Now @ UPGRAD

Leave a comment

Your email address will not be published.

Accelerate Your Career with upGrad

Our Popular Machine Learning Course