At EasyTechJunkie, we're committed to delivering accurate, trustworthy information. Our expert-authored content is rigorously fact-checked and sourced from credible authorities. Discover how we uphold the highest standards in providing you with reliable knowledge.

Learn more...

What Is Decision Tree Learning?

K.C. Bruning
K.C. Bruning

Decision tree learning uses a predictive model with informational branches similar to a tree to gather assumptions about and make a judgment on an item’s value. The system is used for machine learning, statistics, and data mining. Decision trees are also known as regression or classification trees, depending upon the purpose for which they are used.

The process of decision tree learning involves moving from branch to branch of information. Upon reaching each element, whether via computer or a person, it must be determined whether or not it applies to the target item. Once each branch has been explored, the answers can be used to determine value.

Woman doing a handstand with a computer
Woman doing a handstand with a computer

In essence, decision tree learning is the process of answering questions. Each answer moves the process forward until there is enough information to make a decision. For example, a simple tree may start by asking which of two objects to buy. One question may ask whether the object is useful, while another could ask whether one item has a better price than the other. By asking all of these questions it is typically possible to determine which action is statistically more beneficial.

Decision tree learning also explores sub categories. Answering one question may lead to another. This could result in some branches having many sub branches, while others are less elaborate because it is easy to answer the question. Pursuing the process in this fashion enables the user to develop a more detailed assessment of the item.

Another possible use of decision tree learning is categorization. Rather than having each question lead to a single decision, a body of information is divided into different areas, based on the answer for each branch. Once all branches have been categorized, the same process may also be run on each category.

Decision tree learning typically progresses from the top level down. It does not tend to backtrack. Once a question has been fully answered, there is usually no need to refer to it again until the results are being compiled.

The results of decision tree learning can be expressed in a variety of ways. They may be the answer to a yes or no question or a number such as a price or a period of time. Results may also reveal the identity of a certain object and thus name the class in which it belongs.

Discuss this Article

Post your comments
Forgot password?
    • Woman doing a handstand with a computer
      Woman doing a handstand with a computer