A decision tree is a type of Supervised Learning. In which we continuously split data according to some fixed parameters. It has two entities which are decision nodes and leaves. Where leaves are the final outcome of the decision of the tree and where data splits those are called decision nodes. A decision tree is drawn upside down with its root at the top. In the figure given below, we have made a decision tree to check whether a person is fit or not. Here in decision nodes, we have some parameters like age, eating habit, and exercise and data will split on the nodes to make further nodes or leaves. We can see final outcome which is Fit or Unfit in a particular case.
Decision trees are built using an algorithmic methodology that recognizes approaches to part an informational index dependent on various conditions. It is one of the most broadly utilized and commonsense strategies for supervised learning. Decision Trees are a non-parametric supervised learning strategy utilized for both classification and regression errands.
Here are some common terms which we use in the decision tree.
Branches - Division of the whole tree is called branches.
Root Node - It represents the entity that will be divided further.
Terminal Node - A node that cannot be split further is called a terminal node.
Pruning - Removal of sub-nodes from a decision node.
Splitting - The division of nodes is called splitting.
Decision Node - A node that will be divided further into different sub-nodes and will be a sub-node.
Parent and Child Node - When a node gets divided further then it becomes a parent node and the divided nodes or the sub-nodes become a child node of the parent node.
Applications of the decision tree :
In Business Development
In the previous many years, numerous associations had made their information bases to improve their customer administrations. Decision trees are a potential method to separate helpful data from information bases and they have just been utilized in numerous applications in the space of business and management. Specifically, decision tree displaying is broadly utilized in customer relationship management and misrepresentation identification, which are introduced in subsections beneath.
In Fraud Detection
Another generally utilized business application is the location of Fraudulent Financial Statements (FFS). Such an application is especially significant on the grounds that the presence of FFS may bring about lessening the administration's expense pay (Spathis et al., 2003). A conventional method to recognize FFS is to utilize factual strategies. Notwithstanding, it is hard to find all shrouded data because of the need of making a colossal number of suspicions and reclassifying the relationships among countless factors in a financial explanation.
As decision tree displaying can be utilized for making forecasts, there is an expanding number of studies that examine to utilize decision trees in medical care management. For example, Chang (2007) has built up a decision tree model based on 516 bits of information to investigate the concealed information situated inside the clinical history of formatively deferred youngsters. The made model distinguishes that most sicknesses will bring about postponements in psychological turn of events, language advancement, and engine improvement, of which correctness’s are 77.3%, 97.8%, and 88.6% individually. Such discoveries can bring about helping medical care proficient to have an early intercession on formatively postponed youngsters to assist them with making up for lost time their ordinary friends in their turn of events and development.
To Find Prospective Clients
Another utilization of decision trees is in the utilization of demographic information to discover prospective customers. They can help in smoothing out a promoting financial plan and in settling on educated decisions on the objective market that the business is centered around. Without decision trees, the business may spend its promoting market without a particular demographic as a primary concern, which will influence its general incomes.
To Find Prospective Growth Opportunity
One of the utilizations of decision trees includes assessing prospective development open doors for organizations dependent on recorded information. Recorded information on deals can be utilized in decision trees that may prompt the creation of revolutionary changes in the procedure of a business to help develop and grow.
Advantages of the decision tree
1. It creates a comprehensive analysis of the consequences along each branch and identifies decision nodes that need further analysis.
2. Decision trees assign specific values to each problem, decision path, and outcome.
3. Using specific values identifies the relevant decision paths, reduces uncertainty, clears up ambiguity, and clarifies the financial consequences of various courses of action.
4. The decision tree presents visually all of the decision alternatives for quick comparisons in a format that is easy to understand with only brief explanations.
5. Missing values in the data also do NOT affect the process of building a decision tree to any considerable extent.
6. A decision tree does not require normalization of data.
Disadvantages of Decision Tree
1. A little change in the information can cause an enormous change in the structure of the decision tree causing shakiness.
2. For a Decision tree in some cases, an estimation can go undeniably more mind-boggling contrasted with different calculations.
3. A decision tree frequently includes a higher chance to prepare the model.
4. Decision tree preparation is generally costly as the intricacy and time took are more.
5. The Decision Tree calculation is lacking for applying relapse and anticipating ceaseless qualities.
1. What is Clustering
2. FCM Clustering Algorithm