Scribd
Upload
8 views2 pages

Decision Tree Rules Study Notes

Decision trees are a supervised classification method characterized by nodes, branches, and paths that lead to class descriptions. Converting decision trees to IF-THEN rules enhances understanding and simplifies pruning decisions, allowing for easier interpretation and potential rule combination. The quality of the decision tree and rules is contingent on the representativeness of the training sample used.

Uploaded by

sundar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views2 pages

Decision Tree Rules Study Notes

Decision trees are a supervised classification method characterized by nodes, branches, and paths that lead to class descriptions. Converting decision trees to IF-THEN rules enhances understanding and simplifies pruning decisions, allowing for easier interpretation and potential rule combination. The quality of the decision tree and rules is contingent on the representativeness of the training sample used.

Uploaded by

sundar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Decision Tree Rules - Study Notes

DECISION TREE RULES

The decision tree method is a popular and relatively simple supervised classification method. It

involves:

1. Nodes: Each node of the tree specifies a test of some attribute.

2. Branches: Each branch corresponds to one of the values of the attribute.

3. Paths: Each path from the root to a leaf of the decision tree consists of attribute tests, finally

reaching a leaf that describes the class.

The popularity of decision trees is due to the ease of understanding the rules specified by the

nodes. These rules can even be used to retrieve data from a relational database satisfying the rules

using SQL.

Advantages of Converting Decision Trees to Rules:

1. Ease of Pruning Decisions:

- It is easier to see the context of each rule.

2. Better Understanding:

- Rules remove the distinction between attribute tests near the root and those near the leaves.

- Rules are easier to read and understand compared to a decision tree.

IF-THEN Rules:

- Derived Rules: Rules are derived from the paths from the root to the leaf nodes.

- A simple approach generates as many rules as there are leaf nodes.

- Rules can often be combined to produce a smaller set of rules.


Example Rules:

1. If Gender = "Male", then class = B.

2. If Gender = "Female" and Married = "Yes", then class = C; otherwise, class = A.

Simplification of Rules:

1. Simplifying Rules:

- Rules with only one antecedent (e.g., "If Gender = 'Male' then class = B") cannot be simplified.

- Only rules with two or more antecedents are considered for simplification.

2. Removing Unnecessary Antecedents:

- Unnecessary rule antecedents that do not affect the conclusion may be removed.

3. Combining Rules:

- Rules leading to the same class may be combined.

Quality of Decision Trees and Rules:

- The quality of the decision tree and the derived rules depends on the training sample.

- If the training sample does not represent the population well, the derived rules may not be reliable.

You might also like