Scribd
Upload
3 views9 pages

Decision Trees - Pres

Decision trees are a supervised learning algorithm used in machine learning for modeling and predicting outcomes based on input data, applicable for both classification and regression tasks. Key concepts include nodes and edges, splitting criteria, and pruning to enhance model performance while addressing advantages like interpretability and disadvantages such as overfitting. The document outlines the structure of decision trees, methods for splitting, and their pros and cons.

Uploaded by

alirehman123001
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
3 views9 pages

Decision Trees - Pres

Decision trees are a supervised learning algorithm used in machine learning for modeling and predicting outcomes based on input data, applicable for both classification and regression tasks. Key concepts include nodes and edges, splitting criteria, and pruning to enhance model performance while addressing advantages like interpretability and disadvantages such as overfitting. The document outlines the structure of decision trees, methods for splitting, and their pros and cons.

Uploaded by

alirehman123001
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

Title:

Decision
Trees
(Supervised Learning
Algorithms)

Mutayyab Zubair
Decision Trees

01 02
A DECISION TREE IS A TYPE OF ITS STRUCTURES
SUPERVISED LEARNING DECISIONS BASED ON
ALGORITHM THAT IS INPUT DATA, MAKING IT
COMMONLY USED IN MACHINE
LEARNING TO MODEL AND SUITABLE FOR BOTH
PREDICT OUTCOMES BASED CLASSIFICATION AND
ON INPUT DATA. REGRESSION TASKS
Key Concepts of Decision Trees
1. Nodes and Edges
2. Splitting
3. Criteria for Splitting
4. Pruning
5. Advantages and Disadvantages
Nodes and Edges
o Root Node: The top node of the tree representing the
entire dataset, which is then split into subsets.
o Internal Nodes: Nodes that represent feature tests and
have one or more branches (edges).
o Leaf Nodes: Terminal nodes that represent the final
output or class labels for classification tasks or continuous
values for regression tasks.
Splitting:

o The process of dividing a node into two or more sub-


nodes based on a feature that results in the highest
information gain or the best split.
Criteria for Splitting
o Gini Impurity: Measures how often a random element would be
incorrectly labeled if it was randomly assigned a label.
o Entropy (Information Gain): Measures the impurity or
randomness in the dataset. Information gain is the reduction in entropy
after a dataset is split on a feature.
o Mean Squared Error (MSE): Used in regression tasks to measure
the variance of the target values within the subsets.
Pruning:

o The process of removing sections of the tree that provide little


power in predicting target variables. This helps to prevent
overfitting.
Advantages:
 Easy to Interpret: The tree structure is easy to understand and
visualize.

 Handles Both Numerical and Categorical Data: Can be used for


various types of data without much preprocessing.

 Requires Little Data Preparation: Does not require normalization


or scaling of data.
Disadvantages:
Overfitting: Decision trees can create overly complex trees that do not
generalize well to new data.
Bias to Dominant Classes: If some classes dominate, the tree may
become biased towards those classes.
Instability: Small changes in the data can result in a completely
different tree structure.

You might also like