Decision Tree

A decision tree splits the dataset based on feature thresholds

• True

• False

Decision trees can handle which types of data?

• Only numerical

• Only categorical

• Both numerical and categorical

• Only binary

Each leaf node of a decision tree corresponds to

• A splitting criterion

• A predicted class or output value

• A continuous attribute

• A missing feature

Each internal node of a decision tree represents:

• A class label

• A data point

• A test on an attribute (feature)

• A leaf node

What is the main goal of a decision tree algorithm?

• To cluster data into similar groups

• To learn decision rules that predict the target variable

• To reduce data dimensionality

• To optimize linear regression coefficients

Which of the following is used to measure impurity in a decision tree?

• Covariance

• Gini Index and Entropy

• Correlation coefficient

• Variance inflation factor

Entropy in information theory measures:

• The level of randomness or impurity in data

• The distance between data points

• The variance of features

• The number of features in a dataset

What is the formula for Entropy for a binary classification problem?

• -p₁log₂ p₁ -p₂ log₂ p₂

• p₁ + p₂

• ∑(p_i)²

The Gini Index reaches its minimum value when:

• All classes are equally probable

• All samples belong to one class

• The dataset has missing values

• The features are independent

Information Gain is defined as:

• Entropy before split – Entropy after split

• Gini after split – Gini before split

• The variance of the node

• The number of leaf nodes