A supervised learning model that uses a tree-like structure to make decisions.

An unsupervised learning model that uses a tree-like structure to find patterns in data.

A reinforcement learning model that uses a tree-like structure to learn from its environment.

A neural network model that uses a tree-like structure to process data.

They are easy to interpret.

They can handle both categorical and numerical data.

They are robust to outliers.

All of the above.

They can be biased towards the majority class.

They can be sensitive to noise in the data.

They can overfit the data.

All of the above.

ID3

C4.5

CART

All of the above.

ID3 uses information gain to split the data, while C4.5 uses gain ratio.

ID3 can handle only categorical data, while C4.5 can handle both categorical and numerical data.

ID3 is more sensitive to noise in the data than C4.5.

All of the above.

CART uses the Gini impurity to split the data, while ID3/C4.5 use information gain or gain ratio.

CART can handle both categorical and numerical data, while ID3/C4.5 can handle only categorical data.

CART is less sensitive to noise in the data than ID3/C4.5.

All of the above.

Removing unnecessary branches from a decision tree to improve its performance.

Adding new branches to a decision tree to improve its performance.

Changing the decision criteria at each node of a decision tree to improve its performance.

None of the above.

Cost-complexity pruning

Reduced error pruning

Minimum description length pruning

All of the above.

It reduces the size of the tree.

It improves the accuracy of the tree.

It makes the tree easier to interpret.

All of the above.

It can lead to underfitting.

It can make the tree more sensitive to noise in the data.

It can increase the computational cost of building the tree.

All of the above.

When you have a large dataset.

When you have a dataset with both categorical and numerical features.

When you need a model that is easy to interpret.

All of the above.

When you have a small dataset.

When you have a dataset with a lot of noise.

When you need a model with high accuracy.

All of the above.

Fraud detection

Customer churn prediction

Medical diagnosis

All of the above.

scikit-learn

XGBoost

LightGBM

All of the above.

rpart

party

randomForest

All of the above.