Entscheidungsbäume (EN)

Decision Trees

Decision trees are a supervised learning method that segments data through a tree structure of decision rules. Each internal node represents a condition for a feature, while each leaf node contains a decision or prediction. They are particularly useful for their interpretability and ability to process both numerical and categorical data. However, they tend to overfit with too many splits.

Architecture

flowchart TD     A[Data] --> B{Root node}     B --> C{Condition 1}     B --> D{Condition 2}     C --> E[Leaf node 1]     C --> F[Leaf node 2]     D --> G[Leaf node 3]     D --> H[Leaf node 4]     E --> I[Result A]     F --> J[Result B]     G --> K[Result C]     H --> L[Result D] 

In Context

• Typically used together with Random Forests and Gradient Boosting
• Related to: Classification, Regression, Overfitting, Pruning
• Example use: Credit scoring, medical diagnosis, customer segmentation