Cognitive Scaffold

Preparing your thinking workspace

arrow_back_ios_new
MENTAL MODEL · M6665

Iterative Dichotomiser 3

Iterative Dichotomiser 3
DecideHigh supportDecision Science
Included
account_tree

Version 1.0.0 · Updated 2026-07-30

CORE DEFINITION

A decision tree learning algorithm proposed by Ross Quinlan in 1986. Core concepts: - Information Entropy: measures the uncertainty of a dataset - Information Gain: the reduction in uncertainty after selecting an attribute. Algorithm steps: 1. Calculate the entropy of the current dataset. 2. For each attribute, calculate the information gain. 3. Select the attribute with the highest information gain as the split node. 4. Recursively build subtrees.

SCAFFOLDING EFFECT

psychology

Reduce cognitive load

Greedy selection, fast construction. ID3 greedily selects the best split attribute using the information gain criterion, quickly building a decision tree. Although it may not be globally optimal, it is computationally efficient and is the basis for C4.5.

anchor

Anchor fast decisions

A decision tree algorithm proposed by Ross Quinlan in 1986. It uses information entropy to measure dataset uncertainty and uses **information gain** (the reduction in uncertainty after splitting) as the criterion to **greedily** select the best split attribute, recursively building the tree. The mechanism is "local optimum, layer-by-layer approximation," which is computationally efficient, and although not globally optimal, it is the foundation for C4.5 and others.

MINIMUM ACTION

In progress 0/4

Practice this model in one real situation:

Check to track your progress (stored locally)
Learning progress0%
account_treeGenealogyexpand_more
menu_bookReferencesexpand_more

Source support: Explicit

  • link
    en.wikipedia.orghttps://en.wikipedia.org/wiki/ID3_algorithmZH · Explicit
    verified

RELATED MODELS