SESKStuff Everyone Should Know
SESK: Stuff Everyone Should Know · sesk.info/ai-random-forest-bagging

How is a random forest built?

Many decision trees, each trained on a random sample, voting or averaging together.

Start playing free

  1. One very deep decision tree
  2. Many trees trained on random samples, combined ✔
  3. A neural network shaped like a tree

Why: A random forest trains each tree on a bootstrap sample (drawn with replacement) and a random subset of features. Averaging many different trees lets their errors partly cancel out.

Huh, didn't know that: Training each model on a bootstrap sample, drawn with replacement, is called bagging.

The dad joke
A single decision tree overfits. A random forest overfits less, because the trees argue it out.
Like this card?
Play the game

References

Answer: Many trees trained on random samples, combined. A random forest trains each tree on a bootstrap sample (drawn with replacement) and a random subset of features. Averaging many different trees lets their errors partly cancel out.

  1. scikit-learn User Guide: Ensembles scikit-learn.org/stable/modules/ensemble.html
    from a sample drawn with replacement (i.e., a bootstrap sample)
    Checked 2026-10-10.
  2. Google Machine Learning Glossary: bagging developers.google.com/machine-learning/glossary
    a random forest is a collection of decision trees trained with bagging.
    Checked 2026-10-10.

Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.

Test yourself in the game

Artificial IntelligenceWhy are decision trees called a "white box" model?Artificial IntelligenceHow do AI, machine learning and deep learning fit together?Artificial IntelligenceWhat did Alan Turing call his 1950 test of machine intelligence?

That's stuff everyone should know.