Skip to content
BENIBIX Learn

Random Forest

AI📈 Machine LearningClassic ML Algorithms

Also known as Random Decision Forest

Lots of decision trees, each a bit different. They all vote on the answer.

Think of it like

Think of it like asking a hundred friends. You go with what most of them say.

Example

Emma's model spots fake product reviews. It uses 300 trees. For one review, 240 vote fake and 60 vote real, so the review is flagged.

Why it matters

It works well on table data with little tuning. Many teams try it first and are surprised how hard it is to beat.

Definition

A random forest is a model made of many decision trees that vote. Each tree is trained on a random sample of the data and looks at a random mix of features. So each tree makes different mistakes. When a new example comes in, every tree gives an answer and the most common one wins. The crowd is usually far more accurate than any single tree.
A random forest is the top row. The trees work side by side and vote.

Common mistake

Expecting to read it like one tree. With hundreds of trees, you lose the easy explanation a single tree gives.

Key takeaways

  1. 1
    Many trees. Each one trained a bit differently.
  2. 2
    They vote. The most common answer wins.
  3. 3
    Errors cancel. The crowd beats any one tree.

Compare

Learn it properly