Ensemble learning

Can one tree predict the future better than one?

Imagine you're trying to guess the outcome of a football match. You ask several friends for their opinions, but none of them seem to know the result.

Think of asking many friends instead of just one. Each friend gives you a guess, and then you combine all their guesses to get a better prediction. This way, you're not relying on just one person's opinion.

Example

If five friends predict the score as 2-1, 1-0, 3-2, 2-2, and 1-1, averaging these predictions gives you a more accurate guess than any single friend's prediction.

Remember this

Combining multiple predictions (ensemble learning) often results in a better overall prediction than relying on a single prediction.

Text adapted from Wikipedia, licensed under CC BY-SA 4.0.

Related concepts

Random forest

How can we make a forest of decision trees smarter and more accurate?

to use random forests: when you want a strong baseline with minimal hyperparameter tuning

Why not always use the best single tree for predictions?

Boosting (machine learning)

Boosting reduces bias in ML models

Bayesian network

Can we predict the future with probabilities?

Likelihood function

Why can't we just guess probabilities correctly all the time?

score matching does: learns the gradient of the log-density without normalizing

Ever wonder how we can compare apples and oranges fairly in studies?

Swipe through more Machine Learning concepts

Open Pocket Polymath