Articles → MACHINE LEARNING → Ensemble Learning In Machine Learning

Ensemble Learning In Machine Learning

This article describes ensemble learning in Machine Learning.

What Is Ensemble Learning?

Consider a scenario where you want to decide whether to go for a new movie or not. You ask one friend: Should I watch it?. He says, Yes.. Would you fully trust just one opinion?

Now, imagine you ask 10 friends. 7 say Yes, 3 say No. Now you feel more confident that the movie might be good. This is Ensemble Learning.

Rather than relying on a single model, we combine multiple models and either take a vote or find an average to improve our decision.

How Do We Make Models Different In Ensemble Learning?

Different algorithms (heterogeneous ensemble)
Same algorithm, different data (Bagging)
Same algorithm, different hyperparameters
Same algorithm, different feature subsets

Simple Ensemble Techniques

Max voting
Averaging
Weighted average

Max Voting

In Max Voting, multiple models (called base learners) make predictions for the same input, and the class that receives the most votes becomes the final prediction. This is only done for classification.

Suppose you have three classifiers predicting whether an email is spam.

Model	Prediction
Model 1	Spam
Model 2	Not Spam
Model 3	Spam

Votes: Spam (2 votes) and Not Spam (1 vote). The final prediction is Spam.

Averaging

Multiple models make predictions → take their average → that becomes the final output.

Weighted Average

The weighted average is the sum of values multiplied by their weights, divided by the sum of the weights.

Posted By -	Karan Gupta

Posted On -	Wednesday, June 18, 2025

Updated On -	Wednesday, January 28, 2026

Query/Feedback

Your Email Id		**

Subject		*

Query/Feedback	Characters remaining 250	**