Hands-On Artificial Intelligence for Cybersecurity

Ensemble learning

Moving on from data to algorithms, earlier, we mentioned how, in the presence of non-stationary data, it may be useful to introduce an ensemble of classifiers, rather than simply using individual classifiers to improve overall prediction accuracy.

Therefore, the purpose of ensemble learning is to combine different classification algorithms in order to obtain a classifier that allows you to get better predictions than those that can be obtained by using individual classifiers.

To understand why the ensemble classifier behaves better than individual classifiers, we need to imagine that we have a certain number of binary classifiers, all of the same type, characterized by the ability to make correct predictions in 75% of cases ...