What is base learner selection in ensemble learning?
Updated May 16, 2026
Short answer
Base learner selection involves choosing appropriate models that balance bias, variance, and diversity in an ensemble.
Deep explanation
Base learners are the individual models in an ensemble. Their choice affects ensemble performance significantly. Weak learners like shallow trees are preferred in boosting, while stronger learners can be used in bagging. The key is balancing individual accuracy and diversity. Overly complex base learners reduce diversity, while too simple learners may underfit.
Real-world example
Credit scoring systems use tuned decision trees as base learners in ensembles.
Common mistakes
- Using overly complex base models in boosting.
Follow-up questions
- Why are shallow trees used in boosting?
- Can neural networks be base learners?