Editing Bootstrap aggregating (section)

== Advantages and disadvantages ==

Advantages:
* Many weak learners aggregated typically outperform a single learner over the entire set, and have less overfit
* Reduces variance in high-variance [[bias (statistics)|low-bias]] weak learner,<ref name=":3">{{cite web |url= https://corporatefinanceinstitute.com/resources/knowledge/other/bagging-bootstrap-aggregation/ |title=What is Bagging (Bootstrap Aggregation)? |publisher=Corporate Finance Institute |website=CFI |access-date=December 5, 2020}}</ref> which can improve [[efficiency (statistics)]]
* Can be performed in [[Parallel Computing|parallel]], as each separate bootstrap can be processed on its own before aggregation.<ref>{{cite web |url=https://medium.com/swlh/bagging-bootstrap-aggregating-overview-b73ca019e0e9 |title= Bagging (Bootstrap Aggregating), Overview |last=Zoghni |first=Raouf |publisher=The Startup |date=September 5, 2020 |via=Medium}}</ref>

Disadvantages:
* For a weak learner with high bias, bagging will also carry high bias into its aggregate<ref name=":3"/>
* Loss of interpretability of a model.
* Can be computationally expensive depending on the dataset.