{"id":9592,"date":"2025-07-10T13:03:59","date_gmt":"2025-07-10T11:03:59","guid":{"rendered":"https:\/\/www.kubicek.ai\/?post_type=lexicon&#038;p=9592"},"modified":"2026-07-27T13:42:47","modified_gmt":"2026-07-27T11:42:47","slug":"bagging","status":"publish","type":"lexicon","link":"https:\/\/www.kubicek.ai\/en\/lexicon\/bagging\/","title":{"rendered":"Bagging"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Imagine trying to guess how many sweets are in a large jar. Instead of relying on one person&#8217;s guess, you ask ten different people. Each of them will have a slightly skewed view, but when you average their estimates, the result will probably be far more accurate than any individual one. <strong>Bagging<\/strong> works on a similar principle. It creates several slightly different versions of the training data, trains a separate model on each of them, and then averages or votes on their results. This team approach reduces the risk of a large error and makes the overall prediction more reliable.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Bagging<\/strong>, short for <strong>Bootstrap Aggregating<\/strong>, is an ensemble meta-method in machine learning whose purpose is to reduce variance and prevent overfitting. The principle lies in creating a larger number of training datasets from the original one using the bootstrap method, that is, random sampling with replacement. Each newly created set is the same size as the original, but because of the replacement it contains some points several times and others not at all.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">A separate predictive model, typically of the same type \u2013 for example a decision tree \u2013 is then trained on each of these bootstrap sets. In the final phase, called aggregation, the predictions of all these models are combined. For classification tasks, voting is most often used, with the class receiving the most votes winning. For regression tasks the predictions are typically averaged. The resulting aggregated model generally shows better stability and accuracy than any of the individual models.<\/p>\n","protected":false},"featured_media":0,"template":"","class_list":["post-9592","lexicon","type-lexicon","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.kubicek.ai\/en\/wp-json\/wp\/v2\/lexicon\/9592","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kubicek.ai\/en\/wp-json\/wp\/v2\/lexicon"}],"about":[{"href":"https:\/\/www.kubicek.ai\/en\/wp-json\/wp\/v2\/types\/lexicon"}],"wp:attachment":[{"href":"https:\/\/www.kubicek.ai\/en\/wp-json\/wp\/v2\/media?parent=9592"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}