4
$\begingroup$

How to understand the relationships, comparative advantages, and comparative disadvantages of boosting, bootstrapping and bagging in terms of their respective applications in data mining.

$\endgroup$
  • 2
    $\begingroup$ Can you be more specific? It is a topic for a book. $\endgroup$ – user88 Apr 25 '12 at 8:35
4
$\begingroup$

Both boosting and bagging are ensemble techniques -- instead of learning a single classifier, several are trained and their predictions combined. While bagging uses an ensemble of independently trained classifiers, boosting is an iterative process that attempts to mitigate prediction errors of earlier models by predicting them with later models.

Bootstrapping doesn't really fit into this context (unless you mean something different by that term) and is a way of estimating the accuracy of a learned classifier on unseen data, similar to standard train/test data set splits or cross validation.

$\endgroup$
  • 7
    $\begingroup$ Bagging involves bootstrapping. $\endgroup$ – Michael R. Chernick Jul 24 '12 at 16:03

Not the answer you're looking for? Browse other questions tagged or ask your own question.