Bagging

Bagging (Bootstrap aggregating) is a meta-learning technique= that involves creation of an ensemble of models based on random train= ing sets and created from the original training set by sampling with replac= ement.

The final model is a simple average of the individual models within the = ensemble.

In other words, bagging involves:

replicating multiple training sets of equal sizes from= the original training set. The size each set equals to the size of the ori= ginal set
definition of the respective validation sets as the sa= mples not included in the training sets. By chance, about 37% of the sample= s will not included in a training set.
training multiple models using a particular machine le= arning method (the same method and parameters for each model)
for getting a validated prediction for a sample, calculate the predicti= on value as the average prediction by those models that had this compound i= n their validation sets

Bagging achieves two important goals: validation and assessment of predictive uncertainty, that is:

Obtaining a correctly validated predictive statistics (similarly to cro= ss-validation)
Obtaining standard deviations for each prediction, which is possible be= cause of using an ensemble of models rather that a single model.
The s= tandard deviation (referred to as BAGGING-STD) can be used, for calculation= of prediction uncertainty and definition of applicability domain.