Bagging, short for Bootstrap Aggregating, is an ensemble learning technique that enhances the performance of machine learning models, particularly those with high variance, such as decision trees. The core idea behind bagging is to create multiple models by training them on different subsets of the training data, which are generated through a process called bootstrapping. This involves sampling the original dataset with replacement to create several bootstrap samples. By aggregating the predictions from these models, bagging reduces overfitting and improves the overall accuracy and robustness of the final model. It is widely used in various applications, especially in regression tasks.