Bagging, short for Bootstrap Aggregating, is an ensemble machine learning technique designed to improve the stability and accuracy of models. It works by generating multiple bootstrapped samples from the original dataset, which are then used to train individual models. Each model makes predictions, and the final output is typically obtained by averaging or voting on these predictions. This method effectively reduces variance and helps prevent overfitting, making it particularly useful for complex models. Bagging is commonly associated with algorithms like Random Forests, where it enhances performance by leveraging the strengths of multiple learners.