In this chapter a short introduction is given in machine learning methods. First, classification and regression trees are introduced. Both are necessary to understand the use of more complicated methods such as bagging (e.g. random forest) and boosting (e.g. XGBoost). Furthermore, the bias-variance trade-off is discussed, which deals with the quality of a prediction model. When the internal quality is high, the external validity is often low. In machine learning terminology, the internal quality is often referred to as bias, while the external validity is often referred to as variance. The second part of this chapter deals with shrinkage methods. Shrinkage methods aim to shrink the regression coefficients of a prediction model in order to increase the external validity of the model.