The linear regression (LR) model is a simple machine learning approach used for target variables that are continuous (i.e. variables that are real-valued). The LR model takes as its input both a vector of features (conventionally labeled X) and a vector of labels (y). Often different terminology is used —calling X our set of variables or predictors, and y our outcome or dependent variable—but the idea is the same. The data are plotted, and a straight line is then fit to these data points. The objective is to fit the line to the data points so that the distance between the line and points are minimized.