Mean Absolute Error

machine-learning statistics regression

Definition

Mean Absolute Error

The Mean Absolute Error (MAE) is a loss function and evaluation metric for regression tasks that measures the average magnitude of errors in a set of predictions, without considering their direction. Formally, for $m$ samples:

$$\text{MAE}=\frac{1}{m}\sum _{i=1}^m|y_i-{\hat{y}}_i|$$

Unlike MSE, MAE is linear and thus less sensitive to outliers.