Mean Absolute Error is a common evaluation criterion to measure the average magnitude of the errors, which doesn’t consider the direction. In this project, the error for each target is, $$ \text{MAE}(Y, \hat{Y}) = \dfrac{1}{n_{samples}} \sum_{i=1}^{n_{samples}} |y_{i} - \hat{y}_{i}|$$ Where $\hat{Y}$ is the predicted value set and $Y$ is the true value set. $n_{samples}$ means the number of testing samples.