Mean Absolute Error

Synonyms

Absolute error loss; Mean absolute deviation; Mean error

Definition

Mean Absolute Error is a model evaluation metric used with regression models. The mean absolute error of a model with respect to a test set is the mean of the absolute values of the individual prediction errors on over all instances in the test set. Each prediction error is the difference between the true value and the predicted value for the instance.

$$mae = \frac{{\sum \nolimits _{i=1}^{n}}abs\left ({y}_{i} - \lambda ({x}_{i})\right )} {n}$$

where y _i is the true target value for test instance x _i , λ(x _i ) is the predicted target value for test instance x _i , and n is the number of test instances.

Cross References

Mean Squared Error