Do the Absolute Error in Performance (Regression) is same as Means Absolute Error (MAE) ?

Hi @Afif, 

The Absolute error is the difference between the predicted value and the “true” value.

The Means Absolute Error MAE takes the average of absolute errors for a group of predictions and observations

Best, 

Cesar

Hi @Afif,

Yes, this is the same value. As stated in the documentation, the absolute error is calculated by summing the differences between the labels and predictions, and dividing this value by the number of examples.

Best,

Roland

Hi @rjones13

thank you, so both is using the same formula which is MAE formula is it just for confirmation?

Yes, it is the MAE formula. I've also done just a quick check where I performed the calculation manually and it matches.

Best,

Roland