Mean Absolute Error (MAE)
Definition
MAE measures the average absolute distance between prediction and actual value.
The mean of the absolute distances between prediction and observation; all errors contribute linearly and in the unit of the target variable.
Simply explained
Like the average distance between an estimate and the correct result, ignoring direction.
Why it matters in practice
Helps realistically assess model quality, limits, and technical decisions.
Example from business
A sales model is on average 8 units off from the actual value.
Limits and pitfalls
- MAE obscures error direction and weights large errors less than MSE.
Origin & history
MAE is a classic regression metric; its current use is standardized in statistics and ML libraries.
Use in mid-sized companies
- Possible application: A planning team compares sales forecasts with withheld actual values. It checks the MAE along with error direction and large individual errors before selecting a model.
Frequently asked questions
What does Mean Absolute Error (MAE) mean?
The mean of the absolute distances between prediction and observation; all errors contribute linearly and in the unit of the target variable.
What should one pay attention to?
MAE obscures error direction and weights large errors less than MSE.
Sources
Source checked on 10.10.2026. Editorial use cases are hypothetical; no evidence of real customer results.
Editorially reviewed on: