# What is Mean Absolute Error? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Mathematical Foundations  
> **Canonical Citation:** [https://spidits.com/ai-glossary/mean-absolute-error](https://spidits.com/ai-glossary/mean-absolute-error)

## Definition
Mean Absolute Error (MAE) is a mathematical loss metric used in regression models that calculates the average absolute differences between predicted values and actual target values.

## Architectural Mechanics & Deep Dive
Mean Absolute Error (MAE) is a metric used to evaluate regression models. It calculates the average of the absolute differences between predicted values and actual ground-truth values. Unlike Mean Squared Error (MSE), which squares errors and penalizes outliers heavily, MAE provides a linear, robust representation of average prediction error.

## Industry Applications & Real-World Use Cases
Regression model validation, loss calculations, and prediction scoring.

## Frequently Asked Questions

### How does MAE differ from Mean Squared Error (MSE)?
MSE squares the errors (penalizing large outliers heavily). MAE calculates simple absolute differences, making it more robust to outlier noise.

### What is the formula for MAE?
`MAE = (1/n) * sum(|y_pred - y_true|)`.

## Related Terminology
- [loss-function](https://spidits.com/ai-glossary/loss-function)
- [supervised-learning](https://spidits.com/ai-glossary/supervised-learning)
- [cost-function](https://spidits.com/ai-glossary/cost-function)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*