AIExplainer
Machine Learning Intermediate 2 min read

What is Mean Absolute Error?

A measure of the average difference between predicted and actual values

Stands for: MAE

Mean Absolute Error is a way to calculate how far off predictions are from actual values. It does this by averaging the absolute differences between each predicted value and its corresponding actual value.

Imagine you're trying to guess how many cookies are in a jar. If you guess 10 and there are actually 12, your error is 2. If you do this many times and average all your errors, you get the Mean Absolute Error. It's like averaging how far off your cookie guesses were.

A company uses a model to predict daily sales. If the model predicts 100 sales but actually 120 sales happen, the absolute error is 20. After calculating the absolute errors for many days and averaging them, the company gets the Mean Absolute Error, which helps to assess the model's accuracy.

Mean Absolute Error is used to evaluate the performance of predictive models, such as those used in forecasting, regression analysis, and machine learning. It helps to understand how accurate the model's predictions are.

Some people think Mean Absolute Error measures the maximum error, but it actually measures the average error. Others confuse it with Mean Squared Error, which gives more weight to larger errors.

The concept of Mean Absolute Error has been around for a long time and is widely used in statistics and data analysis. Its application in machine learning and predictive modeling has become increasingly important with the growth of data-driven decision making.

Average Absolute Error Mean Absolute Deviation

Three products for different needs — explore what’s relevant to you.