Root Mean Squared Error
noun
say it: “ROOT MEEN SKWAIRD AIR-er” /ˈrut ˈmin ˈskwɛrd ˈɛrər/
The square root of the average squared difference between predicted and real values, giving a typical error in the original units.
What is root mean squared error?
Root mean squared error (RMSE) is the square root of the mean squared error. It's back in the label's own units, such as minutes, and it counts big misses more than mean absolute error does, so a model with a few large misses has an RMSE well above its MAE.
from sklearn.metrics import mean_absolute_error, root_mean_squared_error
minutes = [30, 25, 40]
guessed = [28, 27, 34]
print(round(mean_absolute_error(minutes, guessed), 2)) # 3.33
print(round(root_mean_squared_error(minutes, guessed), 2)) # 3.83: the 6-minute miss counts more
In a sentence
- “Root mean squared error came out higher than MAE because of one big miss.”
- “The delivery model's root mean squared error was 3.8 minutes.”
Level: Journeyman · More AI Basics terms at this level
Updated