Skip to content



The Root Mean Squared Error (RMSE) is equivalent to the standard deviation of the error residuals in a regression problem. Since RMSE is just the square root of the MSE, RMSE is also sensitive to outliers because larger errors have a disproportionately large effect on the score.

\[ {\displaystyle \operatorname {RMSE} = {\sqrt{ \frac {1}{n} \sum _{i=1}^{n}(Y_{i}-{\hat {Y_{i}}})^{2}}}} \]


In order to maintain the convention of maximizing validation scores, this metric outputs the negative of the original score.

Estimator Compatibility: Regressor

Score Range: -∞ to 0


This metric does not have any parameters.


use Rubix\ML\CrossValidation\Metrics\RMSE;

$metric = new RMSE();