Skip to content

[source]

SMAPE#

Symmetric Mean Absolute Percentage Error (SMAPE) is a scale-independent regression metric that expresses the relative error of a set of predictions and their labels as a percentage. It is an improvement over the non-symmetric MAPE in that it is both upper and lower bounded.

SMAPE=100%nt=1n|FtAt|(|At|+|Ft|)/2

Note

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

Estimator Compatibility: Regressor

Output Range: -100 to 0

Parameters#

This metric does not have any parameters.

Example#

use Rubix\ML\CrossValidation\Metrics\SMAPE;

$metric = new SMAPE();

References#


  1. V. Kreinovich. et al. (2014). How to Estimate Forecasting Quality: A System Motivated Derivation of Symmetric Mean Absolute Percentage Error (SMAPE) and Other Similar Characteristics. 


Last update: 2021-03-03