mlr3 (version 0.3.0)

mlr_measures_regr.smape: Symmetric Mean Absolute Percent Error

Description

Regression measure defined as $$ \frac{2}{n} \sum_{i=1}^n \frac{\left| t_i - r_i \right|}{\left| t_i \right| + \left| r_i \right|}. $$

Dictionary

This Measure can be instantiated via the dictionary mlr_measures or with the associated sugar function msr():

mlr_measures$get("smape")
msr("smape")

Meta Information

• Type: "regr"

• Range: \([0, 2]\)

• Minimize: TRUE

• Required prediction: response

See Also

Dictionary of Measures: mlr_measures

as.data.table(mlr_measures) for a complete table of all (also dynamically created) Measure implementations.

Other regression measures: mlr_measures_regr.bias, mlr_measures_regr.ktau, mlr_measures_regr.mae, mlr_measures_regr.mape, mlr_measures_regr.maxae, mlr_measures_regr.medae, mlr_measures_regr.medse, mlr_measures_regr.mse, mlr_measures_regr.msle, mlr_measures_regr.pbias, mlr_measures_regr.rae, mlr_measures_regr.rmse, mlr_measures_regr.rmsle, mlr_measures_regr.rrse, mlr_measures_regr.rse, mlr_measures_regr.rsq, mlr_measures_regr.sae, mlr_measures_regr.srho, mlr_measures_regr.sse