Skip to content

[source]

MCC#

Matthews Correlation Coefficient (MCC) measures the quality of a classification by taking true and false positives and negatives into account. It is generally regarded as a balanced measure which can be used even if the classes are of very different sizes. A coefficient of 1 represents a perfect prediction, 0 no better than random prediction, and −1 indicates total disagreement between prediction and observation.

MCC=TP×TNFP×FN(TP+FP)(TP+FN)(TN+FP)(TN+FN)

Estimator Compatibility: Classifier, Anomaly Detector

Output Range: -1 to 1

Parameters#

This metric does not have any parameters.

Example#

use Rubix\ML\CrossValidation\Metrics\MCC;

$metric = new MCC();

References#


  1. B. W. Matthews. (1975). Decision of the Predicted and Observed Secondary Structure of T4 Phage Lysozyme. 


Last update: 2021-03-03