To evaluate binary classifications and their confusion matrices, scientific researchers can employ several statistical rates, accordingly to the goal of the experiment they are investigating. Despite being a crucial issue in machine learning, no widespread consensus has been reached on a unified elective chosen measure yet. Accuracy and F1 score computed on confusion matrices have been (and still are) among the most popular adopted metrics in binary classification tasks. However, these statistical measures can dangerously show overoptimistic inflated results, especially on imbalanced datasets.

The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation / Chicco, Davide; Jurman, Giuseppe. - In: BMC GENOMICS. - ISSN 1471-2164. - ELETTRONICO. - 21:1(2020), p. 6. [10.1186/s12864-019-6413-7]

The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation

Jurman, Giuseppe
2020-01-01

Abstract

To evaluate binary classifications and their confusion matrices, scientific researchers can employ several statistical rates, accordingly to the goal of the experiment they are investigating. Despite being a crucial issue in machine learning, no widespread consensus has been reached on a unified elective chosen measure yet. Accuracy and F1 score computed on confusion matrices have been (and still are) among the most popular adopted metrics in binary classification tasks. However, these statistical measures can dangerously show overoptimistic inflated results, especially on imbalanced datasets.
2020
1
Chicco, Davide; Jurman, Giuseppe
The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation / Chicco, Davide; Jurman, Giuseppe. - In: BMC GENOMICS. - ISSN 1471-2164. - ELETTRONICO. - 21:1(2020), p. 6. [10.1186/s12864-019-6413-7]
File in questo prodotto:
File Dimensione Formato  
chicco2020advantages.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 611.21 kB
Formato Adobe PDF
611.21 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/343472
Citazioni
  • ???jsp.display-item.citation.pmc??? 624
  • Scopus 2342
  • ???jsp.display-item.citation.isi??? 2032
social impact