On the performance of Matthews correlation coefficient (MCC) for imbalanced dataset

Qiuming Zhu

Research output: Contribution to journalArticlepeer-review

39 Scopus citations


The Matthews Correlation Coefficient (MCC) is one of the popular measurements for classification accuracy. It has been generally regarded as a balanced measure which can be used even if the classes are of very different sizes. The study of this paper finds that this is not true. MCC deteriorates seriously when the dataset in classification are imbalanced. Experiment results and analysis show that MCC is not suitable for classification accuracy measurement on imbalanced datasets.

Original languageEnglish (US)
Pages (from-to)71-80
Number of pages10
JournalPattern Recognition Letters
StatePublished - Aug 2020


  • Classification accuracy measurement
  • Imbalanced dataset
  • Matthews correlation coefficient
  • Performance evaluation

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'On the performance of Matthews correlation coefficient (MCC) for imbalanced dataset'. Together they form a unique fingerprint.

Cite this