@article{chicco_advantages_2020,
	title = {The advantages of the {Matthews} correlation coefficient ({MCC}) over {F1} score and accuracy in binary classification evaluation},
	volume = {21},
	issn = {1471-2164},
	url = {https://doi.org/10.1186/s12864-019-6413-7},
	doi = {10.1186/s12864-019-6413-7},
	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.},
	number = {1},
	urldate = {2022-02-21},
	journal = {BMC Genomics},
	author = {Chicco, Davide and Jurman, Giuseppe},
	month = jan,
	year = {2020},
	keywords = {Accuracy, Binary classification, Biostatistics, Confusion matrices, Dataset imbalance, F1 score, Genomics, Machine learning, Matthews correlation coefficient},
	pages = {6},
}

{"_id":"u7f5y9i7L7HmZNq6g","bibbaseid":"chicco-jurman-theadvantagesofthematthewscorrelationcoefficientmccoverf1scoreandaccuracyinbinaryclassificationevaluation-2020","authorIDs":[],"author_short":["Chicco, D.","Jurman, G."],"bibdata":{"bibtype":"article","type":"article","title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","volume":"21","issn":"1471-2164","url":"https://doi.org/10.1186/s12864-019-6413-7","doi":"10.1186/s12864-019-6413-7","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.","number":"1","urldate":"2022-02-21","journal":"BMC Genomics","author":[{"propositions":[],"lastnames":["Chicco"],"firstnames":["Davide"],"suffixes":[]},{"propositions":[],"lastnames":["Jurman"],"firstnames":["Giuseppe"],"suffixes":[]}],"month":"January","year":"2020","keywords":"Accuracy, Binary classification, Biostatistics, Confusion matrices, Dataset imbalance, F1 score, Genomics, Machine learning, Matthews correlation coefficient","pages":"6","bibtex":"@article{chicco_advantages_2020,\n\ttitle = {The advantages of the {Matthews} correlation coefficient ({MCC}) over {F1} score and accuracy in binary classification evaluation},\n\tvolume = {21},\n\tissn = {1471-2164},\n\turl = {https://doi.org/10.1186/s12864-019-6413-7},\n\tdoi = {10.1186/s12864-019-6413-7},\n\tabstract = {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.},\n\tnumber = {1},\n\turldate = {2022-02-21},\n\tjournal = {BMC Genomics},\n\tauthor = {Chicco, Davide and Jurman, Giuseppe},\n\tmonth = jan,\n\tyear = {2020},\n\tkeywords = {Accuracy, Binary classification, Biostatistics, Confusion matrices, Dataset imbalance, F1 score, Genomics, Machine learning, Matthews correlation coefficient},\n\tpages = {6},\n}\n\n","author_short":["Chicco, D.","Jurman, G."],"key":"chicco_advantages_2020","id":"chicco_advantages_2020","bibbaseid":"chicco-jurman-theadvantagesofthematthewscorrelationcoefficientmccoverf1scoreandaccuracyinbinaryclassificationevaluation-2020","role":"author","urls":{"Paper":"https://doi.org/10.1186/s12864-019-6413-7"},"keyword":["Accuracy","Binary classification","Biostatistics","Confusion matrices","Dataset imbalance","F1 score","Genomics","Machine learning","Matthews correlation coefficient"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/kountour","creationDate":"2020-08-07T09:43:58.816Z","downloads":0,"keywords":["accuracy","binary classification","biostatistics","confusion matrices","dataset imbalance","f1 score","genomics","machine learning","matthews correlation coefficient"],"search_terms":["advantages","matthews","correlation","coefficient","mcc","over","score","accuracy","binary","classification","evaluation","chicco","jurman"],"title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","year":2020,"dataSources":["C5FtkvWWggFfMJTFX","QiNXGx82DM7bbArZY","MnayAXw3qciX87bz7"]}