Fetching the paper…

Reading the bibliography…

2020

Metrics for Multi-Class Classification: an Overview

Grandini, Margherita, Bagli, Enrico, Visani, Giorgio

Original
PDF
Post on X

Understand

Classification tasks in machine learning involving more than two classes are known by the name of "multi-class classification".

Performance indicators are very useful when the aim is to evaluate and compare different classification models or machine learning techniques.
Many metrics come in handy to test the ability of a multi-class classifier.
Those metrics turn out to be useful at different stage of the development process, e.g.

Metrics for Multi-Class Classification: an Overview · Around

Built on

“Macro F1 and Macro F1”, 2019
Original
Juri Opitz and Sebastian Burst · 1911
Earlier work this paper cites.
“Comparison of the predicted and observed secondary structure of T4 phage lysozyme”
B.W. Matthews · 1975
Earlier work this paper cites.
“DISCRIMINATION AND CLASSIFICATION: OVERVIEW”
S.C. CHOI · 1986
Earlier work this paper cites.
“Comparing two K-category assignments by a K-category correlation coefficient”
J. Gorodkin · 2004
Earlier work this paper cites.
“The truth of the f-measure. 2007”, 2007
Yutaka Sasaki · 2007
Earlier work this paper cites.

Similar

“The Balanced Accuracy and Its Posterior Distribution”
K.. Brodersen, C.. Ong, K.. Stephan and J.. Buhmann · 2010
Cited alongside, same era.
“Data Mining Methods Applied to a Digital Forensics Task for Supervised Machine Learning”
Original
Antonio. Tallón-Ballesteros and José Riquelme · 2014
Cited alongside, same era.
“Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric”
Sabri Boughorbel, Fethi Jarray and Mohammed El-Anbari · 2017
Cited alongside, same era.
“Common pitfalls in statistical analysis: Measures of agreement” PCR-8-187[PII]
Priya Ranganathan, C.. Pramesh and Rakesh Aggarwal · 2017
Cited alongside, same era.

Then

“Classifiers and their Metrics Quantified”
J.. Brown · 2018
Later among the works it cites.
“Multi-Class Metrics Made Simple, Part II: the F1-score”, 2019
Boaz Shmueli · 2019
Later among the works it cites.
“The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation”
Davide Chicco and Giuseppe Jurman · 2020
Closest in time.
“Ok I got it…”, 2020
Nechushtan Moran · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…