Metrics for Multi-Class Classification: an Overview
By Margherita Grandini, Enrico Bagli, Giorgio Visani. arXiv.org, 2020
1,297 citations recorded by the source corpus.
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. comparing the performance of two different models or analysing the behaviour of the same model by tuning different parameters. In this white paper we review a list of the most promising multi-class metrics, we highlight their advantages and disadvantages and show their possible usages during the development of a classification model.
View Paper: https://www.semanticscholar.org/paper/2c9022fe0af15568a885e59d475ec8f95726e51b
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- Metrics Reloaded: Recommendations for image analysis validation (2022, unknown): “Positive Predictive Value* PPV Precision [13, 37, 85] [0, 1] ↑ x x x Sensitivity* Recall, Hit Rate, True Positive Rate (TPR) [13, 37, 85] [0, 1] ↑ x x x Specificity* Selectivity, True Negative Rate (TNR) [13, 37, 85] [0, 1] ↑ x”
- A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, background): “We note that such thresholds have important implications for di ff erent applications, and caution must be taken especially in the case of medicine, as discussed by Ruopp et al. [309].”