We analyse 18 evaluation methods for learning algorithms and classifiers, and show how to categorise these methods with the help of an evaluation method taxonomy based on several …
P Flach - Proceedings of the AAAI conference on artificial …, 2019 - aaai.org
This paper gives an overview of some ways in which our understanding of performance evaluation measures for machine-learned classifiers has improved over the last twenty …
We analyze critically the use of classification accuracy to compare classifiers on natural data sets, providing a thorough investigation using ROC analysis, standard machine learning …
PA Flach - … of machine learning and data mining, 2016 - research-information.bris.ac.uk
ROC analysis investigates and employs the relationship between sensitivity and specificity of a binary classifier. Sensitivity or true positiverate measures the proportion of positives …
Different evaluation measures assess different characteristics of machine learning algorithms. The empirical evaluation of algorithms and classifiers is a matter of on-going …
Predictive accuracy has been used as the main and often only evaluation criterion for the predictive performance of classification learning algorithms. In recent years, the area under …
This paper provides a characterization of bias for evaluation metrics in classi cation (eg, Information Gain, Gini, 2, etc.). Our characterization provides a uniform representation for all …
Abstract Evaluation measures play an important role in machine learning because they are used not only to compare different learning algorithms, but also often as goals to optimize in …
This essay gives advice to authors of papers on machine learning, although much of it carries over to other computational disciplines. The issues covered include the material that …