Empirical Comparison of Area under ROC curve (AUC) and Mathew Correlation Coefficient (MCC) for Evaluating Machine Learning Algorithms on Imbalanced Datasets for Binary Classification.
Chongomweru HalimuAsem KasemS. H. Shah NewazPublished in: ICMLSC (2019)
Keyphrases
- machine learning algorithms
- binary classification
- correlation coefficient
- roc curve
- learning problems
- receiver operating characteristic
- class imbalance
- machine learning
- learning algorithm
- decision trees
- multi class classification
- probability estimation
- ensemble methods
- machine learning methods
- class distribution
- learning tasks
- misclassification costs
- random forests
- binary classifiers
- cost sensitive
- active learning
- support vector machine
- multi class
- support vector
- evaluation measures
- generalization error
- learning models
- prediction accuracy
- multi label
- naive bayes
- principal components
- transfer learning
- feature selection