An experimental comparison of cross-validation techniques for estimating the area under the ROC curve.
Antti AirolaTapio PahikkalaWillem WaegemanBernard De BaetsTapio SalakoskiPublished in: Comput. Stat. Data Anal. (2011)
Keyphrases
- cross validation
- model selection
- hyperparameters
- support vector
- training set
- cross validated
- regression problems
- variable selection
- error estimates
- class distribution
- generalization error
- receiver operating characteristic
- unseen data
- regularization parameter
- roc curve
- information criterion
- classification rules
- multi class
- error estimation
- artificial neural networks
- data sets