Joint use of over- and under-sampling techniques and cross-validation for the development and assessment of prediction models.
Rok BlagusLara LusaPublished in: BMC Bioinform. (2015)
Keyphrases
- cross validation
- model selection
- variable selection
- cross validated
- unseen data
- prediction model
- information criterion
- hyperparameters
- training set
- ls svm
- error estimates
- neural network
- regression problems
- generalization error
- prediction accuracy
- prior knowledge
- support vector
- regularization parameter
- bayesian framework
- feature vectors
- machine learning