Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning

By Sebastian Raschka. arXiv.org, 2018

1,070 citations recorded by the source corpus.

The correct use of model evaluation, model selection, and algorithm selection techniques is vital in academic machine learning research as well as in many industrial settings. This article reviews different techniques that can be used for each of these three subtasks and discusses the main advantages and disadvantages of each technique with references to theoretical and empirical studies. Further, recommendations are given to encourage best yet feasible practices in research and applications of machine learning. Common methods such as the holdout method for model evaluation and selection are covered, which are not recommended when working with small datasets. Different flavors of the bootstrap technique are introduced for estimating the uncertainty of performance estimates, as an alternative to confidence intervals via normal approximation if bootstrapping is computationally feasible. Common cross-validation techniques such as leave-one-out cross-validation and k-fold cross-validation are reviewed, the bias-variance trade-off for choosing k is discussed, and practical tips for the optimal choice of k are given based on empirical evidence. Different statistical tests for algorithm comparisons are presented, and strategies for dealing with multiple comparisons such as omnibus tests and multiple-comparison corrections are discussed. Finally, alternative methods for algorithm selection, such as the combined F-test 5x2 cross-validation and nested cross-validation, are recommended for comparing machine learning algorithms when datasets are small.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/eef183687fab4d762a381f2e80e357e08e923f0a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer’s disease (2021, methodology): “The leave-one-out cross-validation (LOOCV), i.e. k-fold CV where k = n 72 , assures small bias but large variance 74 .”
Current Status, Challenges, and Possible Solutions of EEG-Based Brain-Computer Interface: A Comprehensive Review (2020, background): “However, some authors also reported cross-validation measures estimated on training data, which may over-rate the performance (Lotte et al., 2018; Raschka, 2018).”
Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence (2020, background): “Combinations of multiple machine learning algorithms or models, which are known as ensemble techniques, are widely used for providing stability, increasing model performance, and controlling the bias-variance tradeoff [32].”
Dynamically Weighted Balanced Loss: Class Imbalanced Learning and Confidence Calibration of Deep Neural Networks (2021, background): “Stratification enables to randomly split the data set while retaining the correct class distribution in each subset, which is the recommended way of splitting data under class imbalance [55].”
Heart Disease Identification Method Using Machine Learning Classification in E-Healthcare (2020, background): “To evaluate all classifiers on data and find that they get, on average, 50% of the cases right [16].”
The impact of site-specific digital histology signatures on deep learning model accuracy and bias (2021, background): “However, if submitting sites within a dataset are randomly split into equal-sized groups for cross-validation, it is likely that a feature of interest would not be evenly represented among these groups, resulting in biased estimates of accuracy 40 .”