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

TL;DR

This paper reviews techniques for model evaluation, selection, and algorithm comparison in machine learning, providing practical recommendations and discussing their advantages, disadvantages, and empirical performance, especially for small datasets.

Contribution

It offers a comprehensive overview of evaluation and selection methods, including best practices, statistical tests, and alternative approaches like nested cross-validation, with empirical insights.

Findings

Bootstrap methods effectively estimate performance uncertainty.

Optimal k in k-fold cross-validation balances bias and variance.

Nested cross-validation is recommended for small datasets.

Abstract

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.