A1 Refereed original research article in a scientific journal
Evaluation metrics and statistical tests for machine learning
Authors: Rainio, Oona; Teuho, Jarmo; Klén, Riku
Publisher: Nature Research
Publication year: 2024
Journal: Scientific Reports
Journal name in source: Scientific Reports
Article number: 6086
Volume: 14
DOI: https://doi.org/10.1038/s41598-024-56706-x
Web address : https://doi.org/10.1038/s41598-024-56706-x
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/387398800
Additional information: Author correction to this article: https://www.nature.com/articles/s41598-024-66611-y ; DOI: 10.1038/s41598-024-66611-y
Research on different machine learning (ML) has become incredibly popular during the past few decades. However, for some researchers not familiar with statistics, it might be difficult to understand how to evaluate the performance of ML models and compare them with each other. Here, we introduce the most common evaluation metrics used for the typical supervised ML tasks including binary, multi-class, and multi-label classification, regression, image segmentation, object detection, and information retrieval. We explain how to choose a suitable statistical test for comparing models, how to obtain enough values of the metric for testing, and how to perform the test and interpret its results. We also present a few practical examples about comparing convolutional neural networks used to classify X-rays with different lung infections and detect cancer tumors in positron emission tomography images.
Downloadable publication This is an electronic reprint of the original article. |  |
