Preprint · 2026 · Open access
When Error Metrics Contradict: Clarifying RMSE and MAE in Machine Learning Evaluation
Preprints.org · Published 7 August 2026 · DOI 10.20944/preprints202601.2392.v2
In brief
“When Error Metrics Contradict: Clarifying RMSE and MAE in Machine Learning Evaluation” is a 2026 preprint by Walter W. Chen and Kieu Anh Nguyen, published in Preprints.org. OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at Preprints.org.
- Citations
- 0
- Authors
- 2
Abstract
Root mean squared error (RMSE) and mean absolute error (MAE) are among the most widely used performance metrics in machine learning and scientific modeling. Although their mathematical relationship is well established, misunderstandings and misapplications of these metrics continue to appear in the literature. This technical note revisits the fundamental bounds relating RMSE and MAE and identifies a systematic error in a recently published paper in Artificial Intelligence Review, in which RMSE values are numerically smaller than the corresponding MAE values, a relationship that is mathematically impossible. Notably, of the twenty rows in that study transcribed from previously published sources, eighteen satisfy the inequality RMSE >= MAE; the two that do not are shown here to be a transposition of the MAE and RMSE of a cited source and a self-citation to the same authors' earlier work, so that no independently published result in those tables violates the inequality. In addition, supplementary experiments using two common and straightforward machine learning models, Random Forest and XGBoost, demonstrate that comparable or superior performance can be achieved in several of the same datasets used in the aforementioned paper without resorting to highly complex optimization frameworks. Collectively, these findings underscore the importance of verifying the correctness of basic performance metrics and of contextualizing claimed performance gains through transparent baseline comparisons in machine learning evaluation.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Chen, W. W., & Nguyen, K. A. (2026). When Error Metrics Contradict: Clarifying RMSE and MAE in Machine Learning Evaluation. Preprints.org. https://doi.org/10.20944/preprints202601.2392.v2
MLA 9
Chen, Walter W., and Kieu Anh Nguyen. “When Error Metrics Contradict: Clarifying RMSE and MAE in Machine Learning Evaluation.” Preprints.org, 2026. https://doi.org/10.20944/preprints202601.2392.v2.
Chicago
Chen, Walter W. and Kieu Anh Nguyen. 2026. “When Error Metrics Contradict: Clarifying RMSE and MAE in Machine Learning Evaluation.” Preprints.org. https://doi.org/10.20944/preprints202601.2392.v2.
Harvard
Chen, W. W. and Nguyen, K. A. (2026) ‘When Error Metrics Contradict: Clarifying RMSE and MAE in Machine Learning Evaluation’, Preprints.org. doi:10.20944/preprints202601.2392.v2.
IEEE
W. W. Chen and K. A. Nguyen, “When Error Metrics Contradict: Clarifying RMSE and MAE in Machine Learning Evaluation,” Preprints.org, 2026, doi: 10.20944/preprints202601.2392.v2.
BibTeX
@misc{chen2026when,
title = {{When Error Metrics Contradict: Clarifying RMSE and MAE in Machine Learning Evaluation}},
author = {Chen, Walter W. and Nguyen, Kieu Anh},
howpublished = {Preprints.org},
year = {2026},
doi = {10.20944/preprints202601.2392.v2},
url = {https://doi.org/10.20944/preprints202601.2392.v2}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- root mean square error
- mean absolute error
- machine learning model evaluation
- baseline comparison
- random forest
- XGBoost
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Chen, W. W., & Nguyen, K. A. (2026). When Error Metrics Contradict: Clarifying RMSE and MAE in Machine Learning Evaluation. Preprints.org. https://doi.org/10.20944/preprints202601.2392.v2
How many times has this paper been cited?
0 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at Preprints.org.
Who wrote this paper?
Walter W. Chen, Kieu Anh Nguyen.
What is the DOI of this paper?
10.20944/preprints202601.2392.v2. The permanent link is https://doi.org/10.20944/preprints202601.2392.v2.
Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.