Preprint · 2015 · Open access

Using the Mean Absolute Percentage Error for Regression Models

Arnaud De Myttenaere, Boris Golden, Bénédicte Le Grand, Fabrice Rossi A

arXiv (Cornell University) · Published 12 June 2015 · DOI 10.48550/arxiv.1506.04176

Free PDFView at the publisherCite this paper

In brief

“Using the Mean Absolute Percentage Error for Regression Models” is a 2015 preprint by Arnaud De Myttenaere and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 38 citations as of 15 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
38
Most cited in
2021 (9)
References
4
Authors
4

Abstract

We study in this paper the consequences of using the Mean Absolute Percentage Error (MAPE) as a measure of quality for regression models. We show that finding the best model under the MAPE is equivalent to doing weighted Mean Absolute Error (MAE) regression. We show that universal consistency of Empirical Risk Minimization remains possible using the MAPE instead of the MAE.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

De Myttenaere, A., Golden, B., Le Grand, B., & A, F. R. (2015). Using the Mean Absolute Percentage Error for Regression Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1506.04176

MLA 9

De Myttenaere, Arnaud, et al. “Using the Mean Absolute Percentage Error for Regression Models.” arXiv (Cornell University), 2015. https://doi.org/10.48550/arxiv.1506.04176.

Chicago

De Myttenaere, Arnaud, Boris Golden, Bénédicte Le Grand, and Fabrice Rossi A. 2015. “Using the Mean Absolute Percentage Error for Regression Models.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1506.04176.

Harvard

De Myttenaere, A. et al. (2015) ‘Using the Mean Absolute Percentage Error for Regression Models’, arXiv (Cornell University). doi:10.48550/arxiv.1506.04176.

IEEE

A. De Myttenaere, B. Golden, B. Le Grand, and F. R. A, “Using the Mean Absolute Percentage Error for Regression Models,” arXiv (Cornell University), 2015, doi: 10.48550/arxiv.1506.04176.

BibTeX

@misc{demyttenaere2015using,
  title     = {{Using the Mean Absolute Percentage Error for Regression Models}},
  author    = {De Myttenaere, Arnaud and Golden, Boris and Le Grand, Bénédicte and A, Fabrice Rossi},
  howpublished = {arXiv (Cornell University)},
  year      = {2015},
  doi       = {10.48550/arxiv.1506.04176},
  url       = {https://doi.org/10.48550/arxiv.1506.04176}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201755
201811
201922
202044
202199
202233
202333
202444
202555
202622

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification

  • mean absolute percentage error
  • mean absolute error
  • weighted regression
  • empirical risk minimization
  • universal consistency
  • model selection

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

De Myttenaere, A., Golden, B., Le Grand, B., & A, F. R. (2015). Using the Mean Absolute Percentage Error for Regression Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1506.04176

How many times has this paper been cited?

38 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 arXiv (Cornell University).

Who wrote this paper?

Arnaud De Myttenaere, Boris Golden, Bénédicte Le Grand, Fabrice Rossi A.

What is the DOI of this paper?

10.48550/arxiv.1506.04176. The permanent link is https://doi.org/10.48550/arxiv.1506.04176.

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.