Skip to Main content Skip to Navigation
Journal articles

Mean Absolute Percentage Error for regression models

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 prove the existence of an optimal MAPE model and we show the universal consistency of Empirical Risk Minimization based on the MAPE. We also show that finding the best model under the MAPE is equivalent to doing weighted Mean Absolute Error (MAE) regression, and we apply this weighting strategy to kernel regression. The behavior of the MAPE kernel regression is illustrated on simulated data.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01312590
Contributor : Fabrice Rossi <>
Submitted on : Monday, July 10, 2017 - 9:50:51 AM
Last modification on : Sunday, January 19, 2020 - 6:38:32 PM
Long-term archiving on: : Wednesday, January 24, 2018 - 7:25:21 AM

Files

demyttenaeregoldenetal2016mean...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution - ShareAlike 4.0 International License

Identifiers

Collections

Citation

Arnaud de Myttenaere, Boris Golden, Bénédicte Le Grand, Fabrice Rossi. Mean Absolute Percentage Error for regression models. Neurocomputing, Elsevier, 2016, Advances in artificial neural networks, machine learning and computational intelligence — Selected papers from the 23rd European Symposium on Artificial Neural Networks (ESANN 2015), 192, pp.38 - 48. ⟨10.1016/j.neucom.2015.12.114⟩. ⟨hal-01312590v2⟩

Share

Metrics

Record views

277

Files downloads

4945