Compartir
Título
Non-removal strategy for outliers in predictive models: The PAELLA algorithm case
Autor
Facultad/Centro
Área de conocimiento
Título de la revista
Logic Journal of the IGPL
Número de la revista
4
Cita Bibliográfica
Castejón-Limas, M., Alaiz-Moreton, H., Fernández-Robles, L., Alfonso-Cendón, J., Fernández-Llamas, C., Sánchez-González, L., & Pérez, H. (2020). Non-removal strategy for outliers in predictive models: The PAELLA algorithm case. Logic Journal of the IGPL, 28(4), 418-429.https://doi.org/10.1093/jigpal/jzz052
Editorial
Oxford University Press
Fecha
2020-08
ISSN
1367-0751
Resumen
[EN] This paper reports the experience of using the PAELLA algorithm as a helper tool in
robust regression instead of as originally intended for outlier identification and removal.
This novel usage of the algorithm takes advantage of the occurrence vector calculated by
the algorithm in order to strengthen the effect of the more reliable samples and lessen the
impact of those that otherwise would be considered outliers. Following that aim, a series
of experiments are conducted in order to learn how to better use the information contained in the occurrence vector. Using a contrively difficult artificial dataset, a reference
predictive model is fit using the whole raw dataset. The second experiment reports the
results of fitting a similar predictive model but discarding the samples marked as outliers
by PAELLA. The third experiment uses the occurrence vector provided by PAELLA in
order to classify the observations in multiple bins and fit every possible model changing
which bins are considered for fitting and which are discarded in that particular model. The
fourth experiment introduces a sampling process before fitting in which the occurrence
vector represents the likelihood of being considered in the training dataset. The fifth experiment
considers the sampling process as an internal step to be performed interleaved
between the training epochs. The last experiment compares our approach using weighted
neural networks to a state of the art method.
Materia
Palabras clave
Peer review
SI
ID proyecto
- DPI2016-79960-C3-2-P].
- info:eu-repo/grantAgreement/MINECO//DPI2016-79960-C3-2-P
URI
DOI
Aparece en las colecciones
- Artículos [4641]
Ficheros en el ítem
Nombre:
Tamaño:
290.9
xmlui.dri2xhtml.METS-1.0.size-kilobytes
Formato:
Adobe PDF
Descripción:
Manuscrito previo a su publicación