EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A feature selection method based on Shapley values robust for concept shift in regression

Carlos Sebastián, Carlos E. González-Guillén

Neural Computing and Applications · 2024-08 · 36 (23) · 14575-14597

DOI: 10.1007/s00521-024-09745-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neural Computing and Applications, online erschienen am 09.05.2024. Verfasst von Carlos Sebastián und 1 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Centro para el Desarrollo Tecnológico Industrial, Ministerio de Universidades, Universidad Politécnica de Madrid.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Feature selection is one of the most relevant processes in any methodology for creating a statistical learning model. Usually, existing algorithms establish some criterion to select the most influential variables, discarding those that do not contribute to the model with any relevant information. This methodology makes sense in a static situation where the joint distribution of the data does not vary over time. However, when dealing with real data, it is common to encounter the problem of the dataset shift and, specifically, changes in the relationships between variables (concept shift). In this case, the influence of a variable cannot be the only indicator of its quality as a regressor of the model, since the relationship learned in the training phase may not correspond to the current situation. In tackling this problem, our approach establishes a direct relationship between the Shapley values and prediction errors, operating at a more local level to effectively detect the individual biases introduced by each variable. The proposed methodology is evaluated through various examples, including synthetic scenarios mimicking sudden and incremental shift situations, as well as two real-world cases characterized by concept shifts. Additionally, we perform three analyses of standard situations to assess the algorithm’s robustness in the absence of shifts. The results demonstrate that our proposed algorithm significantly outperforms state-of-the-art feature selection methods in concept shift scenarios, while matching the performance of existing methodologies in static situations.

Förderung

  • Centro para el Desarrollo Tecnológico Industrial
  • Ministerio de Universidades
  • Universidad Politécnica de Madrid

Zitieren

APA

Sebastián, C., & González-Guillén, C. E. (2024). A feature selection method based on Shapley values robust for concept shift in regression. Neural Computing and Applications, 36(23), 14575-14597. https://doi.org/10.1007/s00521-024-09745-4

Vancouver

Sebastián C, González-Guillén CE. A feature selection method based on Shapley values robust for concept shift in regression. Neural Computing and Applications. 2024;36(23):14575-14597. doi:10.1007/s00521-024-09745-4

BibTeX
@article{Sebastin2024,
  author = {Sebastián, Carlos and González-Guillén, Carlos E.},
  title = {A feature selection method based on Shapley values robust for concept shift in regression},
  journal = {Neural Computing and Applications},
  year = {2024},
  volume = {36},
  number = {23},
  pages = {14575--14597},
  doi = {10.1007/s00521-024-09745-4}
}
Kostenlos starten →