A Notion of Feature Importance by Decorrelation and Detection of Trends by Random Forest Regression Cover

A Notion of Feature Importance by Decorrelation and Detection of Trends by Random Forest Regression

Data Science Journal

Volume 22 (2023): Issue 1

By: Yannick Gerstorfer, Max Hahn-Klimroth and Lena Krieg

Open Access

|Nov 2023

Authors

Yannick Gerstorfer

gerstorfer@fias.uni-frankfurt.de

Frankfurt Institute for Advanced Studies, Goethe University Frankfurt Frankfurt 60325

Max Hahn-Klimroth

maximilian.hahnklimroth@tu-dortmund.de

Faculty of Computer Sciences, TU Dortmund University Dortmund 44227

Lena Krieg

lena.krieg@tu-dortmund.de

Faculty of Computer Sciences, TU Dortmund University Dortmund 44227

DOI: https://doi.org/10.5334/dsj-2023-042 | Journal eISSN: 1683-1470

Journal RSS Feed

Language: English

Submitted on: May 26, 2023

Accepted on: Sep 27, 2023

Published on: Nov 3, 2023

Published by: Ubiquity Press

In partnership with: Paradigm Publishing Services

Publication frequency: 1 issue per year

Keywords:

Explainable Artificial Intelligence,

Feature Importance,

Gram-Schmidt Decorrelation,

Random Forest Regression,

Trend Estimation

© 2023 Yannick Gerstorfer, Max Hahn-Klimroth, Lena Krieg, published by Ubiquity Press
This work is licensed under the Creative Commons Attribution 4.0 License.

Previous article Volume 22 (2023): Issue 1 Next article