RT info:eu-repo/semantics/article
T1 Implementing local-explainability in Gradient Boosting Trees: Feature Contribution
A1 Delgado Panadero, Ángel
A1 Hernández Lorca, Beatriz
A1 García Ordás, María Teresa
A1 Benítez Andrades, José Alberto
A2 Ingenieria de Sistemas y Automatica
K1 Informática
K1 Ingenierías
K1 XAI
K1 Gradient boosting trees
K1 Explainable artificial intelligence
K1 1203.17 Informática
K1 1206.01 Construcción de Algoritmos
AB [EN] Gradient Boost Decision Trees (GBDT) is a powerful additive model based on tree ensembles. Its nature makes GBDT a black-box model even though there are multiple explainable artificial intelligence (XAI) models obtaining information by reinterpreting the model globally and locally. Each tree of the ensemble is a transparent model itself but the final outcome is the result of a sum of these trees and it is not easy to clarify. In this paper, a feature contribution method for GBDT is developed. The proposed method takes advantage of the GBDT architecture to calculate the contribution of each feature using the residue of each node. This algorithm allows to calculate the sequence of node decisions given a prediction. Theoretical proofs and multiple experiments have been carried out to demonstrate the performance of our method which is not only a local explicability model for the GBDT algorithm but also a unique option that reflects GBDTs internal behavior. The proposal is aligned to the contribution of characteristics having impact in some artificial intelligence problems such as ethical analysis of Artificial Intelligence (AI) and comply with the new European laws such as the General Data Protection Regulation (GDPR) about the right to explain and nondiscrimination.
PB Elsevier
SN 0020-0255
LK https://hdl.handle.net/10612/19025
UL https://hdl.handle.net/10612/19025
NO Delgado-Panadero, Á., Hernández-Lorca, B., García-Ordás, M. T., & Benítez-Andrades, J. A. (2022). Implementing local-explainability in Gradient Boosting Trees: Feature Contribution. Information Sciences. https://doi.org/10.1016/j.ins.2021.12.111
DS BULERIA. Repositorio Institucional de la Universidad de León
RD 01-jun-2024