Implementing local-explainability in Gradient Boosting Trees: Feature Contribution

Bibliographic Details
Title: Implementing local-explainability in Gradient Boosting Trees: Feature Contribution
Authors: Delgado-Panadero, Ángel, Hernández-Lorca, Beatriz, García-Ordás, María Teresa, Benítez-Andrades, José Alberto
Source: Information Sciences, Volume 589, 2022, Pages 199-212
Publication Year: 2024
Collection: Computer Science
Subject Terms: Computer Science - Machine Learning, Computer Science - Logic in Computer Science
More Details: 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.
Document Type: Working Paper
DOI: 10.1016/j.ins.2021.12.111
Access URL: http://arxiv.org/abs/2402.09197
Accession Number: edsarx.2402.09197
Database: arXiv
More Details
DOI:10.1016/j.ins.2021.12.111