gbt-HIPS: Explaining the Classifications of Gradient Boosted Tree Ensembles

gbt-HIPS: Explaining the Classifications of Gradient Boosted Tree Ensembles

This research presents <i>Gradient Boosted Tree High Importance Path Snippets</i> (gbt-HIPS), a novel, heuristic method for explaining gradient boosted tree (GBT) classification models by extracting a single classification rule (CR) from the ensemble of decision trees that make up the GB...

Full description

Bibliographic Details
Main Authors: Julian Hatwell, Mohamed Medhat Gaber, R. Muhammad Atif Azad
Format: Article
Language:English
Published: MDPI AG 2021-03-01
Series:Applied Sciences
Subjects:
explainable artificial intelligence
human-understandable AI systems
gradient boosting
black box problem
machine learning interpretability
Online Access:https://www.mdpi.com/2076-3417/11/6/2511

Internet

https://www.mdpi.com/2076-3417/11/6/2511

Similar Items