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

Hatwell, Julian and Gaber, Mohamed Medhat and Azad, R. Muhammad Atif (2021) gbt-HIPS: Explaining the Classifications of Gradient Boosted Tree Ensembles. Applied Sciences, 11 (6). p. 2511. ISSN 2076-3417

Preview

Text applsci-11-02511.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB)

Abstract

This research presents Gradient Boosted Tree High Importance Path Snippets (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 GBT model. This CR contains the most statistically important boundary values of the input space as antecedent terms. The CR represents a hyper-rectangle of the input space inside which the GBT model is, very reliably, classifying all instances with the same class label as the explanandum instance. In a benchmark test using nine data sets and five competing state-of-the-art methods, gbt-HIPS offered the best trade-off between coverage (0.16–0.75) and precision (0.85–0.98). Unlike competing methods, gbt-HIPS is also demonstrably guarded against under- and over-fitting. A further distinguishing feature of our method is that, unlike much prior work, our explanations also provide counterfactual detail in accordance with widely accepted recommendations for what makes a good explanation.

Item Type:	Article
Identification Number:	10.3390/app11062511
Dates:	Date Event 6 March 2021 Accepted 11 March 2021 Published
Uncontrolled Keywords:	explainable artificial intelligence; human-understandable AI systems; gradient boosting; black box problem; machine learning interpretability
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science CAH11 - computing > CAH11-01 - computing > CAH11-01-05 - artificial intelligence
Divisions:	Faculty of Computing, Engineering and the Built Environment > College of Computing
Depositing User:	Atif Azad
Date Deposited:	12 Mar 2021 11:03
Last Modified:	12 Jan 2022 12:58
URI:	https://www.open-access.bcu.ac.uk/id/eprint/11268

Actions (login required)

View Item