CHIRPS: Explaining random forest classification

Hatwell, Julian and Gaber, Mohamed Medhat and Azad, R. Muhammad Atif (2020) CHIRPS: Explaining random forest classification. Artificial Intelligence Review. ISSN 0269-2821

Preview

Text Hatwell2020_Article_CHIRPSExplainingRandomForestCl.pdf - Published Version Available under License Creative Commons Attribution. Download (8MB)

Abstract

Modern machine learning methods typically produce “black box” models that are opaque to interpretation. Yet, their demand has been increasing in the Human-in-the-Loop pro-cesses, that is, those processes that require a human agent to verify, approve or reason about the automated decisions before they can be applied. To facilitate this interpretation, we propose Collection of High Importance Random Path Snippets (CHIRPS); a novel algorithm for explaining random forest classification per data instance. CHIRPS extracts a decision path from each tree in the forest that contributes to the majority classification, and then uses frequent pattern mining to identify the most commonly occurring split conditions. Then a simple, conjunctive form rule is constructed where the antecedent terms are derived from the attributes that had the most influence on the classification. This rule is returned alongside estimates of the rule’s precision and coverage on the training data along with counter-factual details. An experimental study involving nine data sets shows that classification rules returned by CHIRPS have a precision at least as high as the state of the art when evaluated on unseen data (0.91–0.99) and offer a much greater coverage (0.04–0.54). Furthermore, CHIRPS uniquely controls against under- and over-fitting solutions by maximising novel objective functions that are better suited to the local (per instance) explanation setting.

Item Type:	Article
Identification Number:	10.1007/s10462-020-09833-6
Dates:	Date Event 27 March 2020 Accepted 4 June 2020 Published Online
Uncontrolled Keywords:	XAI, model interpretability, random forests, classification, frequent patterns
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-05 - artificial intelligence
Divisions:	Faculty of Computing, Engineering and the Built Environment > College of Computing
Depositing User:	Mohamed Gaber
Date Deposited:	08 Jun 2020 09:38
Last Modified:	12 Jan 2022 12:58
URI:	https://www.open-access.bcu.ac.uk/id/eprint/9323

Actions (login required)

View Item