On Trustworthy Rule-Based Models and Explanations

TL;DR

This paper examines the challenges of providing trustworthy explanations for rule-based machine learning models, highlighting issues like negative overlap and redundancy, and develops algorithms to analyze these flaws.

Contribution

It introduces algorithms to analyze undesired facets of rule-based models, revealing that common learning tools often produce rule sets with negative traits.

Findings

Rule-based models often contain negative overlap and redundancy.

Existing learning tools tend to induce flawed rule sets.

Algorithms can identify and analyze these undesirable facets.

Abstract

A task of interest in machine learning (ML) is that of ascribing explanations to the predictions made by ML models. Furthermore, in domains deemed high risk, the rigor of explanations is paramount. Indeed, incorrect explanations can and will mislead human decision makers. As a result, and even if interpretability is acknowledged as an elusive concept, so-called interpretable models are employed ubiquitously in high-risk uses of ML and data mining (DM). This is the case for rule-based ML models, which encompass decision trees, diagrams, sets and lists. This paper relates explanations with well-known undesired facets of rule-based ML models, which include negative overlap and several forms of redundancy. The paper develops algorithms for the analysis of these undesired facets of rule-based systems, and concludes that well-known and widely used tools for learning rule-based ML models will induce rule sets that exhibit one or more negative facets.