Visualizing Rule Sets: Exploration and Validation of a Design Space

TL;DR

This paper investigates visual representations of rule sets in machine learning to improve readability and understanding, presenting a design space and user study to evaluate their effectiveness.

Contribution

It introduces a novel visual design space for rule sets and empirically evaluates how visual factors influence rule comprehension.

Findings

Certain visual design factors significantly improve processing efficiency.

Visual representations have minimal impact on rule accuracy.

The work offers practical guidance for better rule communication in ML.

Abstract

Rule sets are often used in Machine Learning (ML) as a way to communicate the model logic in settings where transparency and intelligibility are necessary. Rule sets are typically presented as a text-based list of logical statements (rules). Surprisingly, to date there has been limited work on exploring visual alternatives for presenting rules. In this paper, we explore the idea of designing alternative representations of rules, focusing on a number of visual factors we believe have a positive impact on rule readability and understanding. The paper presents an initial design space for visualizing rule sets and a user study exploring their impact. The results show that some design factors have a strong impact on how efficiently readers can process the rules while having minimal impact on accuracy. This work can help practitioners employ more effective solutions when using rules as a communication strategy to understand ML models.