City Research Online

Abstract

Traditional interpretability techniques such as rule-based models and feature attribution methods, each offer complementary strengths, however are often applied in isolation. Rule-based approaches are intuitive and logically structured, making them easy to understand, but they often struggle to scale effectively. On the other hand, feature attribution techniques like SHAP are well-suited to handling complex models and large datasets but can fall short in terms of interpretability and alignment with human reasoning. In this paper, we introduce a hybrid, human-centric interpretability framework that integraes rule-based modelling with SHAP-based feature attributions within a visual analytics framework and show the benefits for interpretability and interactivity through such techniques. We validate the framework on a case-study of Fishing-vessel trajectories and demonstrate how this integrated approach reveals patterns and discrepancies that would not have been seen using a single approach alone.

Publication Type:	Conference or Workshop Item (Paper)
Additional Information:	This version of the contribution has been accepted for publication, after peer review but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-032-19105-2_39. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms
Publisher Keywords:	Explainable AI, Visual Analytics, Rule-based, featurebased, interpretability
Subjects:	H Social Sciences > HN Social history and conditions. Social problems. Social reform Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments:	School of Science & Technology School of Science & Technology > Department of Computer Science School of Science & Technology > Department of Computer Science > giCentre
SWORD Depositor:	Symplectic Administrator

Export

Downloads