An explainable multi-attribute decision model based on argumentation

Journal article 971 views 293 downloads

Qiaoting Zhong, Xiuyi Fan, Xudong Luo, Francesca Toni

Expert Systems with Applications, Volume: 117, Pages: 42 - 61

Swansea University Author: Xiuyi Fan

PDF | Accepted Manuscript

Released under the terms of a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND).
Download (830.65KB)

DOI (Published version): 10.1016/j.eswa.2018.09.038

Published in:	Expert Systems with Applications
ISSN:	09574174
Published:	2019
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa44264
Tags:	Add Tag No Tags, Be the first to tag this record!

Item Description:	Originality:In this paper, we present a multi-attribute decision model and a method for explaining the decisions it recommends based on an argumentative reformulation of the model. Specifically, (i) we define a notion of best decisions amounting to achieving as many goals as possible and exhibiting as few redundant attributes as possible, and (ii) we generate explanations for why a decision is best or better than or as good as another.Significance:Explainability is important to automatic decision-making systems as without a clear understanding of how a recommended decision is generated, it is hard to ensure human trust, debug and improve these systems. By connecting decision making with argumentation, this work provides a mechanism for realizing explainable decision making. Rigor:All results are shown with full proofs. We also conduct an empirical evaluation of our method with legal practitioners, confirming that our method is helpful to understand automatically generated recommendations.
Keywords:	argumentation, decision making, explanation
Start Page:	42
End Page:	61