A multi-agent negotiation decision support system for Australian Family Law

Full text for this resource is not available from the Research Repository.

Abrahams, Brooke and Zeleznikow, John ORCID: 0000-0002-8786-2644 (2010) A multi-agent negotiation decision support system for Australian Family Law. In: Bridging the Socio-technical Gap in Decision Support Systems. Respicio, Ana, Adam, Frederic, Phillips-Wren, Gloria, Teixeira, Carlos and Telhada, Joao, eds. Frontiers in Artificial Intelligence and Applications, 212 . IOS Press, Amsterdam, pp. 297-308.

Abstract

The paper describes the development of an integrated multi-agent negotiation decision support system designed to assist parties involved in Australian family law disputes achieve legally fairer negotiated outcomes. The system extends our previous work in developing negotiation support systems Family_Winner and AssetDivider. In this environment one agent uses a Bayesian Belief Network expertly modeled with knowledge of the Australian Family Law domain to advise disputants of their Best Alternatives to Negotiated Agreements via a percentage property split. Another agent incorporates this percentage split into an integrative bargaining process and applies heuristics and game theory to equitably distribute marital property assets and facilitate further trade-offs. The purpose of the system is to add greater fairness to family property law negotiations.

Dimensions Badge

Altmetric Badge

Item type Book Section
URI https://vuir.vu.edu.au/id/eprint/9960
DOI 10.3233/978-1-60750-577-8-297
ISBN 9781607505761, 9781607505778
Subjects Historical > Faculty/School/Research Centre/Department > School of Management and Information Systems
Historical > FOR Classification > 0806 Information Systems
Keywords ResPubID21574, BATNAs, Bayesian belief networks, integrative negotiation, multi-agent systems, negotiation decision support systems, Australia
Citations in Scopus 3 - View on Scopus
Download/View statistics View download statistics for this item

Search Google Scholar

Repository staff login