Deniz: A Robust Bidding Strategy for Negotiation Support Systems

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

This paper presents the Deniz agent that has been specifically designed to support human negotiators in their bidding. The design of Deniz is done with the criteria of robustness and the availability of small data, due to a small number of negotiation rounds in mind. Deniz’s bidding strategy is based on an existing optimal concession strategy that concedes in relation to the expected duration of the negotiation. This accounts for the small data and small number of rounds. Deniz deploys an adaptive behavior-based mechanism to make it robust against exploitation. We tested Deniz against typical bidding strategies and against human negotiators. Our evaluation shows that Deniz is robust against exploitation and gains statistically significant higher utilities than human test subjects, even though it is not designed specifically to get the highest utility against humans.

Original languageEnglish
Title of host publicationAdvances in Automated Negotiations, ACAN 2018
EditorsTakayuki Ito, Minjie Zhang, Reyhan Aydogan
PublisherSpringer
Pages29-44
Number of pages16
ISBN (Print)9789811558689
DOIs
Publication statusPublished - 2021
Event11th International Workshop on Automated Negotiation, ACAN 2018 - Stockholm, Sweden
Duration: 13 Jul 201819 Jul 2018

Publication series

NameStudies in Computational Intelligence
Volume905
ISSN (Print)1860-949X
ISSN (Electronic)1860-9503

Conference

Conference11th International Workshop on Automated Negotiation, ACAN 2018
CountrySweden
CityStockholm
Period13/07/1819/07/18

Fingerprint Dive into the research topics of 'Deniz: A Robust Bidding Strategy for Negotiation Support Systems'. Together they form a unique fingerprint.

Cite this