Deniz: A Robust Bidding Strategy for Negotiation Support Systems

Catholijn M. Jonker; Reyhan Aydoğan

doi:10.1007/978-981-15-5869-6_3

Deniz: A Robust Bidding Strategy for Negotiation Support Systems

^*Corresponding author for this work

Interactive Intelligence

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

5 Citations (Scopus)

116 Downloads (Pure)

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 language	English
Title of host publication	Advances in Automated Negotiations, ACAN 2018
Editors	Takayuki Ito, Minjie Zhang, Reyhan Aydogan
Publisher	Springer
Pages	29-44
Number of pages	16
ISBN (Print)	9789811558689
DOIs	https://doi.org/10.1007/978-981-15-5869-6_3
Publication status	Published - 2021
Event	11th International Workshop on Automated Negotiation, ACAN 2018 - Stockholm, Sweden Duration: 13 Jul 2018 → 19 Jul 2018

Publication series

Name	Studies in Computational Intelligence
Volume	905
ISSN (Print)	1860-949X
ISSN (Electronic)	1860-9503

Conference

Conference	11th International Workshop on Automated Negotiation, ACAN 2018
Country/Territory	Sweden
City	Stockholm
Period	13/07/18 → 19/07/18

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Access to Document

10.1007/978-981-15-5869-6_3

DenizAgentPNACANInvitedAccepted author manuscript, 1.56 MB

Cite this

@inproceedings{65247df42122486e98bbf7ca6e31f720,

title = "Deniz: A Robust Bidding Strategy for Negotiation Support Systems",

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{\textquoteright}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.",

author = "Jonker, {Catholijn M.} and Reyhan Aydoğan",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. ; 11th International Workshop on Automated Negotiation, ACAN 2018 ; Conference date: 13-07-2018 Through 19-07-2018",

year = "2021",

doi = "10.1007/978-981-15-5869-6_3",

language = "English",

isbn = "9789811558689",

series = "Studies in Computational Intelligence",

publisher = "Springer",

pages = "29--44",

editor = "Takayuki Ito and Minjie Zhang and Reyhan Aydogan",

booktitle = "Advances in Automated Negotiations, ACAN 2018",

}

Jonker, CM & Aydoğan, R 2021, Deniz: A Robust Bidding Strategy for Negotiation Support Systems. in T Ito, M Zhang & R Aydogan (eds), Advances in Automated Negotiations, ACAN 2018. Studies in Computational Intelligence, vol. 905, Springer, pp. 29-44, 11th International Workshop on Automated Negotiation, ACAN 2018, Stockholm, Sweden, 13/07/18. https://doi.org/10.1007/978-981-15-5869-6_3

Deniz: A Robust Bidding Strategy for Negotiation Support Systems. / Jonker, Catholijn M.; Aydoğan, Reyhan.
Advances in Automated Negotiations, ACAN 2018. ed. / Takayuki Ito; Minjie Zhang; Reyhan Aydogan. Springer, 2021. p. 29-44 (Studies in Computational Intelligence; Vol. 905).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Deniz

T2 - 11th International Workshop on Automated Negotiation, ACAN 2018

AU - Jonker, Catholijn M.

AU - Aydoğan, Reyhan

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85091274100&partnerID=8YFLogxK

U2 - 10.1007/978-981-15-5869-6_3

DO - 10.1007/978-981-15-5869-6_3

M3 - Conference contribution

AN - SCOPUS:85091274100

SN - 9789811558689

T3 - Studies in Computational Intelligence

SP - 29

EP - 44

BT - Advances in Automated Negotiations, ACAN 2018

A2 - Ito, Takayuki

A2 - Zhang, Minjie

A2 - Aydogan, Reyhan

PB - Springer

Y2 - 13 July 2018 through 19 July 2018

ER -

Deniz: A Robust Bidding Strategy for Negotiation Support Systems

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this