How to Recognize and Explain Bidding Strategies in Negotiation Support Systems

Conference Paper (2021)
Authors

Vincent J. Koeman (Vrije Universiteit Amsterdam)

K.V. Hindriks (Vrije Universiteit Amsterdam)

J Gratch (University of Southern California)

Catholijn Jonker (TU Delft - Interactive Intelligence, Universiteit Leiden)

Research Group
Interactive Intelligence
Copyright
© 2021 Vincent J. Koeman, K.V. Hindriks, Jonathan Gratch, C.M. Jonker
To reference this document use:
https://doi.org/10.1007/978-981-16-0471-3_3
More Info
expand_more
Publication Year
2021
Language
English
Copyright
© 2021 Vincent J. Koeman, K.V. Hindriks, Jonathan Gratch, C.M. Jonker
Research Group
Interactive Intelligence
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. @en
Pages (from-to)
35-53
ISBN (print)
9789811604706
DOI:
https://doi.org/10.1007/978-981-16-0471-3_3
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Effective use of negotiation support systems depends on the systems capability of explaining itself to the user. This paper introduces the notion of an explanation matrix and an aberration detection mechanism for bidding strategies. The aberration detection is a mechanism that detects if one of the negotiating parties deviates from their expected behaviour, i.e. when a bid falls outside the range of expected behaviour for a specific strategy. The explanation matrix is used when to explain which aberrations to the user. The idea is that the user, when understanding the aberration, can take effective action to deal with the aberration. We implemented our aberration detection and our explanation mechanisms in the Pocket Negotiator (PN). We evaluated our work experimentally in a task in which participants are asked to identify their opponent’s bidding strategy, under different explanation conditions. As the number of correct guesses increases with explanations, indirectly, these experiments show the effectiveness of our aberration detection mechanism. Our experiments with over 100 participants show that suggesting consistent strategies is more effective than explaining why observed behaviour is inconsistent. An extended abstract of this article can be found in [15].

Files

Koeman2021_Chapter_HowToRecogn... (pdf)
(pdf | 0.645 Mb)
- Embargo expired in 05-12-2022
License info not available