MétaCan
Menu
Back to cohort
Record W1541027861

An interactive system for negotiation in e-commerce with incremental user knowledge

2005· article· en· W1541027861 on OpenAlexaff
Mashrur Mia, Sudhir P. Mudur, T. Radhakrishnan

Bibliographic record

VenueConference of the Centre for Advanced Studies on Collaborative Research · 2005
Typearticle
Languageen
FieldComputer Science
TopicMulti-Agent Systems and Negotiation
Canadian institutionsConcordia University
Fundersnot available
KeywordsNegotiationComputer scienceArchitectureProcess (computing)Software agentProduct (mathematics)Human–computer interactionUser interfaceE-commerceKnowledge managementSoftwareWorld Wide WebArtificial intelligence
DOInot available

Abstract

fetched live from OpenAlex

In retail electronic commerce, incomplete user knowledge is a reality that must be addressed by electronic negotiation models and systems. This is particularly true in the case of multi-attribute products where valid product-configurations may require several constraints on attribute-values to be satisfied. Often, in such cases, the individual buyer refines the preferences for individual attributes as more and more information is exchanged during the negotiation process in an incremental fashion. In this paper, we consider how the negotiating parties can benefit from the incremental knowledge as the negotiation progresses. We assume the trust between the customer and merchant is such that the negotiation is for the purpose of seeking a mutually acceptable configuration of the product and its price. We have implemented a prototype system in which negotiation takes place between a human customer and multiple autonomous software agents, each carrying out sales operations on behalf of different merchants. We also describe the architecture of such an interactive multi-issue negotiation system on a distributed platform. The paper describes the various models we have used, and the multi-agent based software architecture that facilitates the interaction and the user interface. Our initial experiences with the prototype gives hope that e-commerce negotiation systems, in future, can benefit by making use of the incremental knowledge during the negotiation process.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.605
Threshold uncertainty score0.470

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.102
GPT teacher head0.421
Teacher spread0.319 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2005
Admission routes1
Has abstractyes

Explore more

Same venueConference of the Centre for Advanced Studies on Collaborative ResearchSame topicMulti-Agent Systems and NegotiationFrench-language works237,207