Intelligent agents for automated one-to-many e-commerce negotiation
ACSC '02 Proceedings of the twenty-fifth Australasian conference on Computer science - Volume 4
The Distributed Constraint Satisfaction Problem: Formalization and Algorithms
IEEE Transactions on Knowledge and Data Engineering
On Constraint-Based Reasoning in e-Negotiation Agents
Agent-Mediated Electronic Commerce III, Current Issues in Agent-Based Electronic Commerce Systems (includes revised papers from AMEC 2000 Workshop)
| Hi-index | 0.00 |
Automated Negotiation is a process in which two or more parties with different criteria, constraints, and preferences, jointly reach an agreement on the terms of a transaction through an automated constraint satisfaction and preference selection mechanism. In practical real environment the process of negotiation is not very strictly a mechanical selection or constraint satisfaction. It is based socio economic psycho conditions. One-to-many negotiation framework is taken as the default to test this socio economic psycho knowledge incorporation. In these cases of auctions, online trading needs a greater flexibility. Therefore it needs different strategies with different opponents. In this paper, an attempt is made to incorporate the socio economic psycho knowledge in the process of negotiation. All agents working on behalf of one party negotiate individually with other parties. After each negotiation cycle, the group of these agents report back to a coordinating agent that evaluates how well each agent has done, and issues new instructions accordingly. Each individual agent conducts reasoning by using socio psycho knowledge constraint-based technique with the objective of overall profit for both sides. We outline two levels of strategies that can be exercised on two levels, the individual negotiation level, and the coordination level. In our prototype Intelligent Trading Agency (ITA), agents autonomously negotiate multiattribute with socio economic psycho consideration terms of transactions in an e-commerce environment tested with a personal computer trading scenario.