Intelligent Agent for Prediction in E-Negotiation: An Approach

Journal of Software Engineering and Applications, 2015

The research in the area of automated negotiation systems is going on in many universities. This research is mainly focused on making a practically feasible, faster and reliable E-negotiation system. The ongoing work in this area is happening in the laboratories of the universities mainly for training and research purpose. There are number of negotiation systems such as Henry, Kasbaah, Bazaar, Auction Bot, Inspire, and Magnet. Our research is based on making an agent software for E-negotiation which will give faster results and also is secure and flexible. The negotiation partners and contents between the service providers change frequently. The negotiation process can be transformed into rules and cases. Using these features, a new automated negotiation model for agent integrating rule based and case based reasoning can be derived. We propose an E-negotiation system, in which all product information and multiple agent details are stored on the cloud. An E-negotiation agent acts as a negotiator. Agent has user's details and their requirements for a particular product. It will check rules based data whether any rule is matching with the user requirement. An agent will see case based data to check any similar negotiation case matching to the user requirement. If a case matches with user requirement, then agent will start the negotiation process using case based data. If any rule related requirement is found in the rule base data, then agent will start the negotiation process using rule based data. If both rules based data and cases based data are not matching with the user requirement, then agent will start the negotiation process using Bilateral Negotiation model. After completing negotiation process, agent gives feedback to the user about whether negotiation is successful or not. The product details, S. R. Vij et al. 522 rule based data, and case based data will be stored on the cloud. So that system automatically becomes flexible. We also compare E-negotiation agent automated negotiation and behavior prediction system to prove that using rule based and case based approaches system should become fast.

Proceedings of the International Scientific Conference - Sinteza 2020

Artificial intelligence can perform many different tasks in negotiation, reducing time and effort on the part of human negotiators. Today there is an increasing number of negotiation support systems and automated negotiating agents, that can assist human negotiators before and during the process. They can serve as simulators and training tools, but also conduct negotiations more or less autonomously. The aim of this paper is to review different forms of electronic negotiations and current issues in this field.

Springer eBooks, 2008

Knowledge about conflict styles and time pressure during a negotiation are important factors in a negotiation. This knowledge is used to model an agentbased assistant for e-negotiations. The idea of the proposed method is to model a utility concession function depending on the conflict style behaviour of a negotiator. Negotiators, prior to engage in e-negotiations, are asked to fill in a questionnaire designed to measure the conflict mode and specify their reservation levels. The agent-based assistant uses reservation levels and a concession-making model to propose the concession and timing of offers and attributes e.g. in a multiattribute negotiation. The concession-making model is constructed in the utility space and it is constructed using the Thomas-Kilmann Conflict Mode Instrument and negotiation data from an experiment conducted by human negotiators.

Advances in Intelligent Systems and Computing, 2012

In this era of "Services" everywhere, with the explosive growth of E-Commerce and B2B transactions, there is a pressing need for the development of intelligent negotiation systems which consists of feasible architecture, a reliable framework and flexible multi agent based protocols developed in specialized negotiation languages with complete semantics and support for message passing between the buyers and sellers. This is possible using web services on the internet. The key issue is negotiation and its automation. In this paper we review the classical negotiation methods and some of the existing architectures and frameworks. We are proposing here a new combinatory framework and architecture, NAAS. The key feature in this framework is a component for prediction or probabilistic behavior pattern recognition of a buyer, along with the other classical approaches of negotiation frameworks and architectures. Negotiation is practically very complex activity to automate without human intervention so in the future we also intend to develop a new protocol which will facilitate automation of all the types of negotiation strategies like bargaining, bidding, auctions, under our NAAS framework.

Advanced Research on Cloud Computing Design and Applications, 2015

The research in the area of automated negotiation systems is going on in many universities. This research is mainly focused on making a practically feasible, faster and reliable E-negotiation system. The ongoing work in this area is happening in the laboratories of the universities mainly for training and research purpose. There are number of negotiation systems such as Henry, Kasbaah, Bazaar, Auction Bot, Inspire, Magnet. Our research is based on making an agent software for E-negotiation which will give faster results and also is secure and flexible. Cloud Computing provides security and flexibility to the user data. Using these features we propose an E-negotiation system, in which, all product information and agent details are stored on the cloud. This system proposes three conditions for making successful negotiation. First rule based, where agent will check user requirements with rule based data. Second case based, where an agent will see case based data to check any similar previous negotiation case is matching to the user requirement. Third bilateral negotiation model, if both rules based data and case based data are not matching with the user requirement, then agent use bilateral negotiation model for negotiation. After completing negotiation process, agents give feedback to the user about whether negotiation is successful or not. Using rule based reasoning and case based reasoning this system will improve the efficiency and success rate of the negotiation process.

INTERNATIONAL JOURNAL ON Advances in Information Sciences and Service Sciences, 2011

To automate most of commerce time-consuming stages of the buying process, software agent's technologies have been proposed and employed in different transaction stages of e-commerce. The agents in e-negotiation dialogs based on their owner requirements until reaching agreement on one or multi issues of the negotiation. In addition, in many real conditions negotiation, negotiation agents have only limited information about their opponents and bounded rationality. Therefore, using heuristic algorithm to develop negotiation agents' decision-making mechanism is useful. For this propose, we proposed framework of intelligent agent based interactive recommendation and automated negotiation system in B2C e-commerce, so we expect that the negotiation time and transaction cost are reduced.

2004

Nowadays, many researches are being been made for the development of new transaction system in an effort to transform current off-line system into on-line one. However, these researches mainly focuses on ordinary commercial transaction system, i.e. the one that supports fixed price transaction, in which consumers usually ought to buy goods at the price offered by sellers. Accordingly, more studies are to be made for the system to support both buyers and sellers in searching the proper price level through negotiations. Under current e-commerce environment, an automated negotiation system is badly needed to respond quickly and flexibly to the diverse environmental changes and also to perform many negotiations consistently and effectively. To this end, this paper has developed a multi-agent based automated negotiation system. This new system creates multi-issue negotiation proposals automatically, evaluating the counterpart's proposal, and then, if necessary, preparing and sending counter proposals time and again, and finally accepting or rejecting.

2001

Electronic Commerce technology has changed the way traditional business is being done. Transactions’ complexity is increased due both to the huge amount of available information and also to the environment dynamics. Moreover, Electronic Commerce has enabled the arising of new economical structures, as it is the case of Virtual Organisations. Our research aims at providing flexible and general-purpose systems for intelligent negotiation, both for Electronic Commerce and Virtual Organisation formation. This paper proposes an Electronic Market architecture implemented through a Multi-Agent system. This architecture includes both a specific market agent which plays the role of market coordinator, as well as agents representing the individual business partners with their own goals and strategies. We also include a sophisticated negotiation protocol through multi-criteria and distributed constraint formalisms. An online, continuous reinforcement learning algorithm has been designed to enable agents to adapt themselves according to the changing environment, including the competitor agents.

Scalable Computing: Practice and Experience, 2014

An automated negotiation environment, in which agents employ different bargaining strategies is described. During negotiation, as more information is exchanged in the negotiation rounds, the agents can change the preferences for certain attributes of the negotiation object. The multi-agent system is developed for a real estate agency business model and several use cases scenarios, using intelligent software agents, are implemented.

2003

Abstract. Support for negotiation is one of the more important research issues when developing agent systems utilized in e-commerce. While, depending on the type of the transaction, different negotiation procedures need to be utilized, only very few proposed frameworks are generic and flexible enough to handle multiple scenarios. This note presents negotiating agents, which can change their negotiation strategy depending on circumstances.