Research On Bidding Strategy In Continuous Double Auction Market Based On Multi-Agent System

In the 21 st years,along with the development of information technology,electronic commerce emerge as the times require,with the rapid development of electronic commerce,it not only make the exchange of information more convenienter,but also make online transactions more common.continuous double auction(CDA)has been widely applied to many trading areas of society,such as the NASDAQ,the New York Stock Exchange and other stock exchanges.Continuous double auction market mechanism can be divided into two parts,the mechanism design and bidding strategy,Recently scholars at domestic and abroad have made many a representative of bidding strategy,The bidding strategy for the traditional double auction market not only lack of intelligence,,but also did not phased transaction processing.To solve this problem,in this paper the following work was done:1.Firstly,Research on Bidding Strategy in Continuous Double Auction Market Based on Multi-Agent System,The characterizes of bidding strategy for the traditional double auction market is lack of intelligence,for this reason we present the design and analysis of a new self-adaptive bidding strategy(self-adaptive bidding strategy,SA bidding strategy)allows the trader to obtain a higher profit no matter which side it is.Not only heuristic rules but also a reasoning mechanism,short-term and long-term,are employed by this strategy.Agents adopting the strategy dynamically adjust their behaviors in response to the changes of the market.In the experiments,we studied the performance of the SA bidding strategies and compared it with other classic bidding strategies included ZI-C,ZI-U,AA,GNP-AP.Experimental results show that agents adopting the strategy superior to the other strategies in terms of trading success rate and profit.2.Through he inference mechanism of fuzzy cognitive map and the bidding process of Continuous double auction market were analyzed,Trading Agent bidding process found to satisfy a causal relationship,a bidding strategy based on FCM were proposed,and build a model of the Seller Agent i has a certain emotions based on FCMBS bidding strategy.Seller Agent i model has three emotional states produce three different emotional states,depending on the input information of the market.3.Finally,the paper presents FCMBS bidding strategy and SAbidding strategies respectively,ZI-C,ZI-U,GNP-AP and AA strategies were compared.In the course of the experiment were simulated market demand,supply and demand balance,oversupply three market status is verified by experiments FCMBS bidding strategies and SA bidding strategies,not only in terms of benefits is superior to other strategies,while transaction successing rate was dominant.