Agents that react to changing market situations

被引:70
作者
Sim, KM [1 ]
Choi, CY
机构
[1] Chinese Univ Hong Kong, Dept Informat Engn, Shatin, Hong Kong, Peoples R China
[2] Hong Kong & Shanghai Banking Corp, Hong Kong, Hong Kong, Peoples R China
来源
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS | 2003年 / 33卷 / 02期
关键词
negotiation agent; reactive agent;
D O I
10.1109/TSMCB.2002.805694
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Market-driven agents are negotiation agents that react to changing. market situations by making adjustable rates of concession. This paper presents 1) the,foundations for designing market-driven strategies of agents, 2) a testbed of market-driven agents, 3) experimental results in simulating the market-driven approach, and 4) theoretical analyses of agents' performance in extremely large markets. In determining the amount of concession for each trading cycle, market-driven agents in this research are guided by four mathematical functions of eagerness, remaining trading time, trading opportunity, and competition. At different stages of trading, agents may adopt different trading strategies, and make different rates of concession. Four classes of strategies with respect to remaining trading time are discussed. Trading opportunity is determined by considering: 1) number of trading partners, 2) spreads-differences in utilities between an agent and its trading partners, and 3) probability of completing a deal. While eagerness represents an agent's desire to trade, trading competition is determined by the probability that it is not considered as the most preferred trader by its trading partners. Experimental results and theoretical analyses showed that agents guided by market-driven strategies 1) react to changing market situations by making prudent and appropriate rates of concession, and 2) achieve trading outcomes that correspond to intuitions in real-life trading.
引用
收藏
页码:188 / 201
页数:14
相关论文
共 31 条
[1]  
[Anonymous], 1989, MICROECONOMIC THEORY
[2]  
Bazerman MH., 1992, NEGOTIATING RATIONAL
[3]   Learning other agents' preferences in multi-agent negotiation using the Bayesian classifier [J].
Bui, HH ;
Venkatesh, S ;
Kieronska, D .
INTERNATIONAL JOURNAL OF COOPERATIVE INFORMATION SYSTEMS, 1999, 8 (04) :275-293
[4]  
Chavez A, 1996, P 1 INT C PRACT APPL
[5]  
CHAVEZ A, 1997, P 2 INT C PRACT APPL
[6]  
CHOI CY, 2001, THESIS HONG KONG POL
[7]  
Cross John., 1969, EC BARGAINING
[8]  
DAELLENBACH H, 1978, INTRO OPERATION RES
[9]  
GREENWALD D, 1983, MCGRAWHILL DICT MODE
[10]  
GUTTMAN R, 1998, P WORKSH AG MED EL T