2010

Conférence

Agent and Multi-Agent Systems: Technologies and Applications, 4th KES International Symposium, KES-AMSTA 2010, June 23-25, 2010, Proceedings. Part II pp. 302-311, Gdynia, Poland.

In this paper, we study the stock market trading behavior and the interactions between traders. We propose a novel model which includes behavioral and cognitive attitudes of the trader at the micro level and explains their effects on his decision making at the macro level. The proposed simulator is composed of heterogeneous Trader agents with a behavioral cognitive model and the CentralMarket agent matching buying and selling orders. Our artificial stock market is implemented using distributed artificial intelligence techniques. The resulting simulation system is a tool able to numerically simulate financial market operations in a realistic way. Experiments show that representing the micro level led us to validate some stylized facts related to stock market and to observe emergent socio-economic phenomena at the macro level.

@InProceedings{10.1007/978-3-642-00487-2_10,

author="Kodia, Zahra

and Said, Lamjed Ben",

editor="Demazeau, Yves

and Pav{\'o}n, Juan

and Corchado, Juan M.

and Bajo, Javier",

title="Multi-agent Simulation of Investor Cognitive Behavior in Stock Market",

booktitle="7th International Conference on Practical Applications of Agents and Multi-Agent Systems (PAAMS 2009)",

year="2009",

publisher="Springer Berlin Heidelberg",

address="Berlin, Heidelberg",

pages="90--99",

abstract="In this paper, we introduce a new model of Investor cognitive behavior in stock market. This model describes the behavioral and cognitive attitudes of the Investor at the micro level and explains their effects on his decision making. A theoretical framework is discussed in order to integrate a set of multidisciplinary concepts. A Multi-Agent Based Simulation (MABS) is used to: (1) validate our model, (2) build an artificial stock market: SiSMar and (3) study the emergence of certain phenomena relative to the stock market dynamics at the macro level. The proposed simulator is composed of heterogeneous Investor agents with a behavioral cognitive model, an Intermediary agent and the CentralMarket agent matching buying and selling orders. Our artificial stock market is implemented using distributed artificial intelligence techniques. The resulting simulator is a tool able to numerically simulate financial market operations in a realistic way. Preliminary results show that representing the micro level led us to build the stock market dynamics, and to observe emergent socio-economic phenomena at the macro level.",

isbn="978-3-642-00487-2"

}