SIMULATING AN EVOLUTIONARY MULTI-AGENT BASED MODEL OF THE STOCK MARKET

Diana MARICA

Abstract


The paper focuses on artificial stock market simulations using a multi-agent model incorporating 2,000 heterogeneous agents interacting on the artificial market. The agents interaction is due to trading activity on the market through a call auction trading mechanism. The multi-agent model uses evolutionary techniques such as genetic programming in order to generate an adaptive and evolving population of agents. Each artificial agent is endowed with wealth and a genetic programming induced trading strategy. The trading strategy evolves and adapts to the new market conditions through a process called breeding, which implies that at each simulation step, new agents with better trading strategies are generated by the model, from recombining the best performing trading strategies and replacing the agents which have the worst performing trading strategies. The simulation model was build with the help of the simulation software Altreva Adaptive Modeler which offers a suitable platform for financial market simulations of evolutionary agent based models, the S&P500 composite index being used as a benchmark for the simulation results.


Keywords


Multi-agent based modeling; Artificial stock market; Genetic programming; Heterogeneous agents; Simulations

References


Allen, F., & R. Karjalainen (1999), Using genetic algorithms to find technical trading rules, Journal of Financial Economics, 51, pp. 245–271.

Aloud, M., Fasli, M. & Tsang, E. (2013) Modelling the High-Frequency FX Market: an Agent-Base Approach, University of Essex, Colchester, PhD Thesis. http://fac.ksu.edu.sa/sites/default/files/MoniraAloud-Ph.D.Thesis.pdf , accessed October 24, 2014

Arthur, B., Holland, J., & LeBaron, B. (1997) Asset Pricing Under Endogenous Expectations in an Artificial Stock Market, Published In: Arthur, W.B., Durlauf, S.N., Lane, D. The economy as an evolving, complex system II, Redwood City, CA., Addison Wesley, pp. 15-44.

Demir, A., Shadmanov, A., Aydinli, C., & Eray, O. (2015). Designing a forecast model for economic growth of Japan using competitive (hybrid ANN vs multiple regression) models. Ecoforum Journal, 4(2), pp. 49-55. http://www.ecoforumjournal.ro/index.php/eco/article/view/174/111 , accessed June 18, 2015.

Holland, J., & J. Miller (1991), Artificial adaptive agents in economic theory, The American Economic Review, 81, pp. 365–370

Hommes, C. (2006), Heterogeneous agent models in economics and finance, in Handbook of Computational Economics, vol. 2, edited by L. Tesfatsion and K. L. Judd, chap. 23, pp. 1109–1186, Elsevier.

Koza, J. (1992), Genetic Programming: on the Programming of Computers by Means of Natural Selection, The MIT Press, Cambridge.

LeBaron, B. (2006), Agent-based computational finance, in Handbook of Computational Economics, vol. 2, edited by L. Tesfatsion and K. L. Judd, 1 ed., chap. 24, pp. 1187–1233, Elsevier

Leigh, W., R. Purvis, & J. Ragusa (2002), Forecasting the NYSE composite index with technical analysis, pattern recognizer, neural networks, and genetic algorithm: a case study in romantic decision support, Decision Support Systems, 32, pp. 361–377

Lux, T., , & S. Schornstein (2005), Genetic learning as an explanation of stylized facts of foreign exchange markets, Journal of Mathematical Economics, 41(1-2), pp. 169–196

Marchesi, M., S. Cincotti, S. Focardi, & M. Raberto (2000), Development and testing of an artificial stock market, in Modelli Dinamici in Economia e Finanza, Urbino.

Matsumoto, M., & Nishimura, T. (1998) Mersenne Twister: A 623-dimensionally equidistributed uniform pseudorandom number generator. ACM Trans. on Modeling and Computer Simulation, 8 (1), pp. 3-30.

Montana, D. (2002) Strongly Typed Genetic Programming, Evolutionary Computation, 3(2), pp. 199-230.

Phelps, S., Marcinkiewicz, M., & Parsons, S. (2005) Using population-based search and evolutionary game theory to acquire better-response strategies for the double-auction market. In Proceedings of IJCAI-05 Workshop on Trading Agent Design and Analysis (TADA-05).

Raberto, M., & S. Cincotti (2005), Analysis and simulation of a double auction artificial financial market, Physica A, 355, pp. 34–45.

Walia, V., Byde, A., & Cliff, D. (2003). Evolving Market Design in Zero-Intelligence Trader Markets. In IEEE International Conference on E-Commerce (IEEE-CEC03), Newport Beach, CA., USA.

Witkam, J. (2003). Altreva Adaptive Modeler simulation software, http://www.altreva.com/technology.html


Full Text: PDF

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.