Transformations  in
Business & Economics

NOVEL AUTOMATED MULTI-AGENT INVESTMENT SYSTEM BASED ON SIMULATION OF SELF-EXCITATORY OSCILLATIONS
A. Raudys, D. Plikynas, S. Masteika

ABSTRACT. Modern financial markets are dominated by the algorithmic trading tools, which essentially changed previously observed regularities in the investment data sets. In order to develop robust and reliable trading algorithms new approaches have to be employed. In this paper we investigate how to (i) model spread of self-excited oscillations in social mediums and (ii) simulate data series of rare events' (e.g. crises). We proposed a novel multi-agent investment simulation system, composed from a multitude of artificial investing agents. Consequently, we developed a simulation tool, which can deal with self-excited oscillations and high dimensionality small sample size problems arising in the modern financial markets. The novel multi-agent system was tested with real market ant synthetic data for the period between 2007 and 2013. In an out-of-sample regime, the novel approach outperformed benchmark trading strategies.

KEYWORDS: automated trading systems, agents-based modelling, social mediums, self-excited oscillations.

JEL classification: C63, C67, G02, G17.