Risk avoiding strategy in multi-agent trading system

The authors of this paper present an approach to trading strategy design for a multi-agent system which supports investment decisions on the stock market. The individual components of the system, the functionalities, and the mechanism of assessing the individual agents are briefly described. The main component, the supervisor agent, uses as a strategy a consensus method to reduce the level of investment risk. This method allows the coordination of the work of agents, and on the basis of decisions provided by the agents, and presents trading advice to the investor. The strategy testing has been done on FOREX quotes, namely on the pair EUR/USD. The results of the research are described and the directions of the further development of the platform are provided in the conclusion.