Design and implementation of a multiagent stock trading system

摘要

Stock trading is one of the key items in an economy and estimating its behavior and taking the best decision in it are among the most challenging issues. Solutions based on intelligent agent systems are proposed to cope with those challenges. Agents in a multiagent system (MAS) can share a common goal or they can pursue their own interests. That nature of MASs exactly fits the requirements of a free market economy. Although existing studies include noteworthy proposals on agent-based market simulation and researchers discuss theoretical design issues of agent-based stock exchange systems, unfortunately only a very few of the studies consider exact development and implementation of multiagent stock trading systems within the software engineering perspective and guides to the software engineers for constructing such software systems starting from scratch. To fill this gap, in this paper, we discuss the development of a multiagent-based stock trading system by taking into consideration software design according to a well-defined agent oriented software engineering methodology and implementation with a widely-used MAS software development framework. Each participant in the system is first designed as belief-desire-intention agents with their facts, goals, and plans, and then belief-desire-intention reasoning and behavioral structure of the designed agents are implemented. Lessons learned during design and development within the software engineering perspective and evaluation of the implemented multiagent stock exchange system are also reported.