A Platform for Stock Market Simulation with Distributed Agent-Based Modeling

摘要

Agent-based modeling (ABM) has been widely used in stock market simulation. However, traditional simulations of stock markets with ABM on single computers are limited by the computing capability as breakthroughs in financial research need much larger amount of agents. This paper introduces a platform for stock market simulation with ABM focusing on large scale parallel agents in a distributed computing environment such as Cluster and MPP. With the customized trade strategies inside the agents, the runtime system of the platform can distribute the massive amount of agents to multiple computing nodes automatically during the execution of the simulation. And agents exchange information with each other and the market through a uniform communication system. With this platform financial researchers can design their own financial model without caring about the complexity of paral-lelization and related problems. The sample simulation on the platform is verified to be compatible with the data from Euronext-NYSE and the platform shows fair scalability and performance under different parallelism configurations.