Introducing ATOM

In recent years, Artificial Intelligence systems have received an increasing amount of academic interest in Economics and Finance. Among these works, Artificial Stock Markets (ASM) have particularly benefited from the agent based approach and from the Multi-Agent philosophy. The application fields for Agents-based modelling and simulations in Finance appears extremely promising. For example, one can study the impact of a Tobins tax on the financial system, or one can develop new stress tests for assessing financial resilience to economic shocks or to develop new automatic trading techniques. Implementing realistic simulations of complex financial dynamics using both artificial intelligence, distributed agents and realistic market algorithms gives the researcher a powerful tool for understanding stylized facts and for experimenting various regulations in a controlled, riskless experimental environment. MAS offer a new framework for investigating questions that have been tackled for years with tools grounded on non realistic assumptions. On the contrary, ASM are grounded on an individual-based approach with local interactions, distributed knowledge and resources, heterogeneous environments, agent autonomy, artificial intelligence, speech acts, discrete scheduling and simulation, all things that cannot be used or done in traditional, aggregate models.