Interacting neural networks: an artificial life approach for stock markets
暂无分享,去创建一个
In this paper we present a behavioural approach to the study of financial markets based on co-evolving adaptive agents rather than on crude price forecasting, or generally speaking, statistical methods. The main aspects we stress in this work are the generality of the neural network approach for the modeling of artificial adaptive agents [1] and the application of Artificial Life paradigms to neural networks learning techniques. In this framework we study the behaviour emerging from the interaction of the agents especially with respect to the evolution of stock price and expectations of the agents.
[1] Long-Ji Lin,et al. Self-improving reactive agents: case studies of reinforcement learning frameworks , 1991 .
[2] J. Holland,et al. Artificial Adaptive Agents in Economic Theory , 1991 .