摘要
针对传统股市研究方法存在的不足,提出用人工神经网络的学习能力模拟Agent的适应性。借鉴Holland的模拟股市建模思想,引入ERA方案建立股市模型。运用Agent行为一致性神经网络方法并结合CT方法对股市进行仿真,模拟不确定环境下股市的动态演化过程。该模型可更好地理解股市的动力学特性。
In accordance with the limitation of traditional research on the stock market, a method of simulating the adaptability of Agent by neural network is proposed, and refer to the modeling scheme of Holland's stock market model, an applied model of stock market using ERA scheme is built. The dynamic evolvement of the stock market under uncertain environment is simulated through the neural network approach to the self-development of consistency in Agent behavior with CT method. This scheme can aim to understand the dynamic specialty of stock market deeply.
出处
《计算机工程》
CAS
CSCD
北大核心
2009年第5期177-179,共3页
Computer Engineering
基金
贵州省科技基金资助项目(20072205)
贵州大学研究生创新基金校级资助项目(2007037)
关键词
人工神经网络
复杂适应系统
SWARM仿真平台
ERA方案
CT方法
artificial neural network
Complex Adaptive System(CAS)
Swarm simulation toolkit
Environment-Rules-Agents(ERA) scheme
Cross Target(CT) method