基于Agent的股票价格行为仿真  

Simulation of Stock Prices Behavior Based on Agent

作　　者：刘大海[1] 王治宝[1] 孙洪军[1] 张瀚[1] 

机构地区：[1]南开大学信息技术科学学院,天津300071

出　　处：《计算机工程》2004年第19期168-170,共3页Computer Engineering

基　　金：天津市自然科学基金资助项目(23601411)

摘　　要：对于股票市场价格行为的解释一直是现代金融理论的核心问题之一。上世纪80年代以来,基于Agent的计算金融学提出:社会经济系统的各种复杂性来源于经济系统中个体(Agent)的适应性行为。该文的基本思路即是借助行为金融学和人工智能研究的成果,采用Agent系统理论和计算机仿真相结合,构建符合现实的仿真股市,并通过适应性个体之间的行为和个体与外界经济环境的交互,对股票市场的价格行为提供一种新颖的理解思路。The explanation of the behavior of stock market prices has been one of key questions of the modern financial theory all the time. Since the eighties, the agent-based finance points out that various kinds of complexity of the social economic system stem from the individual's adaptability exchange behavior. First the authors predigest actual stock market reasonable, then construct adaptive agents base on the modeling technology of multi-agent. Thus, model of stock market is constructed based on simple mutual behavior of adaptive agents successfully. The authors attempt to offer a kind of novel thought to the behavior of stock market prices.

关 键 词：计算金融学 MULTI-AGENT 价格行为 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]