基于虚拟股市的演化复杂性度量与分析

建立了基于遗传元胞自动机的虚拟股市模型,股市中的股民用元胞代表,股民具备自主学习的能力,同时亦受邻近股民投资历史的影响,股民间的相互影响通过选择算子与交叉算子实现,外界环境通过改变变异概率影响股市系统的演化行为.提取了度量系统演化复杂性的特征量,并在此基础上,研究了它与个体数量及耦合强度之间的关系.大量实验表明：足量的个体与适度的耦合强度有利于维持系统的长期演化.

Measurement and analysis of evolvement complexity based on artificial stock market

A mathematical model of an artificial market was established with the modeling method and ideas of cellular automata, in which, cells are used to represent stockholders who are capable of learning by themselves and are affected by the investing history of those in their neighborhood. The interaction among them was realized through the selection operator and crossover operator. The surroundings affect the behavior of the stock system by changing the mutation possibility. The feature measuring the complexity of system evolvement was obtained, on the basis of which the relationship between the feature and the number of individuals as well as the coupling strength was studied. Experiments indicate that plenty of individuals and proper coupling strength are propitious to maintaining the long-term evolvement of the system.