【摘要】 贝叶斯网络说明变量集合的联合条件概率分布为自然地表示因果信息提供了一种方法 .用贝叶斯网络进行预测的核心问题是选择最符合样本数据的网络结构 ,即根据数据样本 D和先验知识ζ找出后验概率 p(Sh|D,ζ)最大的贝叶斯网络 S.提出了一种基于贝叶斯网络的实时行情预测算法 ,并对其数据结构与实现方法进行了阐述 .更多还原

【Abstract】 Bayesian network explains the probabilistic relationships among variables. It is a natural way to express the causal information. The core question in realizing the Bayesian network is to choose the network model that best represents the dependent relationships of the variables samples,that is ,given sample D and prior knowledge ζ to find a Bayesian network S that fits the maximum posterior probability p(Sh|D,ζ) .The algorithms and data structures of a dynamic market forecast engine that base on Bayesian network is expatiated.更多还原