Abstract: Due to the stock price fluctuations have stronger mutation and easily influenced by outside factors, cause it’s difficult to predict stock price movements. A stock market volatility forecasting model based on characteristics of outliers pattern（SFSVM） is presented. Firstly, SFSVM algorithm utilizes Markov Blanket algorithm obtaining local network to shield the effects of other node to the target node; Secondly, analyzing the index of the target node to extract characteristic of outliers pattern from the general behavior；then SFSVM algorithm capture outlier features using sliding window, put characteristic of outliers pattern into original SVM model as a prior knowledge, this method can predict peak point and smooth effect of peak point on the predicted results, it also can improve forecasting model robustness. Experimental results, obtained by running on datasets taken from stock plate index, show that this method performs better than neural network algorithm and the standard SVM algorithm on stock trend projections.

Key words: characteristics of outliers model, Support Vector Machines（SVM）, Markov Blanket, prior knowledge

摘要： 由于股票价格波动具有较强的突变性且易受外界因素影响，导致股票价格走势难以预测。提出基于离群特征模式的股市波动预测模型（SFSVM）。该算法首先利用马尔可夫毯选取目标结点的局部网络结构，以屏蔽其他结点对目标结点的影响；对目标结点的指标进行分析，提取异于一般行为的离群特征模式；利用滑动窗口捕捉离群特征，将离群特征模式作为先验知识加入原SVM模型，预测尖峰点并平滑尖峰点对于预测结果的影响，提高预测模型的稳健性。在股票板块数据上进行实验结果证明，SFSVM算法相对于神经网络和标准的SVM算法，在股票的走势预测方面有更好的预测效果。

关键词: 离群特征模式, 支持向量机, 马尔可夫毯, 先验知识