Computer Engineering and Applications ›› 2024, Vol. 60 ›› Issue (11): 346-355.DOI: 10.3778/j.issn.1002-8331.2303-0032

• Engineering and Applications • Previous Articles     Next Articles

Structured Maximum Margin Twin Support Vector Machine and Its Application in Stock Trend Prediction

LIN Mingsong, YANG Xiaomei, YANG Zhixia   

  1. College of Mathematics and Systems Science, Xinjiang University, Urumuqi 830046, China
  • Online:2024-06-01 Published:2024-05-31

结构化最大间隔双支持向量机在股票预测中的应用

林明松,杨晓梅,杨志霞   

  1. 新疆大学 数学与系统科学学院,乌鲁木齐 830046

Abstract: The stock price is affected by many factors, such as policy, macro-economy and the company’s operating conditions, among which there is a certain degree of correlation. So the stock data of high noise and non-stationary feature makes stock prediction difficult. Based on the separability between classes of Mahalanobis distance, this paper proposes structured maximum margin twin suport vector machine (SMM-TWSVM). The method finds two nonparallel hyperplane for positive class samples and negative class samples respectively, so that the Euclidean distance of each class of samples from their own hyperplane is as small as possible, and the Mahalanobis distance of divorced class hyperplane is as large as possible. The experimental results of 8 benchmark datasets show that this method has a stable accuracy in the classification of noisy data, thus improving the prediction performance and anti-noise ability of the model. Meanwhile, it is applied to the prediction of the fluctuation tend of stock price, through the empirical analysis of 14 stocks such as Ping An of China and Shanghai Composite Index, Shanghai A Index, Shanghai 380 Index, the results show that compared with other comparison models, SMM-TWSVM shows better prediction results and has certain practical value.

Key words: classification, twin support vector machine, data structure, Mahalanobis distance, stock prediction

摘要: 股票价格受政策、宏观经济以及公司经营状况等多方因素的影响,且各因素之间存在较高的相关性,因此股票数据存在的高噪声、非平稳等特性使得股票预测充满困难。为了减少数据中存在的噪声对股价预测准确性的影响,基于马氏距离的类间隔可分性,提出了结构化最大间隔双支持向量机,其分别针对正类样本和负类样本,寻找两个非平行的超平面,使每一类样本离本类样本的欧式距离尽可能小,同时离异类超平面的马氏距离尽可能大。8组基准数据集的实验结果表明,该方法在含噪声数据的分类问题上具有稳定的准确率,从而提升了模型的预测性能和抗噪能力。同时将其应用到股票涨跌趋势预测中,通过对上证综指、上证A指、上证380指数以及中国平安等14只股票实证分析的结果表明,相较于其他对比模型,结构化最大间隔双支持向量机表现出了较好的预测结果,具有一定的实用价值。

关键词: 分类问题, 双支持向量机, 数据结构, 马氏距离, 股票预测