基于粗糙集理论的支撑向量机预测方法研究

Study of Forecasting Algorithm for Support Vector Machines Based on Rough Sets

分析了粗糙集理论方法与支撑向量机方法两者各自的优势和互补性 ,探讨了粗糙集与支撑向量机的结合方法 ,然后提出了一种基于粗糙集数据预处理的支撑向量机预测系统。该系统利用粗糙集理论在处理大数据量、消除冗余信息等方面的优势 ,减少支撑向量机的训练数据 ,克服支撑向量机方法因为数据量太大 ,处理速度慢等缺点。将该系统应用于股票价格预测中 ,与 BP神经网络法和标准的支撑向量机方法相比 ,得到了较高的预测精度 ,从而说明了基于粗糙集理论的方法作为信息预处理的支撑向量机学习系统的优越性。

By analyzing the generalities and specialities of rough sets (RS) and support vector machines (SVM) in knowledge representation and process of classification, a minimum decision network combining RS with SVM in intelligence processing is investigated, and a kind of SVM system on RS is proposed for forceasting. Using RS theory on the advantage of dealing with great data and eliminating redundant information, the system reduces the training data of SVM, and overcomes the disadvantage of great data and slow speed. Finally, the system is used to forecast Shanghai Stock Exchange Index, and experimental results prove that the approach can achieve greater forecasting accuracy and generalization ability than the BP neural network and standard SVM.