基于网络舆情支持向量机的股票价格预测研究

Stock Price Prediction Base on Network Public Opinion and Support Vector Machine

提出一种基于网络舆情和股票技术指标数据的支持向量机回归模型(NPOSVM),提高了股票价格的预测精度.模型首先将抓取的微博、股吧等股评观点分为正面和负面两类,计算正面观点所占的比例作为网络舆情,然后对网络舆情和股票技术指标数据作主成分分析,最后对保留的主成分运用支持向量机回归建模预测.实证分析国药股份(SH600511),仿真结果表明网络舆情与股票价格之间的相关系数为0.76;基于股票技术指标数据的支持向量机回归模型(TI-SVM)预测平均相对误差为1.29%、趋势准确率为57.14%,而NPO-SVM预测平均相对误差为0.66%、趋势准确率为71.43%.于是证明,NPO-SVM模型显著地提高了预测精度,是一种有效的预测股票价格的模型.

In order to improve the prediction accuracy of the stock price, based on network public opinion and technical indicators, a stock prediction model （NPO-SVM） is put forward by support vector machine regression. Firstly, stock comments such as micro-blog and stock forum are divided into both positive and negative categories, and stock network public opinion is defined by the ratio of positive comments. Then, the input data of stock network public opinion and technical indicators are reduced to several factors by the principal component analysis. Finally, the model is built with the reserved factors by support vector machine regression. The NPO-SVM is tested with China National Medicines Corporation （SH600511）, and the simulation results show that, the correlation coefficient between stock network public opinion and stock price is 0.76, the average relative error of stock prediction model （TI-SVM） based on technical indicators is 1.29% and the trend accuracy rate is 57.14%, while the average relative error of NPO-SVM is 0.66% and the trend accuracy rate is 71.43%. Therefore the NPO-SVM can improve the accuracy of the prediction and is a higher efficient stock prediction model.