基于支持向量机的股价预测研究

Stock Price Forecasting Based on Support Vector Machine

支持向量机(SVM)方法作为数据挖掘中的一种人工智能方法,能够解决数据维数过大、非线性、小样本等问题,在股价预测方面比其他方法具有更大的优势.本文利用支持向量机的分类原理,用上证180股价指数中的90个成分股作为训练样本对支持向量机模型进行训练,选取上市公司基本面中的行业特征和公司相关财务指标以及股票市场中的技术指标,然后用训练好的模型对剩余的90个成分股样本的股票价格的涨跌进行分类预测,结果显示支持向量机方法对股价涨跌的预测具有较高的准确性.

As an artificial intelligence method in data mining,support vector machine(SVM)can solve the problems of large data dimension,non-linear,small sample and so on,therefore,it is more advantageous than other methods in stock price forecasting.Based on the classification principle of support vector machine,this paper selects the industry characteristics in the fundamentals of listed companies,relevant financial indicators of the company and technical indicators in the stock market,the support vector machine model is trained with 90 component stocks in Shanghai 180 stock index as training samples,and then the trained model is used to classify and predict the rise and fall of stock prices of the remaining 90 component stocks.The results show that the support vector machine method has higher accuracy in predicting the rise and fall of stock prices.