应用财经新闻挖掘的金融品种价格走势预测  

Financial price trend forecast using financial news mining

作　　者：陈海文[1] 蔡志平[1] 方峰[1] 

机构地区：[1]国防科学技术大学计算机学院,湖南长沙410073

出　　处：《计算机工程与科学》2016年第9期1909-1916,共8页Computer Engineering & Science

基　　金：国家自然科学基金(61379145;61170288;61272510)

摘　　要：随着经济的不断发展,金融活动中的不确定性日益增加,金融预测受到学术界及金融界的高度重视。人们希望通过获得预测性的判断和推测,掌握金融产品未来的发展趋势和规律。而近期随着互联网发展,出现海量财经信息,仅仅依靠历史价格的数据挖掘技术,不能很好地反映金融市场多元因素的影响。因此,通过挖掘财经新闻信息中的情感倾向信息,结合金融历史价格数据,组合多元线性回归和差分自回归滑动平均模型,提出了一种基于财经新闻信息挖掘的金融价格走势预测方法,通过实际数据验证,表明该方法可以获得较为准确的预测结果。With the rapid development of the economy, uncertainty of financial activities has been in- creasing, so financial price prediction attracts great attentions from the academia and the financial indus- try. How to obtain predictive judgment and speculation and how to grasp the prospective development tendency and regularity of the financial world becomes urgent. Recently, with the help of rapid internet development, solely relying on the data mining technology to obtain massive financial information on the price history cannot reflect the impact of multiple factors in the financial market. We therefore propose a financial price trend prediction method based on financial news mining, which can digthe emotional tend- ency messages from the financial news information. Combined with the financial historical price data, we use a combination model of multiple linear regression and differential self-regression to predict future fi- nancial price trend. Real data show that the proposal can obtain more accurate prediction results.

关 键 词：财经新闻 金融市场预测 多元线性回归 ARIMA 情感信息 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]