应用财经新闻挖掘的金融品种价格走势预测

计算机工程与科学

应用财经新闻挖掘的金融品种价格走势预测

陈海文，蔡志平，方峰

（国防科学技术大学计算机学院,湖南长沙 410073）

收稿日期:2015-12-11 修回日期:2016-03-04 出版日期:2016-09-25 发布日期:2016-09-25
基金资助:
国家自然科学基金（61379145，61170288，61272510）

Financial price trend forecast using financial news mining

CHEN Hai-wen，CAI Zhi-ping，FANG Feng

（College of Computer,National University of Defense Technology,Changsha 410073,China）

Received:2015-12-11 Revised:2016-03-04 Online:2016-09-25 Published:2016-09-25

摘要/Abstract

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。

关键词: 财经新闻, 金融市场预测, 多元线性回归, ARIMA, 情感信息

Abstract:

With the rapid development of the economy, uncertainty of financial activities has been increasing, so financial price prediction attracts great attentions from the academia and the financial industry. 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 tendency 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 financial price trend. Real data show that the proposal can obtain more accurate prediction results.

Key words: financial news, financial market predicting, multiple linear regression, ARIMA, sentimental information

陈海文，蔡志平，方峰. 应用财经新闻挖掘的金融品种价格走势预测[J]. 计算机工程与科学.

CHEN Hai-wen，CAI Zhi-ping，FANG Feng. Financial price trend forecast using financial news mining [J]. Computer Engineering & Science.

参考文献

［1］Abu-Mostafa Y,Atiya A.Introduction to financial fore-casting［J］.Applied Intelligence,1996,6(3):205-213.
［2］Chen Jing, He Guo-zhu, Yu Ping. Prediction of retail price index of Sichuan province based on ARIMA model［C］∥Proc of 2014 International Conference on Management and Engineering,2014:1.
［3］Zhang D,Zhou L.Discovering golden nuggets: Data mining in financial application［J］.IEEE Transactions on Systems,Man,and Cybernetics,Part C: Applications and Reviews,2004,34(4):513-522.
［4］Ruiz E J,Hristidis V,Castillo C,et al.Correlating financial time series with micro-blogging activity［C］∥Proc of the 5th ACM International Conference on Web Search and Data Mining,2012:513-522.
［5］Ramos S B,Veiga H,Latoeiro P.Predictability of stock market activity using Google search queries［M］∥Statistics & Econometric Working Papers,2013:1.
［6］Schumaker R P,Chen H.A quantitative stock prediction system based on financial news［J］.Information Processing & Management,2009,45(5): 571-583.
［7］Granger C,Joyeux R.An introduction to long-memory time series models and fractional differencing［J］.Journal of Time Series Analysis,1980,1(1):15-29.
［8］Contreras J,Espinola R,Nogales F J,et al. ARIMA models to predict next-day electricity prices［J］. IEEE Power Engineering Review,2003, 18(3):1014-1020.
［9］Box G,Jenkins G.Time series analysis: Forecasting and control［M］.New Jersey: Prentice Hall,1994.
［10］Makridakis S,Andersen A,Carbone R,et al.The accuracy of extrapolation (time series) methods: Results of a forecasting competition ［J］.Journal of Forecasting,1982,1(2):111-153.
［11］Zhang G.Time series forecasting using a hybrid ARIMA and neural network model［J］.Neurocomputing,2003,50(1):159-175.
［12］Xu Xing-fa. Financial forecasting［M］. Beijing: University of Modern Administration,1985:1-10.(in Chinese)
［13］Ruiz E J,Hristidis V,Castillo C.Cor-relating financial time series with micro-Blogging activity［C］∥Proc of ACM International Conference on Web Search & Data Mining, 2012:513-522.
［14］Li Bin. Forecasting financial time series using linear predictive filters［J］. Imperial College London, 2013, 8(8):1-4.
［15］Soule G. Study of effectiveness of time series modeling (arima) in forecasting stock prices［J］. International Journal of Computer Science Engineering & Applica, 2014 （4）:349-352.
［16］Leng Jin-song. Modelling and analysis on noisy financial time series ［J］.Journal of Computer and Communications,2014(2):64-69.
［17］Wang Cheng-guo, Deng Zhong-yuan, Chen Hai-wen, et al. Financial variety trend prediction technology based on ARIMA model［J］. Computer Technology and Development,2015,7(7):11-14.(in Chinese)
［18］Wang Rui. Comparison of different methods of variable selection in the determination of ARMA order［D］.Jinan:Shandong University,2013.(in Chinese)
［19］Wang Chun. The effect of investor setiment on return and volatility of stock market-based on empirical study of net flow of open-end equity founds［J］. Chinese Journal of Management Science,2014, 22(9):49-56.(in Chinese)
［20］Zhou Sheng-chen,Shi Xun-zhi,Qu Wen-ting. Stock market time series prediction based on Weibo search and SVM［J］. Computer and Modernization, 2013, 1(4):22-26.(in Chinese)
［21］Li Yu-mei. Stock market trend forecast based on internet reviews［D］. Harbin:Harbin Institute of Technology,2012.(in Chinese)
［22］Wang Bao-hua. Financial forecasting method based on text mining technologies［D］. Harbin:Harbin Institute of Technology,2012.(in Chinese)
［23］Yu Pei-kun, Zhong Rui-jun. Individual investor sentiment can predict the market rate of return［J］. Nankai Business Review, 2009, 12(1):96-101.(in Chinese)
［24］Liu Fang, Dai Kui, Wang Zhi-ying, et al. Research on the technology of quantitative security evaluation based on fuzzy number arithmetic operation［J］. Fuzzy Systems and Mathematics,2004,18(4):51-54.
［25］Preis T, Stanley H E. Trend switching processes in finan-
cial markets［M］∥ Econophysics Approaches to Large-Scale Business Data and Financial Crisis. Tokyo:Springer Japan, 2010:7674-7678.
［26］Bollen J, Mao H, Zeng X J. Twitter mood predicts the stock market［J］.Computer Science, 2010,2(1):1-8.
附中文参考文献：
［12］徐星发.金融预测学［M］.北京: 北京现代管理大学,1985: 1-10.
［17］王成国,邓仲元,陈海文,等.基于ARIMA模型的金融品种走势预测技术［J］.计算机技术与发展,2015,7(7):11-14.
［18］王锐.多种变量选择方法ARMA阶数中的比较［D］.济南:山东大学,2013.
［19］王春.投资者情绪对股票市场收益和波动的影响—基于开放式股票型基金资金净流入的实证研究［J］.中国管理科学,2014,22(9):49-56.
［20］周胜臣,施询之,瞿文婷,等.基于微博搜索和SVM的股市时间序列预测研究［J］.计算机与现代化,2013(4): 22-26.
［21］李玉梅.基于互联网评论的股票市场趋势预测［D］.哈尔滨：哈尔滨工业大学,2012.
［22］王保华.基于文本挖掘技术的金融预测方法研究［D］.哈尔滨：哈尔滨工业大学,2012.
［23］余佩琨,钟瑞军.个人投资者情绪能预测市场收益率吗［J］．南开管理评论，2009,12(1):96-101.

[1]	肖妮妮, 金畅, 段湘煜. 基于提高伪平行句对质量的无监督领域适应机器翻译[J]. 计算机工程与科学, 2022, 44(12): 2230-2237.
[2]	林涛, 冯竞凯, 郝章肖, 黄少群. 基于组合预测模型的云计算资源负载预测研究[J]. 计算机工程与科学, 2020, 42(07): 1168-1173.
[3]	郭利进1，何西硕1,2,3，徐新喜2，石梅生2，王济虎2. 基于灰色多元线性回归融合模型的故障率预测[J]. 计算机工程与科学, 2018, 40(11): 2047-2053.
[4]	刘锦萍，郁金祥. 基于改进的粒子群算法的多元线性回归模型参数估计[J]. J4, 2010, 32(4): 101-105.