[Objective] This paper tries to predict stock trends with the help of deep learning models, financial data and related news events. [Methods] First, we built a classification model for news events. Then, we used the recurrent neural networks to construct a forecasting model for stock trends based on news, capital flows and corporate financial reports. [Results] The prediction accuracy was improved by the proposed model (76.22% and 77.36% for the mining and pharmaceutical manufacturing industries). [Limitations] We did not examine the different impacts of news headlines and full-texts on stock market. We only chose news events from the past one year, which needs to be expanded. [Conclusions] News events could improve the accuracy of predicting stock trends.
Birz G. Stale Economic News, Media and the Stock Market[J]. Journal of Economic Psychology, 2017, 61(3): 384-412. .
[2]
Nassirtoussi A K, Aghabozorgi S, Wah T Y, et al.Text Mining of News-headlines for FOREX Market Prediction: A Multi-layer Dimension Reduction Algorithm with Semantics and Sentiment[J]. Expert Systems with Applications, 2015, 42(1): 306-324.
[3]
Li X, Wang C, Dong J, et al.Improving Stock Market Prediction by Integrating both Market News and Stock Prices[C]// Proceedings of International Conference on Database and Expert Systems Applications. Springer Berlin Heidelberg, 2011: 279-293.
[4]
Schumaker R P, Chen H. Textual Analysis of Stock Market Prediction Using Breaking Financial News: The AZFinText System[J]. ACM Transactions on Information Systems, 2009, 27(2): Article No. 12.
[5]
Tetlock P C, Macskassy S.More than Words: Quantifying Language to Measure Firms’ Fundamentals[J]. The Journal of Finance, 2008, 63(3): 1437-1467.
(Kong Xiangyu, Bi Xiuchun, Zhang Shuguang.Financial News and Stock Market Forecast——An Empirical Analysis Based on Data Mining Technology[J]. Mathematical Statistics and Management, 2016, 35(2): 215-224.)
[7]
Basu S.Investment Performance of Common Stocks in Relation to Their Price-Earnings Ratios: A Test of the Efficient Market Hypothesis[J]. Journal of Finance, 1977, 32(3): 663-682.
[8]
Fama E F, French K R.Size and Book-to-Market Factors in Earnings and Returns[J]. Journal of Finance, 2012, 50(1): 131-155.
[9]
Kim Y. Convolutional Neural Networks for Sentence Classification[OL]. arXiv Preprint, arXiv: 1408.5882, 2014.
Gers F A, Schmidhuber J, Cummins F.Learning to Forget: Continual Prediction with LSTM[J]. Neural Computation, 2000, 12(10): 2451-2471.
[12]
Sundermeyer M, Ney H, Schlüter R.LSTM Neural Networks for Language Modeling[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015, 23(3): 517-529.
[13]
Leven S.The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting[J]. Neural Networks, 1996, 9(3): 543-544.
(Zhang Jianbo, Li Zhen.The Study of the Industry Factors on the Volatility of China’s Stock Price[J]. Journal of Shandong University: Philosophy and Social Sciences, 2014(1): 88-93.)
[15]
Yu H, Chen R, Zhang G.A SVM Stock Selection Model within PCA[J]. Procedia Computer Science, 2014, 31: 406-412.
[16]
Shynkevich Y, McGinnity T M, Coleman S A, et al. Forecasting Movements of Health-Care Stock Prices Based on Different Categories of News Articles Using Multiple Kernel Learning[J]. Decision Support Systems, 2016, 85(C): 74-83.
