Abstract
How to predict stock price movements based on quantitative market data modeling is an attractive topic. In front of the market news and stock prices that are commonly believed as two important market data sources, how to extract and exploit the hidden information within the raw data and make both accurate and fast predictions simultaneously becomes a challenging problem. In this paper, we present the design and architecture of our trading signal mining platform that employs extreme learning machine (ELM) to make stock price prediction based on those two data sources concurrently. Comprehensive experimental comparisons between ELM and the state-of-the-art learning algorithms, including support vector machine (SVM) and back-propagation neural network (BP-NN), have been undertaken on the intra-day tick-by-tick data of the H-share market and contemporaneous news archives. The results have shown that (1) both RBF ELM and RBF SVM achieve higher prediction accuracy and faster prediction speed than BP-NN; (2) the RBF ELM achieves similar accuracy with the RBF SVM and (3) the RBF ELM has faster prediction speed than the RBF SVM. Simulations of a preliminary trading strategy with the signals are conducted. Results show that strategy with more accurate signals will make more profits with less risk.
Similar content being viewed by others
Notes
To inter-day value traders and news traders, they usually take the overnight news articles into consideration, as they analyze the mid- or long-term impacts of news, such as daily, weekly and even monthly. However, for high frequency trading, they usually make use of intra-day short-term signals. Since before the main trading hours, there is an auction session in H-share market, the impact of the news overnight is assumed to be reflected in the auction prices and absorbed before continuous session starts. Therefore, regarding to our platform’s prediction frequency, we only keep intra-day news. This approach also follows the method in many previous works in computer science, e.g., Schumaker et al. [31].
Software is downloaded on ictclas.org.
Levenberg–Marquardt algorithm has its implementation in MATLAB 7.14 toolbox.
Notation #(X) indicates the number of object X.
Online dynamic reconfiguration is not discussed in the paper, since all the four models are not online algorithms and training can be setup as an overnight job. We record the training time of each model and present them in Table 9. As we can see from the results, the training time of four models is much longer than validation and testing time, and the time of BP-NN is much longer than the time of the other three models.
References
Schumaker RP, Chen H (2010) A discrete stock price prediction engine based on financial news. Computer 43(1):51–56
Yeh C-Y, Huang C-W, Lee S-J (2011) A multiple-kernel support vector regression approach for stock market price forecasting. Expert Syst Appl 38:2177–2186
Huang G-B, Zhu Q-Y, Siew C-K (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501
Huang G-B, Siew C-K (2004) Extreme learning machine: RBF network case. In: Control, automation, robotics and vision conference, ICARCV’04, vol 2, pp 1029–1036
Wei X-K, Li Y-H, Feng Y (2006) Comparative study of extreme learning machine and support vector machine. In: Advances in neural networks, ISNN’06, vol 3971. Springer, Berlin, Heidelberg, pp 1089–1095
Huang G-B, Wang DH, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybernet 2(2):107–122
Li X, Wang C, Dong J, Wang F, Deng X, Shanfeng Z (2011) Improving stock market prediction by integrating both market news and stock prices. In: Hameurlain A, Liddle S, Schewe K-D, Zhou X (eds) Database and expert systems applications. Lecture notes in computer science, volume 6861. Springer, Berlin, pp 279–293
Seo Y-W, Giampapa J, Sycara K (2004) Financial news analysis for intelligent portfolio management. PhD thesis, Robotics Institute, Carnegie Mellon University
Yu L, Yue YW, Wang S, Lai KK (2010) Support vector machine based multiagent ensemble learning for credit risk evaluation. Expert Syst Appl 37(2):1351–1360
Schumaker RP, Chen H (2009) Textual analysis of stock market prediction using breaking financial news: The azfin text system. ACM Trans Inf Syst 27(2):12:1–12:19
Fu T-C, Chung F-L, Ng V, Luk R Pattern discovery from stock time series using self-organizing maps. In: Workshop notes of workshop on temporal data mining, KDD’01
Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43:59–69
Kohonen T, Somervuo P (1998) Self-organizing maps of symbol strings. Neurocomputing 21(1–3):19–30
Ultsch A (1999) Data mining and knowledge discovery with emergent self-organizing feature maps for multivariate time series. Kohonen Maps 46:33–46
Godbole N, Manjunath S, Steven S (2007) Large-scale sentiment analysis for news and blogs. ICWSM’07, Boulder, Colorado, USA
Kim S-M, Hovy E (2004) Determining the sentiment of opinions. In: Proceedings of the 20th international conference on computational linguistics, COLING’04, pp 1367–1373, Stroudsburg, PA, USA, 2004. Association for Computational Linguistics
Pang B, Lee L (2008) Opinion mining and sentiment analysis. Found Trends Inf Retr 2(1–2):1–135
Pang B, Lee L, Vaithyanathan S (2002) Thumbs up?: sentiment classification using machine learning techniques. In Proceedings of the conference on empirical methods in natural language processing, EMNLP’02, pp 79–86, Stroudsburg, PA, USA. Association for Computational Linguistics.
Van Gestel T, Suykens JAK, Baestaens D-E, Lambrechts A, Lanckriet G, Vandaele B, De Moor B, Vandewalle J (2001) Financial time series prediction using least squares support vector machines within the evidence framework. IEEE Trans Neural Netw 12(4):809–821
Tay FEH, Cao L (2001) Application of support vector machines in financial time series forecasting. Omega 29(4):309–317
Tay FEH, Cao L (2002) Modified support vector machines in financial time series forecasting. Neurocomputing 48(1):847–861
Cao L, Gu Q (2002) Dynamic support vector machines for non-stationary time series forecasting. Intell Data Anal 6(1):67–83
Kyoung-Jae K (2003) Financial time series forecasting using support vector machines. Neurocomputing 55(1–2):307–319
Cao L, Tay FEH (2001) Financial forecasting using support vector machines. Neural Comput Appl 10(2):184–192
Cao L, Tay FEH (2003) Support vector machine with adaptive parameters in financial time series forecasting. IEEE Trans Neural Netw 14(6):1506–1518
Huang W, Nakamori Y, Wang S-Y (2005) Forecasting stock market movement direction with support vector machine. Comput Oper Res 32(10):2513–2522
Sun Z-L, Choi T-M, Au K-F, Yu Y (2008) Sales forecasting using extreme learning machine with applications in fashion retailing. Decis Support Syst 46(1):411–419
Sun Y, Yuan Y, Wang G (2011) An os-elm based distributed ensemble classification framework in p2p networks. Neurocomputing 74(16):2438–2443
Handoko SD, Keong KC, Soon OY, Zhang GL, Brusic V (2006) Extreme learning machine for predicting hla-peptide binding. In: Advances in neural networks, ISNN’06, vol 3973. Springer, Berlin, Heidelberg, pp 716–721
Saraswathi S, Sundaram S, Sundararajan N, Zimmermann M, Nilsen-Hamilton M (2011) Icga-pso-elm approach for accurate multiclass cancer classification resulting in reduced gene sets in which genes encoding secreted proteins are highly represented. IEEE/ACM Trans Comput Biol Bioinf 8(2):452–463
Schumaker RP, Chen H (2009) A quantitative stock prediction system based on financial news. Inf Process Manag 45(5):571–583
Schumaker RP, Chen H (2006) Textual analysis of stock market prediction using financial news articles. In: Americas conference on information systems, AMCIS’06, vol 1, pp 1–20
Feldman R, Sanger J (2007) The text mining handbook. Cambridge University Press, Cambridge
Gidófalvi G (2001) Using news articles to predict stock price movements. PhD thesis, Department of Computer Science and Engineering, University of California
Cao L, Tay FEH (2004) Support vector machine with adaptive parameters in financial time series forecasting. IEEE Trans Neural Netw 14(6):1506–1518
Ritter JR (2003) Behavioral finance. Pac Basin Financ J 11(4):429–437
Acknowledgments
This work was partly supported by National Natural Science Foundation of China (Grant No. 61300137); the Guangdong Natural Science Foundation, China (Grant No. S2011040002222); the Fundamental Research Funds for the Central Universities, SCUT (Grant No. 2012ZM0077). This work was also supported by Shenzhen New Industry Development Fund under grant No. JCYJ20120617120716224.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, X., Xie, H., Wang, R. et al. Empirical analysis: stock market prediction via extreme learning machine. Neural Comput & Applic 27, 67–78 (2016). https://doi.org/10.1007/s00521-014-1550-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-014-1550-z