Abstract
Stock trend prediction has been of great interest for both investment benefits and research purposes. Unlike image processing or natural language processing, where the amount of data could easily reach a million order of magnitude, the application of artificial intelligent models is however limited in the domain of stock prediction because of insufficient amount of stock price data. This article seeks to ameliorate the stock prediction task from a different angle and provides a novel method to enlarge the training data by firstly clustering different stocks according to their retracement probability density function, and then combine all the day-wise information of the same stock cluster as enlarged training data, which is then fed into a recurrent neural network to make stock trend prediction. Experimental results show that this data augmentation technique suits for deep learning methods and notably improves the stock trend prediction task.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akita, R., Yoshihara, A., Matsubara, T., Uehara, K.: Deep learning for stock prediction using numerical and textual information. In: Proceedings of the 15th IEEE/ACIS International Conference on Computer and Information Science, pp. 1–6 (2016)
Atsalakis, G.S., Protopapadakis, E.E., Valavanis, K.P.: Stock trend forecasting in turbulent market periods using neuro-fuzzy systems. Oper. Res. Int. J. 16(2), 245–269 (2016)
Barak, S., Dahooie, J.H., Tichỳ, T.: Wrapper ANFIS-ICA method to do stock market timing and feature selection on the basis of japanese candlestick. Expert Syst. Appl. 42(23), 9221–9235 (2015)
Chandar, S.K., Sumathi, M., Sivanandam, S.: Prediction of stock market price using hybrid of wavelet transform and artificial neural network. Indian J. Sci. Technol. 9(8) (2016)
Cho, K., van Merrienboer, B., Gülçehre, Ç., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of 2014 Conference on Empirical Methods in Natural Language Processing, pp. 1724–1734 (2014)
Dolson, M.: Discriminative nonlinear dimensionality reduction for improved classification. Int. J. Neural Syst. 5(04), 313–333 (1994)
Engle, R.F.: The econometrics of ultra-high-frequency data. Econometrica 68(1), 1–22 (2000)
Fu, T.c., Chung, F.l., Ng, V., Luk, R.: Pattern discovery from stock time series using self-organizing maps. In: Proceedings of Workshop Notes of KDD 2001 Workshop on Temporal Data Mining, pp. 26–29 (2001)
Gálvez, R.H., Gravano, A.: Assessing the usefulness of online message board mining in automatic stock prediction systems. J. Comput. Sci. 19, 43–56 (2017)
Hadavandi, E., Shavandi, H., Ghanbari, A.: Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting. Knowl.-Based Syst. 23(8), 800–808 (2010)
Hartman, E.J., Keeler, J.D., Kowalski, J.M.: Layered neural networks with gaussian hidden units as universal approximations. Neural Comput. 2(2), 210–215 (1990)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Hsu, C.M.: A hybrid procedure for stock price prediction by integrating self-organizing map and genetic programming. Expert Syst. Appl. 38(11), 14026–14036 (2011)
Jiang, Z., Chen, P., Pan, X.: Announcement based stock prediction. In: Proceedings of 2016 International Symposium on Computer, Consumer and Control, pp. 428–431 (2016)
Kohonen, T.: The self-organizing map. Neurocomputing 21(1), 1–6 (1998)
Liu, Y., Qin, Z., Li, P., Wan, T.: Stock volatility prediction using recurrent neural networks with sentiment analysis. In: Proceedings of 30th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, pp. 192–201 (2017)
Mangiameli, P., Chen, S.K., West, D.: A comparison of som neural network and hierarchical clustering methods. Eur. J. Oper. Res. 93(2), 402–417 (1996)
Nader, E., Badr, A., Fatah, A.: An intelligent framework using hybrid social media and market data, for stock prediction analysis. Int. J. Comput. Inf. Technol. 5(3) (2016)
Patel, H., Parikh, S.: Comparative analysis of different statistical and neural network based forecasting tools for prediction of stock data. In: Proceedings of 2nd International Conference on Information and Communication Technology for Competitive Strategies, p. 126 (2016)
Rosenblatt, M., et al.: Remarks on some nonparametric estimates of a density function. Ann. Math. Stat. 27(3), 832–837 (1956)
Tang, Y., Wu, Z., Meng, H.M., Xu, M., Cai, L.: Analysis on gated recurrent unit based question detection approach. In: Proceedings of 17th Annual Conference of the International Speech Communication Association, pp. 735–739 (2016)
Tsai, C.F., Hsiao, Y.C.: Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches. Decis. Support Syst. 50(1), 258–269 (2010)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (2013)
Wei, J., Huang, J.: An exotic long-term pattern in stock price dynamics. PLoS ONE 7(12), e51666 (2012)
Wei, L., Chen, T., Ho, T.: A hybrid model based on adaptive-network-based fuzzy inference system to forecast taiwan stock market. Expert Syst. Appl. 38(11), 13625–13631 (2011)
Yang, J., Rao, R., Hong, P., Ding, P.: Ensemble model for stock price movement trend prediction on different investing periods. In: Proceedings of 12th International Conference on Computational Intelligence and Security, pp. 358–361 (2016)
Acknowledgments
This work was partially supported by the National Natural Science Foundation of China (No. 61332018).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Zhang, J., Rong, W., Liang, Q., Sun, H., Xiong, Z. (2017). Data Augmentation Based Stock Trend Prediction Using Self-organising Map. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10635. Springer, Cham. https://doi.org/10.1007/978-3-319-70096-0_92
Download citation
DOI: https://doi.org/10.1007/978-3-319-70096-0_92
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70095-3
Online ISBN: 978-3-319-70096-0
eBook Packages: Computer ScienceComputer Science (R0)