ABSTRACT
A growing number of financial market participants use the deep learning models to predict the future market movement via exploiting the news and social media messages. Memory cells like long short-term memory (LSTM) and gated recurrent unit (GRU), though play indispensable roles in sequence prediction, are criticized for lacking the interaction between inputs and previous context. The Mogrifier LSTM cell is designed to enhance such relationship. We employ this novel cell in our hybrid attention prediction network. The new structure enriches the communication between the previous message embedding and the current signal, hence a better learning process representation compared with the neural network without such mechanism. Experiment on real-world stock market data shows the Mogrifier based cell can outperform the venerable ones across different market sectors while still achieves lower prediction volatility.
- Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The journal of Finance, 25(2), 383--417.Google ScholarCross Ref
- Jung, J., & Shiller, R. J. (2005). Samuelson's dictum and the stock market. Economic Inquiry, 43(2), 221--228.Google ScholarCross Ref
- A Robust Predictive Model for Stock Price Prediction Using Deep Learning and Natural Language ProcessingGoogle Scholar
- Wu, Y., Zhang, S., Zhang, Y., Bengio, Y., & Salakhutdinov, R. R. (2016). On multiplicative integration with recurrent neural networks. In Advances in neural information processing systems (pp. 2856--2864).Google Scholar
- Jia, R., & Liang, P. (2017). Adversarial examples for evaluating reading comprehension systems. arXiv preprint arXiv:1707.07328.Google Scholar
- Box, G. E., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: forecasting and control. John Wiley & Sons.Google Scholar
- Kihoro, J., Otieno, R. O., & Wafula, C. (2004). Seasonal time series forecasting: A comparative study of ARIMA and ANN models.Google Scholar
- Baillie, R. T. (1980). Predictions from ARMAX models. Journal of Econometrics, 12(3), 365--374.Google ScholarCross Ref
- Golmohammadi, K., Zaiane, O. R., & Díaz, D. (2014, November). Detecting stock market manipulation using supervised learning algorithms. In 2014 International Conference on Data Science and Advanced Analytics (DSAA) (pp. 435--441). IEEE.Google ScholarCross Ref
- Basak, S., Kar, S., Saha, S., Khaidem, L., & Dey, S. R. (2019). Predicting the direction of stock market prices using tree-based classifiers. The North American Journal of Economics and Finance, 47, 552--567.Google ScholarCross Ref
- Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985). Learning internal representations by error propagation (No. ICS-8506). California Univ San Diego La Jolla Inst for Cognitive Science.Google ScholarCross Ref
- Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735--1780.Google Scholar
- Chung, J., Gulcehre, C, Cho, K., & Bengio, Y. (2015, June). Gated feedback recurrent neural networks. In International conference on machine learning (pp. 2067--2075).Google Scholar
- Selvin, S., Vinayakumar, R., Gopalakrishnan, E. A., Menon, V. K., & Soman, K. P. (2017, September). Stock price prediction using LSTM, RNN and CNN-sliding window model. In 2017 international conference on advances in computing, communications and informatics (icacci) (pp. 1643--1647). IEEE.Google ScholarCross Ref
- Sim, H. S., Kim, H. I, & Ahn, J. J. (2019). Is deep learning for image recognition applicable to stock market prediction?. Complexity, 2019.Google Scholar
- Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv: 1301.3781.Google Scholar
- Pennington, J., Socher, R., & Manning, C. D. (2014, October). Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 1532--1543).Google ScholarCross Ref
- Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473.Google Scholar
- Shih, S. Y., Sun, F. K., & Lee, H. Y. (2019). Temporal pattern attention for multivariate time series forecasting. Machine Learning, 108(8-9), 1421--1441.Google ScholarDigital Library
- Hu, Z., Liu, W., Bian, J., Liu, X., & Liu, T. Y. (2018, February). Listening to chaotic whispers: A deep learning framework for news-oriented stock trend prediction. In Proceedings of the eleventh ACM international conference on web search and data mining (pp. 261--269).Google ScholarDigital Library
- Melis, G., Kočiský, T., & Blunsom, P. (2019). Mogrifier lstm. arXiv preprint arXiv: 1909 01792.Google Scholar
- Xu, Y., & Cohen, S. B. (2018, July). Stock movement prediction from tweets and historical prices. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 1970--1979).Google ScholarCross Ref
Index Terms
- Stock Movement Classification from Twitter via Mogrifier Based Memory Cells with Attention Mechanism
Recommendations
A New Model for Stock Price Movements Prediction Using Deep Neural Network
SoICT '17: Proceedings of the 8th International Symposium on Information and Communication TechnologyIn this paper, we introduce a new prediction model depend on Bidirectional Gated Recurrent Unit (BGRU). Our predictive model relies on both online financial news and historical stock prices data to predict the stock movements in the future. Experimental ...
A RNN-LSTM-Based Predictive Modelling Framework for Stock Market Prediction Using Technical Indicators
The successful prediction of the stocks’ future price would produce substantial profit to the investor. In this paper, we propose a framework with the help of various technical indicators of the stock market to predict the future prices of the stock ...
A novel hybrid model based on recurrent neural networks for stock market timing
AbstractStock market timing is regarded as a challenging task of financial prediction. An accurate prediction of stock trend can yield great profits for investors. At present, recurrent neural networks (RNNs) have a good performance in stock market ...
Comments