Information Systems Review (경영정보학연구)

The Korea Society of Management Information Systems (한국경영정보학회)
권호 표지
DOI QR코드

DOI QR Code

Chart-based Stock Price Prediction by Combing Variation Autoencoder and Attention Mechanisms

변이형 오토인코더와 어텐션 메커니즘을 결합한 차트기반 주가 예측

  • Received : 2020.12.07
  • Accepted : 2020.12.23
  • Published : 2021.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, many studies have been conducted to increase the accuracy of stock price prediction by analyzing candlestick charts using artificial intelligence techniques. However, these studies failed to consider the time-series characteristics of candlestick charts and to take into account the emotional state of market participants in data learning for stock price prediction. In order to overcome these limitations, this study produced input data by combining volatility index and candlestick charts to consider the emotional state of market participants, and used the data as input for a new method proposed on the basis of combining variantion autoencoder (VAE) and attention mechanisms for considering the time-series characteristics of candlestick chart. Fifty firms were randomly selected from the S&P 500 index and their stock prices were predicted to evaluate the performance of the method compared with existing ones such as convolutional neural network (CNN) or long-short term memory (LSTM). The results indicated the method proposed in this study showed superior performance compared to the existing ones. This study implied that the accuracy of stock price prediction could be improved by considering the emotional state of market participants and the time-series characteristics of the candlestick chart.

최근 인공지능 기법을 활용하여 캔들스틱 차트를 분석함으로써 주식가격 예측의 정확성을 높이고자 하는 다양한 연구가 진행되어 왔다. 그러나 이러한 연구들은 주식가격 예측을 위한 학습에 있어 캔들스틱 차트의 시계열적 특성을 고려하지 못한다는 점과 시장 참여자들의 감정 상태를 고려하지 못한다는 점 등이 문제로 지적되고 있다. 본 연구에서는 시장 참여자들의 감정상태를 반영하기 위해 변동성지수(VIX: volatility index) 차트를 캔들스틱 차트와 함께 고려하여 학습시키고 이를 변이형 오토인코더(VAE: variational auto encoder)와 어텐션 메커니즘(attention mechanisms)을 결합한 새로운 방법으로 분석하여 캔들스틱 차트의 시계열적 특성을 고려함으로써 기존 연구의 한계를 극복하고자 한다. 본 연구에서 제안한 방법의 성능 비교를 위해 S&P 500 기업 가운데 50개를 임의로 추출하여 제안한 방법을 통해 이들의 주식가격을 예측하고 이를 합성곱 신경망(CNN: convolutional neural network) 또는 장단기메모리(LSTM: long-short term memory) 등과 같은 기존 방법들과 비교하였다. 비교 결과 기존 방법들에 비해 본 연구에서 제안한 방법이 더 우수한 성능을 보이는 것으로 나타났다. 본 연구는 시장 참여자들의 감정 상태와 캔들스틱 차트의 시계열적 특성을 고려함으로써 주식 가격 예측의 정확성을 높였다는 점에서 그 의의가 있다.

Keywords

References

  1. 김기호, 유경원, "인구고령화가 인적자본 투자 및 금융시장에 미치는 영향", 보험개발연구, 제19권, 제3호, 2008, pp. 165-207. 
  2. 김현모, 박재홍, "온라인주식게시판 정보가주식투자자의 거래행태에 미치는 영향", Information Systems Review, 제18권, 제2호, 2016, pp. 23-38.  https://doi.org/10.14329/isr.2016.18.2.023
  3. 신동하, 최광호, 김창복, "RNN과 LSTM을 이용한 주가 예측율 향상을 위한 딥러닝 모델", 한국정보기술학회논문지, 제15권, 제10호, 2017, pp. 9-16  https://doi.org/10.14801/jkiit.2017.15.10.9
  4. Bahdanau, D., K. Cho, and Y. Bengio, "Neural machine translation by jointly learning to align and translate", 3rd International Conference on Learning Representations, ICLR, 2015, Available at http://arxiv.org/abs/1409.0473. 
  5. Bao, W., J. Yue, and Y. Rao, "A deep learning framework for financial time series using stacked autoencoders and long-short term memory", PLOS ONE, Vol.12, No.7, 2017, e0180944. 
  6. Bekaert, G. and M. Hoerova, "The VIX, the variance premium and stock market volatility", Journal of Econometrics, Vol.183, No.2, 2014, pp. 181-192.  https://doi.org/10.1016/j.jeconom.2014.05.008
  7. Bengio, Y., P. Frasconi, and P. Simard, "The problem of learning long-term dependencies in recurrent networks", IEEE International Conference on Neural Networks, 1993, pp. 1183-1188. 
  8. Braun, H. and J. S. Chandler, "Predicting stock market behavior through rule induction: Anthe-learning-from-example-approach", Decision Science, Vol.18, No.3, 1987, pp. 415-429.  https://doi.org/10.1111/j.1540-5915.1987.tb01533.x
  9. Chen, J. F., W. L. Chen, C. P. Huang, S. H. Huang, and A. P. Chen, "Financial time-series data analysis using deep convolutional neural networks", 7th International Conference on Cloud Computing and Big Data (CCBD), 2016, pp. 87-92. 
  10. Chu, W. and D. Cai, "Stacked similarity-aware autoencoders", Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17), 2017, pp. 1561-1567 
  11. Chung, H. and K. S. Shin, "Genetic algorithm-optimized multi-channel convolutional neural network for stock market prediction", Neural Computing and Applications, Vol.32, 2020, pp. 7897-7914.  https://doi.org/10.1007/s00521-019-04236-3
  12. Ding, G. and L. Qin, "Study on the prediction of stock price based on the associated network model of LSTM", International Journal of Machine Learning and Cybernetics, Vol.11, 2020, pp. 1307-1317.  https://doi.org/10.1007/s13042-019-01041-1
  13. Ding, X. Y. Zhang, T. Liu, and J. Duan, "Deep learning for event-driven stock prediction", Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), 2015, pp. 2327-2333. 
  14. Fama, E. F., "The behavior of stock-market prices", The Journal of Business, Vol.38, No.1, 1965, pp. 34-105.  https://doi.org/10.1086/294743
  15. Graves, A. and J. Schmidhuber, "Framewise phoneme classification with bidirectional LSTM and other neural network architectures", Neural Networks, Vol.18, No.5, 2005, pp. 602-610. https://doi.org/10.1016/j.neunet.2005.06.042
  16. Guo, S. J., F. C. Hsu, and C. C. Hung, "Deep candlestick predictor: A framework toward forecasting the price movement from candlestick charts", 9th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP), 2018, pp. 219-226. 
  17. Ham, Y., J. Kim, and J. Luo, "Deep learning for multi-year ENSO forecasts", Nature, Vol.573, 2019, pp. 568-572.  https://doi.org/10.1038/s41586-019-1559-7
  18. Hochreiter, S. and J. Schmidhuber, "Long short-term memory", Neural Computation, Vol.9, No.8, 1997, pp. 1735-1780.  https://doi.org/10.1162/neco.1997.9.8.1735
  19. Huynh, H. D., L. M. Dang, and D. Duong, "A new model for stock price movements prediction using deep neural network", Proceedings of the Eighth International Symposium on Information and Communication Technology - SoICT, 2017, pp.57-62. 
  20. Karevan, Z. and J. Suykens, "Transductive LSTM for time-series prediction: An application to weather forecasting", Neural Networks, Vol.125, 2020, pp. 1-9.  https://doi.org/10.1016/j.neunet.2019.12.030
  21. Kim, T. and H. Y. Kim, "Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data", PLOS ONE, Vol.14, No.2, 2019, e0212320. 
  22. Kingma, D. P. and M. Welling, "Stochastic gradient VB and the variational auto-encoder", Second International Conference on Learning Representations, 2013, pp. 1-14. 
  23. Liu Y., Z. Qin, P. Li, and T. Wan, "Stock volatility prediction using recurrent neural networks with sentiment analysis", International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, 2017, pp. 192-201 
  24. Liu, H. and B. Song, "Stock price trend prediction model based on deep residual network and stock price graph", 11th International Symposium on Computational Intelligence and Design (ISCID), 2018, pp. 328-331. 
  25. Marshall, B. R., Young, M. R., and L. C. Rose, "Candlestick technical trading strategies: Can they create value for investors?", Journal of Banking & Finance, Vol.30, No.8, 2006, pp. 2303-2323.  https://doi.org/10.1016/j.jbankfin.2005.08.001
  26. Murphy, J. J., Intermarket Analysis: Profiting from Global Market Relationships, John Wiley & Sons, Toronto, 2011. 
  27. Nguyen, T. H., K. Shirai, and J. Velcin, "Sentiment analysis on social media for stock movement prediction", Expert Systems with Applications, Vol.42, No.24, 2015, pp. 9603-9611.  https://doi.org/10.1016/j.eswa.2015.07.052
  28. Niaki, S. T. A. and S. Hoseinzade, "Forecasting S&P 500 index using artificial neural networks and design of experiments", Journal of Industrial Engineering International, Vol.9, No.1, 2013, pp. 1-9.  https://doi.org/10.1186/2251-712X-9-1
  29. Ou, J. A. and S. H. Penman, "Accounting measurement, price earnings ratio, and the information-content of security prices", Journal of Accounting Research, Vol.27, 1989, pp. 111-144.  https://doi.org/10.2307/2491068
  30. Pagolu, V. S., K. N. R. Challa, G. Panda, and B. Majhi, "Sentiment analysis of twitter data for predicting stock market movements", International conference on Signal Processing, Communication, Power and Embedded System (SCOPES), 2016, pp. 1-5. 
  31. Patalay, S. and M. R. Bandlamudib, "Stock price prediction and portfolio selection using artificial intelligence", Asia Pacific Journal of Information Systems, Vol.30, No.1, 2020, pp. 31-52  https://doi.org/10.14329/apjis.2020.30.1.31
  32. Persio, L. D. and O. Honchar, "Artifiial neural networks architectures for stock price prediction: Comparisons and applications", International Journal of Circuits, Systems and Signal Processing, Vol.10, 2016, pp. 403-413. 
  33. Rush, A. M., S. Chopra, and J. Weston, "A neural attention model for abstractive sentence summarization", Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015, pp. 379-389. 
  34. Schuster, M. and K. K. Paliwal, "Bidirectional recurrent neural networks", IEEE Transactions on Signal Processing, Vol.45, No.11, 1997, pp. 2673-2681.  https://doi.org/10.1109/78.650093
  35. Song, Y., Stock Trend Prediction: Based on Machine Learning Methods, Master Thesis, UCLA, 2018, Available at https://escholarship.org/uc/item/0cp1x8th. 
  36. Yao, K., G. Zweig, and B. Peng, "Attention with intention for a neural network conversation model", NIPS Workshop on Machine Learning for Spoken Language Understanding and Interaction 2015, 2015, Available at http://arxiv.org/abs/1510.08565. 
  37. Zhipeng, J. and L. Chao, "Financial time series forecasting based on characterized candlestick and the support vector classification with cooperative coevolution", Journal of Computers, Vol.14, No.3, 2019, pp. 195-209.  https://doi.org/10.17706/jcp.14.3.195-209
  38. Zhong, X. and D. Enke, "Forecasting daily stock market return using dimensionality reduction", Expert Systems with Applications, Vol.67, 2017, pp. 126-139. https://doi.org/10.1016/j.eswa.2016.09.027