Information Systems Review (경영정보학연구)

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

DOI QR Code

Stock Price Direction Prediction Using Convolutional Neural Network: Emphasis on Correlation Feature Selection

합성곱 신경망을 이용한 주가방향 예측: 상관관계 속성선택 방법을 중심으로

  • Kyun Sun Eo (SKK Business School, Sungkyunkwan University) ;
  • Kun Chang Lee (Global Business Administration/Department of Health Sciences & Technology / SAIHST(Samsung Advanced Institute for Health Sciences & Technology), Sungkyunkwan University)
  • 어균선 (성균관대학교 경영대학) ;
  • 이건창 (성균관대학교 글로벌 경영학과/삼성융합의과학원(SAIHST) 융합의과학과)
  • Received : 2020.04.18
  • Accepted : 2020.06.10
  • Published : 2020.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, deep learning has shown high performance in various applications such as pattern analysis and image classification. Especially known as a difficult task in the field of machine learning research, stock market forecasting is an area where the effectiveness of deep learning techniques is being verified by many researchers. This study proposed a deep learning Convolutional Neural Network (CNN) model to predict the direction of stock prices. We then used the feature selection method to improve the performance of the model. We compared the performance of machine learning classifiers against CNN. The classifiers used in this study are as follows: Logistic Regression, Decision Tree, Neural Network, Support Vector Machine, Adaboost, Bagging, and Random Forest. The results of this study confirmed that the CNN showed higher performancecompared with other classifiers in the case of feature selection. The results show that the CNN model effectively predicted the stock price direction by analyzing the embedded values of the financial data

딥러닝(Deep learning) 기법은 패턴분석, 이미지분류 등 다양한 분야에서 높은 성과를 나타내고 있다. 특히, 주식시장 분석문제는 머신러닝 연구분야에서도 어려운 분야이므로 딥러닝이 많이 활용되는 영역이다. 본 연구에서는 패턴분석과 분류능력이 높은 딥러닝의 일종인 합성곱신경망(Convolutional Neural Network) 모델을 활용하여 주가방향 예측방법을 제안한다. 추가적으로 합성곱신경망 모델을 효율적으로 학습시키기 위한 속성선택(Feature Selection, FS)방법이 적용된다. 합성곱신경망 모델의 성과는 머신러닝 단일 분류기와 앙상블 분류기를 벤치마킹하여 객관적으로 검증된다. 본 연구에서 벤치마킹한 분류기는 로지스틱 회귀분석(Logistic Regression), 의사결정나무(Decision Tree), 인공신경망(Neural Network), 서포트 벡터머신(Support Vector Machine), 아다부스트(Adaboost), 배깅(Bagging), 랜덤포레스트(Random Forest)이다. 실증분석 결과, 속성선택을 적용한 합성곱신경망이 다른 벤치마킹 분류기보다 분류 성능이 상대적으로 높게 나타났다. 이러한 결과는 합성곱신경망 모델과 속성선택방법을 적용한 예측방법이 기업의 재무자료에 내포된 가치를 보다 정교하게 분석할 수 있는 가능성이 있음을 실증적으로 확인할 수 있었다.

Keywords

Acknowledgement

이 논문은 2019년 대한민국 교육부와 한국연구재단의 지원을 받아 수행된 연구임(NRF-2019S1A5A2A01046529).

References

  1. Affonso, C., A. L. D. Rossi, F. H. A. Vieira, and A. C. P. de Leon Ferreira, "Deep learning for biological image classification", Expert Systems with Applications, Vol.85, 2017, pp. 114-122. https://doi.org/10.1016/j.eswa.2017.05.039
  2. Arlot, S. and A. Celisse, "A survey of cross-validation procedures for model selection", Statistics Surveys, Vol.4, 2010, pp. 40-79. https://doi.org/10.1214/09-SS054
  3. Ballings, M., D. Van den Poel, N. Hespeels, and R. Gryp, "Evaluating multiple classifiers for stock price direction prediction", Expert Systems with Applications, Vol.42, No.20, 2015, pp. 7046-7056. https://doi.org/10.1016/j.eswa.2015.05.013
  4. Chang, F., "Deep learning for biological image classification", Neural Networks & Machine Learning, Vol.1, No.1, 2017, pp. 2-2.
  5. Chong, E., C. Han, and F. C. Park, "Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies", Expert Systems with Applications, Vol.83, 2017, pp. 187-205. https://doi.org/10.1016/j.eswa.2017.04.030
  6. Dang, L. M., S. I. Hassan, S. Im, and H. Moon, "Face image manipulation detection based on a convolutional neural network", Expert Systems with Applications, Vol.129, 2019, pp. 156-168. https://doi.org/10.1016/j.eswa.2019.04.005
  7. Di Persio, L. and O. Honchar, "Artificial neural networks architectures for stock price prediction: Comparisons and applications", International Journal of Circuits, Systems and Signal Processing, Vol.10, 2016, pp. 403-413.
  8. Eo, K. S. and K. C. Lee, "Predicting stock price direction by using data mining methods", Journal of the Korea Society of Computer and Information, Vol.22, No.11, 2017, pp. 111-116. https://doi.org/10.9708/JKSCI.2017.22.11.111
  9. Gunduz, H., Y. Yaslan, and Z. Cataltepe, "Intraday prediction of Borsa Istanbul using convolutional neural networks and feature correlations", Knowledge-Based Systems, Vol.137, 2017, pp. 138-148. https://doi.org/10.1016/j.knosys.2017.09.023
  10. Hiransha, M., E. A. Gopalakrishnan, V. K. Menon, and K. P. Soman, "NSE stock market prediction using deep-learning models", Procedia Computer Science, Vol.132, 2018, pp. 1351-1362. https://doi.org/10.1016/j.procs.2018.05.050
  11. Hosaka, T., "Bankruptcy prediction using imaged financial ratios and convolutional neural networks", Expert Systems with Applications, Vol.117, 2019, pp. 287-299. https://doi.org/10.1016/j.eswa.2018.09.039
  12. Hoseinzade, E. and S. Haratizadeh "CNNpred: CNN-based stock market prediction using a diverse set of variables", Expert Systems with Applications, Vol.129, 2019, pp. 273-285. https://doi.org/10.1016/j.eswa.2019.03.029
  13. Hu, H., L. Tang, S. Zhang, and H. Wang, "Predicting the direction of stock markets using optimized neural networks with Google Trends", Neurocomputing, Vol.285, 2018, pp. 188-195. https://doi.org/10.1016/j.neucom.2018.01.038
  14. Huang, W., Y. Nakamori, and S. Y. Wang, "Forecasting stock market movement direction with support vector machine", Computers & Operations Research, Vol.32, No.10, 2005, pp. 2513-2522. https://doi.org/10.1016/j.cor.2004.03.016
  15. Joo, I. T. and S. H. Choi, "Stock prediction model based on bidirectional LSTM recurrent neural network", Korea Information Electron Communication Technology, Vol.11, No.2, 2018, pp. 204-208.
  16. Kim, K., "Financial time series forecasting using support vector machines", Neurocomputing, Vol.55, 2003, No.1-2, pp. 307-319. https://doi.org/10.1016/S0925-2312(03)00372-2
  17. Kingma, D. P. and J. Ba, "Adam: A method for stochastic optimization", The 3rd International Conference on Learning Representations, 2014, arXiv preprint arXiv:1412.6980.
  18. Kraus, M. and S. Feuerriegel, "Decision support from financial disclosures with deep neural networks and transfer learning", Decision Support Systems, Vol.104, 2017, pp. 38-48. https://doi.org/10.1016/j.dss.2017.10.001
  19. LeCun, Y. and Y. Bengio, "Convolutional networks for images, speech, and time series", In M. Arbib, editor, The Handbook of Brain Theory and Neural Networks, MIT Press, Cambridge, Massachusetts, 1995, pp. 255-258.
  20. LeCun, Y., L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition", Proceedings of the IEEE, Vol.86, No.11, 1998, pp. 2278-2324. https://doi.org/10.1109/5.726791
  21. Lee, M. C., "Using support vector machine with a hybrid feature selection method to the stock trend prediction", Expert Systems with Applications, Vol.36, No.8, 2009, pp. 10896-10904. https://doi.org/10.1016/j.eswa.2009.02.038
  22. Lee, M. S. and H. C. Ahn, "A time series graph based convolutional neural network model for effective input variable pattern learning: Application to the prediction of stock market", Journal of Intelligence and Information Systems, Vol.24, No.1, 2018, pp. 167-181.
  23. Moghaddam, M., Q. Chen, and A. V. Deshmukh, "A neuro-inspired computational model for adaptive fault diagnosis", Expert Systems with Applications, Vol.140, 2020, p. 112879.
  24. Ou, P. and H. Wang, "Prediction of stock market index movement by ten data mining techniques", Modern Applied Science, Vol.3, No.12, 2009, pp. 28-42. https://doi.org/10.5539/mas.v3n12p28
  25. Patel, J., S. Shah, P. Thakkar, and K. Kotecha, "Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques", Expert Systems with Applications, Vol.42, No.1, 2015, pp. 259-268. https://doi.org/10.1016/j.eswa.2014.07.040
  26. Pour, M. P. and H. Seker, "Transform domain representation-driven convolutional neural networks for skin lesion segmentation", Expert Systems with Applications, Vol.144, p. 113129, 2020.
  27. Qiu, M., Y. Song, and F. Akagi, "Application of artificial neural network for the prediction of stock market returns: The case of the Japanese stock market", Chaos, Solitons & Fractals, Vol.85, 2016, pp. 1-7. https://doi.org/10.1016/j.chaos.2016.01.004
  28. Sellami, A. and H. Hwang, "A robust deep convolutional neural network with batch-weighted loss for heartbeat classification", Expert Systems with Applications, Vol.122, 2019, pp. 75-84, https://doi.org/10.1016/j.eswa.2018.12.037
  29. Sezer, O. B. and A. M. Ozbayoglu, "Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approach", Applied Soft Computing, Vol. 70, 2018, pp. 525-538. https://doi.org/10.1016/j.asoc.2018.04.024
  30. Soomro, T. A., A. J. Afifi, J. Gao, O. Hellwich, L. Zheng, and M. Paul, "Strided fully convolutional neural network for boosting the sensitivity of retinal blood vessels segmentation", Expert Systems with Applications, Vol. 134, 2019, pp. 36-52. https://doi.org/10.1016/j.eswa.2019.05.029
  31. Ting, F. F., Y. J. Tan, and K. S. Sim, "Convolutional neural network improvement for breast cancer classification", Expert Systems with Applications, Vol.120, 2019, pp. 103-115. https://doi.org/10.1016/j.eswa.2018.11.008
  32. Wang, Q., W. Xu, and H. Zheng, "Combining the wisdom of crowds and technical analysis for financial market prediction using deep random subspace ensembles", Neurocomputing, Vol.299, 2018, pp. 51-61. https://doi.org/10.1016/j.neucom.2018.02.095
  33. Yang, H., C. Yuan, B. Du, Y. Li, J. Xing, W. Hu, and S. J. Maybank, "Asymmetric 3d convolutional neural networks for action recognition", Pattern Recognition, Vol.85, 2019, pp. 1-12. https://doi.org/10.1016/j.patcog.2018.07.028
  34. Yuan, X., L. Xie, and M. Abouelenien, "A regularized ensemble framework of deep learning for cancer detection from multi-class, imbalanced training data", Pattern Recognition, Vol.77, 2018, pp. 160-172. https://doi.org/10.1016/j.patcog.2017.12.017
  35. 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