Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

DR-LSTM: Dimension reduction based deep learning approach to predict stock price

  • Ah-ram Lee (Department of Statistics, Ewha Womans University) ;
  • Jae Youn Ahn (Department of Statistics, Ewha Womans University) ;
  • Ji Eun Choi (Department of Statistics and Data Science, Pukyong National University) ;
  • Kyongwon Kim (Department of Statistics, Ewha Womans University)
  • Received : 2024.01.18
  • Accepted : 2024.01.30
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

In recent decades, increasing research attention has been directed toward predicting the price of stocks in financial markets using deep learning methods. For instance, recurrent neural network (RNN) is known to be competitive for datasets with time-series data. Long short term memory (LSTM) further improves RNN by providing an alternative approach to the gradient loss problem. LSTM has its own advantage in predictive accuracy by retaining memory for a longer time. In this paper, we combine both supervised and unsupervised dimension reduction methods with LSTM to enhance the forecasting performance and refer to this as a dimension reduction based LSTM (DR-LSTM) approach. For a supervised dimension reduction method, we use methods such as sliced inverse regression (SIR), sparse SIR, and kernel SIR. Furthermore, principal component analysis (PCA), sparse PCA, and kernel PCA are used as unsupervised dimension reduction methods. Using datasets of real stock market index (S&P 500, STOXX Europe 600, and KOSPI), we present a comparative study on predictive accuracy between six DR-LSTM methods and time series modeling.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No.2021R1A6A1A10039823, RS-2023-00219212).

References

  1. Aizerman A (1964). Theoretical foundations of the potential function method in pattern recognition learning, Automation and Remote Control, 25, 821-837.
  2. Aronszajn N (1950). Theory of reproducing kernels, Transactions of the American Mathematical Society, 68, 337-404. https://doi.org/10.1090/S0002-9947-1950-0051437-7
  3. Boser BE, Guyon IM, and Vapnik VN (1992, July). A training algorithm for optimal margin classifiers. In Proceedings of the Fifth Annual Workshop on Computational Learning Theory, 144-152.
  4. Chen K, Zhou Y, and Dai F (2015, October). A LSTM-based method for stock returns prediction: A case study of China stock market. In Proceedings of 2015 IEEE International Conference on Big Data (big data), Santa Clara, CA, 2823-2824.
  5. Fan J and Li R (2001). Variable selection via nonconcave penalized likelihood and its oracle properties, Journal of the American Statistical Association, 96, 1348-1360. https://doi.org/10.1198/016214501753382273
  6. Fong Y and Xu J (2021). Forward stepwise deep autoencoder-based monotone nonlinear dimensionality reduction methods, Journal of Computational and Graphical Statistics, 30, 519-529. https://doi.org/10.1080/10618600.2020.1856119
  7. Gao S, Han L, Luo D, Liu G, Xiao Z, Shan G, Zhang Y, and Zhou W (2021). Modeling drug mechanism of action with large scale gene-expression profiles using GPAR, an artificial intelligence platform, BMC Bioinformatics, 22, 1-13. https://doi.org/10.1186/s12859-020-03915-6
  8. Hochreiter S and Schmidhuber J (1997). Long short-term memory, Neural Computation, 9, 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  9. Idrees SM, Alam MA, and Agarwal P (2019). A prediction approach for stock market volatility based on time series data, IEEE Access, 7, 17287-17298. https://doi.org/10.1109/ACCESS.2019.2895252
  10. Jolliffe IT (1986). Generalizations and adaptations of principal component analysis, Principal Component Analysis, Springer, 223-234.
  11. Kwiatkowski D, Phillips PC, Schmidt P, and Shin Y (1992). Testing the null hypothesis of stationarity against the alternative of a unit root: How sure are we that economic time series have a unit root?, Journal of Econometrics, 54, 159-178. https://doi.org/10.1016/0304-4076(92)90104-Y
  12. Kim K, Li B, Yu Z, and Li L (2020). On post dimension reduction statistical inference, The Annals of Statistics, 48, 1567-1592. https://doi.org/10.1214/19-AOS1859
  13. Kim K (2023). A note on sufficient dimension reduction with post dimension reduction statistical inference, AStA Advances in Statistical Analysis, 1-21.
  14. Li KC (1991). Sliced inverse regression for dimension reduction, Journal of the American Statistical Association, 86, 316-327. https://doi.org/10.1080/01621459.1991.10475035
  15. Li B (2018). Sufficient Dimension Reduction: Methods and Applications with R, CRC Press, New York.
  16. Li L (2007). Sparse sufficient dimension reduction, Biometrika, 94, 603-613. https://doi.org/10.1093/biomet/asm044
  17. Li KC (1992). On principal Hessian directions for data visualization and dimension reduction: Another application of Stein's lemma, Journal of the American Statistical Association, 87, 1025-1039. https://doi.org/10.1080/01621459.1992.10476258
  18. Li B and Wang S (2007). On directional regression for dimension reduction, Journal of the American Statistical Association, 102, 997-1008. https://doi.org/10.1198/016214507000000536
  19. Madziwa L, Pillalamarry M, and Chatterjee S (2022). Gold price forecasting using multivariate stochastic model, Resources Policy, 76, 102544.
  20. Malladi RK and Dheeriya PL (2021). Time series analysis of cryptocurrency returns and volatilities, Journal of Economics and Finance, 45, 75-94. https://doi.org/10.1007/s12197-020-09526-4
  21. Matias JM and Reboredo JC (2012). Forecasting performance of nonlinear models for intraday stock returns, Journal of Forecasting, 31, 172-188. https://doi.org/10.1002/for.1218
  22. Ramezanian R, Peymanfar A, and Ebrahimi SB (2019). An integrated framework of genetic network programming and multi-layer perceptron neural network for prediction of daily stock return: An application in Tehran stock exchange market, Applied Soft Computing, 82, 105551.
  23. Selvin S, Vinayakumar R, Gopalakrishnan EA, Menon VK, and Soman KP (2017, September). Stock price prediction using LSTM, RNN and CNN-sliding window model. In Proceedings of 2017 International Conference on Advances in Computing, Communications and Informatics (icacci), Udupi, 1643-1647.
  24. Sujatha KV and Sundaram SM (2010). A combined PCA-MLP model for predicting stock index. In Proceedings of the 1st Amrita ACM-W Celebration on Women in Computing in India, 1-6.
  25. Scholkopf B, Smola A, and Muller KR (1997, October). Kernel principal component analysis. In Proceedings of International Conference on Artificial Neural Networks, Berlin, Heidelberg, 583-588.
  26. Tsai CF, Lin YC, Yen DC, and Chen YM (2011). Predicting stock returns by classifier ensembles, Applied Soft Computing, 11, 2452-2459. https://doi.org/10.1016/j.asoc.2010.10.001
  27. Tibshirani R (1996). Regression shrinkage and selection via the lasso, Journal of the Royal Statistical Society Series B: Statistical Methodology, 58, 267-288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
  28. Tran MN, Nguyen N, Nott D, and Kohn R (2020). Bayesian deep net GLM and GLMM, Journal of Computational and Graphical Statistics, 29, 97-113. https://doi.org/10.1080/10618600.2019.1637747
  29. Wang T, Lei S, Jiang Y, Chang C, Snoussi H, Shan G, and Fu Y (2022). Accelerating temporal action proposal generation via high performance computing, Frontiers of Computer Science, 16, 1-10. https://doi.org/10.1007/s11704-021-0173-7
  30. Wang J, Sun T, Liu B, Cao Y, and Wang D (2018, December). Financial markets prediction with deep learning. In Proceedings of 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, 97-104.
  31. Wen Y, Lin P, and Nie X (2020, March). Research of stock price prediction based on PCA-LSTM model. In Proceedings of IOP Conference Series: Materials Science and Engineering, Guangzhou, 012109.
  32. Wu HM (2008). Kernel sliced inverse regression with applications to classification, Journal of Computational and Graphical Statistics, 17, 590-610. https://doi.org/10.1198/106186008X345161
  33. Xiao X, Mo H, Zhang Y, and Shan G (2022). Meta-ANN-A dynamic artificial neural network refined by meta-learning for short-term load forecasting, Energy, 246, 123418.
  34. Xia Y, Tong H, Li WK, and Zhu L-X (2009). An adaptive estimation of dimension reduction space, Journal of the Royal Statistical Society Series B: Statistical Methodology, 64, 299-346.
  35. Yin X, Li B, and Cook RD (2008). Successive direction extraction for estimating the central subspace in a multiple-index regression, Journal of Multivariate Analysis, 99, 1733-1757. https://doi.org/10.1016/j.jmva.2008.01.006
  36. Zou H, Hastie T, and Tibshirani R (2006). Sparse principal component analysis, Journal of Computational and Graphical Statistics, 15, 265-286. https://doi.org/10.1198/106186006X113430