A prediction model for stock market based on the integration of independent component analysis and Multi-LSTM

Hongzeng He; Shufen Dai; Hongzeng He; Shufen Dai

doi:10.3934/era.2022196

Electronic Research Archive

2022, Volume 30, Issue 10: 3855-3871. doi: 10.3934/era.2022196

Previous Article Next Article

Research article

A prediction model for stock market based on the integration of independent component analysis and Multi-LSTM

Hongzeng He ^{1,2
,
,},
Shufen Dai ¹

1.
School of Economics and Management, University of Science and Technology Beijing, Beijing 100083, China
2.
Returned Overseas Talent and Expert Service Center, MOHRSS, Beijing 100083, China

Received: 20 June 2022 Revised: 14 August 2022 Accepted: 18 August 2022 Published: 25 August 2022

In this paper, we investigate the statistical behaviors of the stock market complex network. A hybrid model is proposed to predict the variations of five stock prices in the securities plate sub-network. This model integrates independent component analysis (ICA) and multivariate long short-term memory (Multi-LSTM) neural network to analyze the trading noise and improve the prediction accuracy of stock prices in the sub-network. Firstly, we apply ICA to deconstruct the original dataset and remove the independent components that represent the trading noise. Secondly, the rest of the independent components are given to Multi-LSTM neural network. Finally, prediction results are reconstructed from the outputs of the Multi-LSTM neural network and the corresponding mixing matrix. The experiment results indicate that the hybrid model outperforms the benchmark approaches, especially in terms of the stock market complex network.
- independent component analysis,
- Multi-LSTM,
- stock market,
- complex network,
- prediction model
Citation: Hongzeng He, Shufen Dai. A prediction model for stock market based on the integration of independent component analysis and Multi-LSTM[J]. Electronic Research Archive, 2022, 30(10): 3855-3871. doi: 10.3934/era.2022196

Related Papers:

Abstract

In this paper, we investigate the statistical behaviors of the stock market complex network. A hybrid model is proposed to predict the variations of five stock prices in the securities plate sub-network. This model integrates independent component analysis (ICA) and multivariate long short-term memory (Multi-LSTM) neural network to analyze the trading noise and improve the prediction accuracy of stock prices in the sub-network. Firstly, we apply ICA to deconstruct the original dataset and remove the independent components that represent the trading noise. Secondly, the rest of the independent components are given to Multi-LSTM neural network. Finally, prediction results are reconstructed from the outputs of the Multi-LSTM neural network and the corresponding mixing matrix. The experiment results indicate that the hybrid model outperforms the benchmark approaches, especially in terms of the stock market complex network.

References

[1]	H. He, S. Dai, Effectiveness of price limit on stock market network: A time-migrated DCCA approach, Complexity, 2021 (2021). https://doi.org/10.1155/2021/3265843 doi: 10.1155/2021/3265843
[2]	S. Kumar Chandar, Hybrid models for intraday stock price forecasting based on artificial neural networks and metaheuristic algorithms, Pattern Recognit. Lett., 147 (2021), 124–133. https://doi.org/10.1016/j.patrec.2021.03.030 doi: 10.1016/j.patrec.2021.03.030
[3]	A. Bose, C. Hsu, S. S. Roy, K. C. Lee, B. Mohammadi-ivatloo, S. Abimannan, Forecasting stock price by hybrid model of cascading Multivariate Adaptive Regression Splines and Deep Neural Network, Comput. Electr. Eng., 95 (2021), 107405. https://doi.org/10.1016/j.compeleceng.2021.107405 doi: 10.1016/j.compeleceng.2021.107405
[4]	A. Thakkar, K. Chaudhari, A comprehensive survey on deep neural networks for stock market: The need, challenges, and future directions, Expert Syst. Appl., 177 (2021), 114800. https://doi.org/10.1016/j.eswa.2021.114800 doi: 10.1016/j.eswa.2021.114800
[5]	H. Na, S. Kim, Predicting stock prices based on informed traders' activities using deep neural networks, Econ. Lett., 204 (2021), 109917. https://doi.org/10.1016/j.econlet.2021.109917 doi: 10.1016/j.econlet.2021.109917
[6]	S. Wang, Z. Li, J. Zhu, Z. Lin, M. Zhong, Stock selection strategy of A-share market based on rotation effect and random forest, AIMS Math., 5 (2020), 4563–4580. https://doi.org/10.3934/math.2020293 doi: 10.3934/math.2020293
[7]	Z. Dai, H. Zhou, X. Dong, Forecasting stock market volatility: the role of gold and exchange rate, AIMS Math., 5 (2020), 5094–5105. https://doi.org/10.3934/math.2020327 doi: 10.3934/math.2020327
[8]	J. E, J. Ye, L. He, H. Jin, A denoising carbon price forecasting method based on the integration of kernel independent component analysis and least squares support vector regression, Neurocomputing, 434 (2021), 67–79. https://doi.org/10.1016/j.neucom.2020.12.086 doi: 10.1016/j.neucom.2020.12.086
[9]	C. Lu, Integrating independent component analysis-based denoising scheme with neural network for stock price prediction, Expert Syst. Appl., 37 (2010), 7056–7064. https://doi.org/10.1016/j.eswa.2010.03.012 doi: 10.1016/j.eswa.2010.03.012
[10]	L. Kao, C. Chiu, C. Lu, J. Yang, Integration of nonlinear independent component analysis and support vector regression for stock price forecasting, Neurocomputing, 99 (2013), 534–542. https://doi.org/10.1016/j.neucom.2012.06.037 doi: 10.1016/j.neucom.2012.06.037
[11]	J. E, Y. Bao, J. Ye, Crude oil price analysis and forecasting based on variational mode decomposition and independent component analysis, Physica A, 484 (2017), 412–427. https://doi.org/10.1016/j.physa.2017.04.160 doi: 10.1016/j.physa.2017.04.160
[12]	J. E, J. Ye, H. Jin, A novel hybrid model on the prediction of time series and its application for the gold price analysis and forecasting, Physica A, 527 (2019), 121454. https://doi.org/10.1016/j.physa.2019.121454 doi: 10.1016/j.physa.2019.121454
[13]	C. Fang, F. Marle, Dealing with project complexity by matrix-based propagation modelling for project risk analysis, J. Eng. Des., 24 (2013), 239–256. https://doi.org/10.1080/09544828.2012.720014 doi: 10.1080/09544828.2012.720014
[14]	W. Qiao, W. Liu, E. Liu, A combination model based on wavelet transform for predicting the difference between monthly natural gas production and consumption of U.S., Energy, 235 (2021), 121216. https://doi.org/10.1016/j.energy.2021.121216 doi: 10.1016/j.energy.2021.121216
[15]	Y. Zhang, B. Yan. M. Aasma, A novel deep learning framework: Prediction and analysis of financial time series using CEEMD and LSTM, Expert Syst. Appl., 159 (2020), 113609. https://doi.org/10.1016/j.eswa.2020.113609 doi: 10.1016/j.eswa.2020.113609
[16]	W. Bao, J. Yue, Y. Rao, A deep learning framework for financial time series using stacked autoencoders and long-short term memory, PLOS ONE, 12 (2017), e0180944. https://doi.org/10.1371/journal.pone.0180944 doi: 10.1371/journal.pone.0180944
[17]	P. Comon, Independent component analysis, A new concept, Signal Process., 36 (1994), 287–314. https://doi.org/10.1016/0165-1684(94)90029-9 doi: 10.1016/0165-1684(94)90029-9
[18]	Y. Chen, J. Wu, Z. Wu, China's commercial bank stock price prediction using a novel K-means-LSTM hybrid approach, Expert Syst. Appl., 202 (2022), 117370. https://doi.org/10.1016/j.eswa.2022.117370 doi: 10.1016/j.eswa.2022.117370
[19]	K. Bandara, C. Bergmeir, S. Smyl, Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approach, Expert Syst. Appl., 140 (2020), 112896. https://doi.org/10.1016/j.eswa.2019.112896 doi: 10.1016/j.eswa.2019.112896
[20]	H. G. Seedig, R. Grothmann, T. A. Runkler, Forecasting of clustered time series with recurrent neural networks and a fuzzy clustering scheme, in 2009 International Joint Conference on Neural Networks, IEEE, (2009), 2846–2853. https://doi.org/10.1109/IJCNN.2009.5178775
[21]	A. Hyvärinen, Topographic independent component analysis, Neural Comput., 13 (2001), 1527–1558. https://doi.org/10.1162/089976601750264992 doi: 10.1162/089976601750264992
[22]	W. Dai, J. Wu, C. Lu, Combining nonlinear independent component analysis and neural network for the prediction of Asian stock market indexes, Expert Syst. Appl., 39 (2012), 4444–4452. https://doi.org/10.1016/j.eswa.2011.09.145 doi: 10.1016/j.eswa.2011.09.145
[23]	Y. Ouyang, Evaluation of river water quality monitoring stations by principal component analysis, Water. Res., 39 (2005), 2621–2635. https://doi.org/10.1016/j.watres.2005.04.024 doi: 10.1016/j.watres.2005.04.024
[24]	F. Zhou, Z. Huang, C. Zhang, J. Yan, Carbon price forecasting based on CEEMDAN and LSTM, Appl. Energy, 311 (2022), 118601. https://doi.org/10.1016/j.apenergy.2022.118601 doi: 10.1016/j.apenergy.2022.118601
[25]	Y. Wu, Q. Wu, J. Zhu, Improved EEMD-based crude oil price forecasting using LSTM networks, Physica A, 516 (2019), 114–124. https://doi.org/10.1016/j.physa.2018.09.120 doi: 10.1016/j.physa.2018.09.120
[26]	M. A. Colominas, G. Schlotthauer, M. E. Torres, Improved complete ensemble EMD: A suitable tool for biomedical signal processing, Biomed. Signal Process. Control, 14 (2014), 19–29. https://doi.org/10.1016/j.bspc.2014.06.009 doi: 10.1016/j.bspc.2014.06.009
[27]	D. Borges, M. C. V. Nascimento, COVID-19 ICU demand forecasting: A two-stage Prophet-LSTM approach, Appl. Soft Comput., 125 (2022), 109181. https://doi.org/10.1016/j.asoc.2022.109181 doi: 10.1016/j.asoc.2022.109181
[28]	S. Mehrkanoon, Deep shared representation learning for weather elements forecasting, Knowledge Based Syst., 179 (2019), 120–128. https://doi.org/10.1016/j.knosys.2019.05.009 doi: 10.1016/j.knosys.2019.05.009
[29]	F. X. Diebold, R S. Mariano, Comparing predictive accuracy, J. Bus. Econ. Stat., 13 (1995), 134–144. https://doi.org/10.2307/1392185 doi: 10.2307/1392185
[30]	H. Liu, J. Wang, K. Vajravelu, Integrating independent component analysis and principal component analysis with neural network to predict Chinese stock market, Math. Probl. Eng., 2011 (2011), 1–15. https://doi.org/10.1155/2011/382659 doi: 10.1155/2011/382659
[31]	B. Huang, Q. Ding, G. Sun, H. Li, Stock Prediction based on Bayesian-LSTM, in ICMLC 2018: Proceedings of the 2018 10th International Conference on Machine Learning and Computing, (2018), 128–133. https://doi.org/10.1145/3195106.3195170
[32]	C. Lu, T. Lee, C. Chiu, Financial time series forecasting using independent component analysis and support vector regression, Decis. Support Syst., 47 (2009), 115–125. https://doi.org/10.1016/j.dss.2009.02.001 doi: 10.1016/j.dss.2009.02.001

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)