Education, Science, Technology, Innovation and Life
Open Access
Sign In

A Time Series Data Prediction Model Based on Adaptive Weighted LSTM

Download as PDF

DOI: 10.23977/acss.2023.070112 | Downloads: 33 | Views: 495

Author(s)

Wanlu Shen 1, Ruotong Wu 1

Affiliation(s)

1 School of Science, Northeast Electric Power University, Jilin, 132011, China

Corresponding Author

Wanlu Shen

ABSTRACT

Financial time series prediction has always been a hot topic in the field of statistics learning. Aiming at the step selection problem of LSTM time series prediction model, this paper proposes an adaptive weighted LSTM model based on model average method. The model average is mainly reflected in two aspects: On the one hand, the proposed method takes intraday price information into account. Firstly, functional and nonlinear information of intraday price series are extracted through functional principal component analysis and kernel principal component analysis, and then Bagging is used to fit the residual sequence generated by the original LSTM model. On the other hand, the proposed method integrates the information of the model under different time Windows by using the weight based on distance correlation coefficient, and adaptively solves the step size selection problem, so as to improve the effectiveness of the overall model. The actual data analysis results show that the proposed method can effectively improve the prediction accuracy of the original LSTM model and has a certain robustness. Due to the flexibility of the proposed method, it can be used in time series prediction such as energy consumption prediction, environment detection and road traffic flow monitoring.

KEYWORDS

Stock Price Prediction, LSTM, FPCA, PCA, Model Averaging Method, Distance correlation coefficient

CITE THIS PAPER

Wanlu Shen, Ruotong Wu. A Time Series Data Prediction Model Based on Adaptive Weighted LSTM. Advances in Computer, Signals and Systems (2023) Vol. 7: 91-100. DOI: http://dx.doi.org/10.23977/acss.2023.070112.

REFERENCES

[1] Li Z W, Han J, Song Y P. On the forecasting of high-frequency financial time series based on ARIMA model improved by deep learning [J]. Journal of Forecasting, 2020, 39(7): 1081-1097
[2] Engle R F, Rangel J G. The spline-GARCH model for low-frequency volatility and its global macroeconomic causes [J]. The Review of Financial Studies, 2008, 21(3): 1187-1222
[3] Qi Yang, Xianbing Cao. Stock price analysis and prediction based on ARMA-GARCH model [J]. Practice and understanding of mathematics, 2016, 46(06): 80-86.
[4] Wei Dou. Stock Price Trend Forecast Based on LSTM [D]. Tianjin University, 2020. DOI: 10.27356/d. cnki. gtjdu. 2020.003177.
[5] Xingjun Xu, Gangfeng Yan. Stock Price Trend Analysis Based on BP Neural Network [J]. Zhejiang Finance, 2011(11): 57-59, 64
[6] Youen Chen, Yang Luo. A Review of Stock Forecasting Based on Portfolio Model [J]. Science and Technology and Industry, 2022, 22(11): 214-220.
[7] Yu Chen. Based on optimizing multi-dimensional characteristics of machine learning to pick stocks and timing portfolio strategy to build [D]. Nanjing information engineering university, 2022. The DOI: 10.27248/ d.cnki.gnjqc. 2022.000489.
[8] Liu F, Cai M, Wang L, et al. An Ensemble Model Based on Adaptive Noise Reducer and Over-Fitting Prevention LSTM for Multivariate Time Series Forecasting [J]. IEEE Access, 2019, PP (99):1-1.
[9] Zhao Y, Ren X, Zhang X. Optimization of a Comprehensive Sequence Forecasting Framework Based on DAE-LSTM Algorithm [J]. Journal of Physics: Conference Series, 2021, 1746(1):012087 (12pp).
[10] Weijia Wu. Factor of compound factor quantitative stock selection scheme research [D]. Shanghai normal university, 2022. The DOI: 0.27312/d.cnki.gshsu.2022.000782.
[11] Mengmeng Yang, Xinghui Wang, Xing Zhao, Could enhance average method based on dynamic factor of stock price prediction [J]. Journal of Qilu University of Technology, 2022, 4 (5): 75-82. The DOI: 10.16442/ j.cnki. qlgydxxb. 2022.05.012.
[12] Chaobin Huang, Ximing Cheng. Research on stock price prediction based on LSTM neural network [J]. Journal of Information Science and Technology University of Beijing (Natural Science Edition), 2021, 36(1): 79-83.
[13] Yabo Zhao, Hua He. Stock Price Range Prediction Model Based on Information granulation and BP-Bagging [J]. Ploidy journal of Hebei university of technology, 2022 (05): 55 + 59-74. The DOI: 10.14081/j.cnki.hgdxb. 2022.05.005.
[14] Liu B, Tang X, Cheng J, et al. Traffic Flow Combination Forecasting Method Based on Improved LSTM and ARIMA[J]. 2019.

Downloads: 12156
Visits: 249054

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.