| 708 | 12 | 96 |
| Downloads | Citas | Reads |
The traditional stock index forecasting methods were conducted on the noisy, non-stationary and non-linear original stock index time series data, which would degrade the prediction accuracy. In order to deal with this issue, a novel stock index prediction method was proposed by incorporating the time-frequency features and the convolutional neural network. Firstly, the original time series data were decomposed into time-frequency features by employing the variational mode decomposition(VMD). The decomposed series data had a low signal-to-noise ratio and also stationarity with a clear trend. Then, by combining with temporal convolutional network(TCN), a fusion of time-frequency-based convolutional neural network model was proposed. Finally, compared with eight baseline methods on six real-world datasets, the experimental results showed that our method had higher prediction accuracy and better interpretability.
[1] ARIYO A A,ADEWUMI A O,AYO C K.Stock price prediction using the ARIMA model[C]//The 16th International Conference on Computer Modelling and Simulation.Piscataway:IEEE Press,2014:106-112.
[2] WICHAIDIT S,KITTITORNKUN S.Predicting SET50 stock prices using CARIMA (cross correlation ARIMA)[C]//International Computer Science and Engineering Conference.Piscataway:IEEE Press,2015:1-4.
[3] 魏宇.沪深300股指期货的波动率预测模型研究[J].管理科学学报，2010,13(2):66-76.WEI Y.Volatility forecasting models for CSI300 index futures[J].Journal of management sciences in China,2010,13(2):66-76.
[4] HASSAN M R,NATH B.Stock market forecasting using hidden Markov model:a new approach[C]//The 5th International Conference on Intelligent Systems Design and Applications.Piscataway:IEEE Press,2005:192-196.
[5] 朱永明.基于粗糙集理论的股市预测研究[J].郑州大学学报(理学版),2009,41(4):40-44.ZHU Y M.Study on prediction of stocking market based on rough set theory[J].Journal of Zhengzhou university (natural science edition),2009,41(4):40-44.
[6] MEESAD P,RASEL R I.Predicting stock market price using support vector regression[C]//2013 International Conference on Informatics,Electronics and Vision.Piscataway:IEEE Press,2013:1-6.
[7] HEATON J B,POLSON N G,WITTE J H.Deep learning in finance[EB/OL].(2018-01-04)[2021-05-03].https://arxiv.org/pdf/1602.06561.pdf.
[8] 姚宏亮，艾刘可，王浩，等.均线滞后的时序自回归股市态势预测算法[J].郑州大学学报(理学版),2018,50(3):60-66.YAO H L,AI L K,WANG H,et al.Time series autoregressive stock market forecasting algorithm based on moving average hysteresis[J].Journal of Zhengzhou university (natural science edition),2018,50(3):60-66.
[9] 李艳灵，杨志鹏，王莎莎，等.基于卷积神经网络进行电影院人群分布统计[J].信阳师范学院学报(自然科学版),2020,33(4):675-680.LI Y L,YANG Z P,WANG S S,et al.The distribution of cinema population based on convolutional neural network[J].Journal of Xinyang normal university (natural science edition),2020,33(4):675-680.
[10] 杨青，王晨蔚.基于深度学习LSTM神经网络的全球股票指数预测研究[J].统计研究，2019,36(3):65-77.YANG Q,WANG C W.A study on forecast of global stock indices based on deep LSTM neural network[J].Statistical research,2019,36(3):65-77.
[11] PRADEEPKUMAR D,RAVI V.Forecasting financial time series volatility using particle swarm optimization trained quantile regression neural network[J].Applied soft computing,2017,58:35-52.
[12] 熊志斌.ARIMA融合神经网络的人民币汇率预测模型研究[J].数量经济技术经济研究，2011,28(6):64-76.XIONG Z B.Research on RMB exchange rate forecasting model based on combining ARIMA with neural networks[J].The journal of quantitative & technical economics,2011,28(6):64-76.
[13] DU Y L.Application and analysis of forecasting stock price index based on combination of ARIMA model and BP neural network[C]//Chinese Control and Decision Conference.Piscataway:IEEE Press,2018:2854-2857.
[14] HSIEH T J,HSIAO H F,YEH W C.Forecasting stock markets using wavelet transforms and recurrent neural networks:an integrated system based on artificial bee colony algorithm[J].Applied soft computing,2011,11(2):2510-2525.
[15] CAO J,LI Z,LI J.Financial time series forecasting model based on CEEMDAN and LSTM[J].Physica A:statistical mechanics and its applications,2019,519:127-139.
[16] DRAGOMIRETSKIY K,ZOSSO D.Variational mode decomposition[J].IEEE transactions on signal processing,2014,62(3):531-544.
[17] RILLING G,FLANDRIN P,GONCALVES P.On empirical mode decomposition and its algorithms[C]//The 6th IEEE-EURASIP Workshop on Nonlinear Signal and Image ProcessingP Workshop on Nonlinear Signal and Image Processing.Piscataway:IEEE Press,2003:8-11.
[18] TORRES M E,COLOMINAS M A,SCHLOTTHAUER G,et al.A complete ensemble empirical mode decomposition with adaptive noise[C]//2011 IEEE International Conference on Acoustics,Speech and Signal Processing.Piscataway:IEEE Press,2011:4144-4147.
[19] CHUNG J,GULCEHRE C,CHO K,et al.Empirical evaluation of gated recurrent neural networks on sequence modeling[EB/OL].(2014-12-11)[2021-04-15].https://arxiv.org/pdf/1412.3555.pdf.
[20] OORD A V D,DIELEMAN S,ZEN H,et al.WaveNet:a generative model for raw audio[EB/OL].(2016-09-19)[2021-03-28].https://arxiv.org/pdf/1609.03499.pdf.
[21] LIN Z.Modelling and forecasting the stock market volatility of SSE composite index using GARCH models[J].Future generation computer systems,2018,79:960-972.
[22] ZHANG X,LI Y X,WANG S Z,et al.Enhancing stock market prediction with extended coupled hidden Markov model over multi-sourced data[J].Knowledge and information systems,2019,61(2):1071-1090.
[23] LAHMIRI S.Minute-ahead stock price forecasting based on singular spectrum analysis and support vector regression[J].Applied mathematics and computation,2018,320:444-451.
[24] WANG X,WANG Y J,WENG B,et al.Stock2Vec:a hybrid deep learning framework for stock market prediction with representation learning and temporal convolutional network[EB/OL].(2020-09-29)[2021-05-03].https://arxiv.org/pdf/2010.01197.pdf.
[25] WANG J,LUO Y Y,TANG L Y,et al.A new weighted CEEMDAN-based prediction model:an experimental investigation of decomposition and non-decomposition approaches[J].Knowledge-based systems,2018,160:188-199.
Basic Information:
DOI：10.13705/j.issn.1671-6841.2021225
China Classification Code:TP183;F830.9
Citation Information:
[1]JIANG Zhenyu,HUANG Yanyong,LI Tianrui ,et al.Fusion of Time-frequency-based Convolutional Neural Network in Financial Time Series Forecasting[J].Journal of Zhengzhou University(Natural Science Edition),2022,54(02):81-88.DOI:10.13705/j.issn.1671-6841.2021225.
Fund Information:
教育部人文社会科学青年基金项目(21YJCZH045); 中央高校基本科研业务专项资金项目(JBK2101001)
2021-05-31
2021
2021-12-24
2022-03-03
2022
1
2021-11-09
2021-11-09
2021-11-09