A hybrid stock price index forecasting model based on variational mode decomposition and LSTM network

Changes in the composite stock price index are a barometer of social and economic development. To improve the accuracy of stock price index prediction, this paper introduces a new hybrid model, VMD-LSTM, that combines variational mode decomposition (VMD) and a long short-term memory (LSTM) network. The proposed model is based on decomposition-and-ensemble framework. VMD is a data-processing technique through which the original complex series can be decomposed into a limited number of subseries with relatively simple modes of fluctuations. It can effectively overcome the shortcomings of mode mixing that sometimes exist in the empirical mode decomposition (EMD) method. LSTM is an improved version of recurrent neural networks (RNNs) that introduces a “gate” mechanism, and can effectively filter out the critical previous information, making it suitable for the financial time series forecasting. The capability of VMD-LSTM in stock price index forecasting is verified comprehensively by comparing with some single models and the EMD-based and other VMD-based hybrid models. Evaluated by level and directional prediction criteria, as well as a newly introduced statistic called the complexity-invariant distance (CID), the VMD-LSTM model shows an outstanding performance in stock price index forecasting. The hybrid models perform significantly better than the single models, and the forecasting accuracy of the VMD-based models is generally higher than that of the EMD-based models.

[1]  Shom Prasad Das,et al.  Novel hybrid SVM-TLBO forecasting model incorporating dimensionality reduction techniques , 2016, Applied Intelligence.

[2]  Bo Zhang,et al.  Volatility behavior of visibility graph EMD financial time series from Ising interacting system , 2015 .

[3]  Long Yu,et al.  Bidirectional LSTM Malicious webpages detection algorithm based on convolutional neural network and independent recurrent neural network , 2019, Applied Intelligence.

[4]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[5]  Yanfei Li,et al.  Smart multi-step deep learning model for wind speed forecasting based on variational mode decomposition, singular spectrum analysis, LSTM network and ELM , 2018 .

[6]  J. A. Chambers,et al.  Exploiting inherent relationships in RNN architectures , 1999, Neural Networks.

[7]  Pablo Moscato,et al.  Deep neural networks understand investors better , 2018, Decis. Support Syst..

[8]  Wang Jun,et al.  A weighted EMD-based prediction model based on TOPSIS and feed forward neural network for noised time series , 2017, Knowl. Based Syst..

[9]  Ligang Zhou,et al.  Posterior probability based ensemble strategy using optimizing decision directed acyclic graph for multi-class classification , 2017, Inf. Sci..

[10]  Dixiong Yang,et al.  Multi-step prediction of strong earthquake ground motions and seismic responses of SDOF systems based on EMD-ELM method , 2016 .

[11]  Hui Li,et al.  Class-imbalanced dynamic financial distress prediction based on Adaboost-SVM ensemble combined with SMOTE and time weighting , 2020, Inf. Fusion.

[12]  Ali Akbar Abdoos,et al.  A new intelligent method based on combination of VMD and ELM for short term wind power forecasting , 2016, Neurocomputing.

[13]  Kihwan Nam,et al.  Financial news-based stock movement prediction using causality analysis of influence in the Korean stock market , 2019, Decis. Support Syst..

[14]  Fei Xie,et al.  Automatic evaluation of facial nerve paralysis by dual-path LSTM with deep differentiated network , 2020, Neurocomputing.

[15]  Jian Cao,et al.  Financial time series forecasting model based on CEEMDAN and LSTM , 2019, Physica A: Statistical Mechanics and its Applications.

[16]  Chang Liu,et al.  Planetary Gears Feature Extraction and Fault Diagnosis Method Based on VMD and CNN , 2018, Sensors.

[17]  Zahra Karevan,et al.  Transductive LSTM for time-series prediction: An application to weather forecasting , 2020, Neural Networks.

[18]  Ram Bilas Pachori,et al.  Instantaneous voiced/non-voiced detection in speech signals based on variational mode decomposition , 2015, J. Frankl. Inst..

[19]  Xiaodan Liang,et al.  LSTM with Wavelet Transform Based Data Preprocessing for Stock Price Prediction , 2019, Mathematical Problems in Engineering.

[20]  Salim Lahmiri,et al.  Automated pathologies detection in retina digital images based on complex continuous wavelet transform phase angles. , 2014, Healthcare technology letters.

[21]  Lucas F. M. da Silva,et al.  Exploring the use of deep neural networks for sales forecasting in fashion retail , 2018, Decis. Support Syst..

[22]  Hermann Ney,et al.  From Feedforward to Recurrent LSTM Neural Networks for Language Modeling , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[23]  Jie Sun,et al.  Dynamic financial distress prediction with concept drift based on time weighting combined with Adaboost support vector machine ensemble , 2017, Knowl. Based Syst..

[24]  Guandong Xu,et al.  Deep learning for decision making and the optimization of socially responsible investments and portfolio , 2019, Decis. Support Syst..

[25]  Ma Yu,et al.  Analysis of Asia Pacific stock markets with a novel multiscale model , 2019 .

[26]  Lijun Yang,et al.  EMD- PNN based welding defects detection using laser-induced plasma electrical signals , 2019, Journal of Manufacturing Processes.

[27]  Salim Lahmiri,et al.  A variational mode decompoisition approach for analysis and forecasting of economic and financial time series , 2016, Expert Syst. Appl..

[28]  Weihua Gui,et al.  Non-ferrous metals price forecasting based on variational mode decomposition and LSTM network , 2020, Knowl. Based Syst..

[29]  Jongwoo Lee,et al.  A study on novel filtering and relationship between input-features and target-vectors in a deep learning model for stock price prediction , 2018, Applied Intelligence.

[30]  Peng He,et al.  Bearing Fault Diagnosis Method Based on EMD-CNNs , 2017 .

[31]  Jun Wang,et al.  Forecasting stochastic neural network based on financial empirical mode decomposition , 2017, Neural Networks.

[32]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[33]  Kunikazu Kobayashi,et al.  Time series forecasting using a deep belief network with restricted Boltzmann machines , 2014, Neurocomputing.

[34]  Safwan Mohd Nor,et al.  Interdependence and contagion among industry-level US credit markets: An application of wavelet and VMD based copula approaches , 2017 .

[35]  Lean Yu,et al.  A randomized-algorithm-based decomposition-ensemble learning methodology for energy price forecasting , 2018, Energy.

[36]  Guangyu Ding,et al.  Study on the prediction of stock price based on the associated network model of LSTM , 2019, International Journal of Machine Learning and Cybernetics.

[37]  Karl Aberer,et al.  Robust Online Time Series Prediction with Recurrent Neural Networks , 2016, 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[38]  Xiaoying Tian,et al.  A hybrid modelling method for time series forecasting based on a linear regression model and deep learning , 2019, Applied Intelligence.

[39]  R. K. Agrawal,et al.  A combination of artificial neural network and random walk models for financial time series forecasting , 2013, Neural Computing and Applications.

[40]  Mohd Tahir Ismail,et al.  Improving forecasting accuracy for stock market data using EMD-HW bagging , 2018, PloS one.

[41]  Eamonn J. Keogh,et al.  CID: an efficient complexity-invariant distance for time series , 2013, Data Mining and Knowledge Discovery.

[42]  Dominique Zosso,et al.  Variational Mode Decomposition , 2014, IEEE Transactions on Signal Processing.

[43]  Lei Ge,et al.  Exploring the attention mechanism in LSTM-based Hong Kong stock price movement prediction , 2019, Machine Learning and AI in Finance.

[44]  Salim Lahmiri,et al.  Intraday stock price forecasting based on variational mode decomposition , 2016, Journal of Computer Science.

[45]  Heng-Li Yang,et al.  An Integrated Model Combined ARIMA, EMD with SVR for Stock Indices Forecasting , 2016, Int. J. Artif. Intell. Tools.

[46]  Ha Young Kim,et al.  ModAugNet: A new forecasting framework for stock market index value with an overfitting prevention LSTM module and a prediction LSTM module , 2018, Expert Syst. Appl..

[47]  Kejun Wang,et al.  Photovoltaic power forecasting based LSTM-Convolutional Network , 2019 .

[48]  K. Lai,et al.  Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm , 2008 .

[49]  Jun Wang,et al.  Forecasting stock market indexes using principle component analysis and stochastic time effective neural networks , 2015, Neurocomputing.

[50]  Jun Wang,et al.  Financial time series prediction by a random data-time effective RBF neural network , 2014, Soft Comput..

[51]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[52]  Wei Xu,et al.  Enhancing intraday stock price manipulation detection by leveraging recurrent neural networks with ensemble learning , 2019, Neurocomputing.

[53]  Florentin Wörgötter,et al.  Evolving artificial neural networks with feedback , 2019, Neural Networks.

[54]  Zhengquan Xu,et al.  CTS-DP: Publishing correlated time-series data via differential privacy , 2017, Knowl. Based Syst..

[55]  Farid Mohammad Maalek Ghaini,et al.  Improving DWT-RNN model via B-spline wavelet multiresolution to forecast a high-frequency time series , 2019, Expert Syst. Appl..

[56]  Salim Lahmiri,et al.  Comparative study of ECG signal denoising by wavelet thresholding in empirical and variational mode decomposition domains. , 2014, Healthcare technology letters.

[57]  Ha Young Kim,et al.  Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models , 2018, Expert Syst. Appl..

[58]  Ha Young Kim,et al.  Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data , 2019, PloS one.

[59]  Mohamed Lazaar,et al.  Integration of Principal Component Analysis and Recurrent Neural Network to Forecast the Stock Price of Casablanca Stock Exchange , 2019, Procedia Computer Science.

[60]  Spyros Makridakis,et al.  Accuracy measures: theoretical and practical concerns☆ , 1993 .

[61]  Zhigang Zeng,et al.  Recurrent neural network for combined economic and emission dispatch , 2017, Applied Intelligence.

[62]  Bo Zhang,et al.  Constructing a PM2.5 concentration prediction model by combining auto-encoder with Bi-LSTM neural networks , 2020, Environ. Model. Softw..

[63]  Pradipta Kishore Dash,et al.  Hybrid Variational Mode Decomposition and evolutionary robust kernel extreme learning machine for stock price and movement prediction on daily basis , 2019, Appl. Soft Comput..

[64]  Stefan Feuerriegel,et al.  Decision support from financial disclosures with deep neural networks and transfer learning , 2017, Decis. Support Syst..