Improving Financial Time Series Prediction Accuracy Using Ensemble Empirical Mode Decomposition and Recurrent Neural Networks

Abstract Precise time series prediction serves as an important role in constructing a digital twin (DT). The various internal and external interferences result in highly nonlinear and stochastic time series. Although artificial neural networks (ANNs) are often used to forecast time series because of their strong self-learning and nonlinear fitting capabilities, it is a challenging and time-consuming task to obtain the optimal ANN architecture. This paper proposes a hybrid time series prediction model based on an ensemble empirical mode decomposition (EEMD), long short-term memory (LSTM) neural networks, and Bayesian optimization (BO). To improve the predictability of stochastic and nonstationary time series, the EEMD method is implemented to decompose the original time series into several components (each component is a single-frequency and stationary signal) and a residual signal. The decomposed signals are used to train the neural networks, in which the hyperparameters are fine-tuned by the BO algorithm. The following time series data are predicted by summating all the predictions of the decomposed signals based on the trained neural networks. To evaluate the performance of the proposed EEMD-BO-LSTM neural networks, this paper conducts two case studies (the wind speed prediction and the wave height prediction) and implements a comprehensive comparison between the proposed method and other approaches including the persistence model, autoregressive integrated moving average (ARIMA) model, LSTM neural networks, BO-LSTM neural networks, and EEMD-LSTM neural networks. The results show an improved prediction accuracy using the proposed method by multiple accuracy metrics.

Download Full-text

A Hybrid Wind Speed Prediction Approach Based on Ensemble Empirical Mode Decomposition and BO-LSTM Neural Networks for Digital Twin

ASME 2020 Power Conference ◽

10.1115/power2020-16500 ◽

2020 ◽

Author(s):

Weifei Hu ◽

Yihan He ◽

Zhenyu Liu ◽

Jianrong Tan ◽

Ming Yang ◽

...

Keyword(s):

Neural Networks ◽

Time Series ◽

Wind Speed ◽

Empirical Mode Decomposition ◽

Time Series Data ◽

Time Series Prediction ◽

Ensemble Empirical Mode Decomposition ◽

Series Data ◽

Digital Twin ◽

Mode Decomposition

Abstract Precise time series prediction serves as an important role in constructing a Digital Twin (DT). The various internal and external interferences result in highly non-linear and stochastic time series data sampled from real situations. Although artificial Neural Networks (ANNs) are often used to forecast time series for their strong self-learning and nonlinear fitting capabilities, it is a challenging and time-consuming task to obtain the optimal ANN architecture. This paper proposes a hybrid time series prediction model based on ensemble empirical mode decomposition (EEMD), long short-term memory (LSTM) neural networks, and Bayesian optimization (BO). To improve the predictability of stochastic and nonstationary time series, the EEMD method is implemented to decompose the original time series into several components, each of which is composed of single-frequency and stationary signal, and a residual signal. The decomposed signals are used to train the BO-LSTM neural networks, in which the hyper-parameters of the LSTM neural networks are fine-tuned by the BO algorithm. The following time series data are predicted by summating all the predictions of the decomposed signals based on the trained neural networks. To evaluate the performance of the proposed hybrid method (EEMD-BO-LSTM), this paper conducts a case study of wind speed time series prediction and has a comprehensive comparison between the proposed method and other approaches including the persistence model, ARIMA, LSTM neural networks, B0-LSTM neural networks, and EEMD-LSTM neural networks. Results show an improved prediction accuracy using the EEMD-BO-LSTM method by multiple accuracy metrics.

Download Full-text

High‐Frequency Trading and Financial Time‐Series Prediction with Spiking Neural Networks

Wilmott ◽

10.1002/wilm.10927 ◽

2021 ◽

Vol 2021 (113) ◽

pp. 18-33

Author(s):

Kang Gao ◽

Wayne Luk ◽

Stephen Weston

Keyword(s):

Neural Networks ◽

Time Series ◽

High Frequency ◽

Financial Time Series ◽

Time Series Prediction ◽

Spiking Neural Networks ◽

High Frequency Trading ◽

Financial Time

Download Full-text

Predicting Financial Prices of Stock Market using Recurrent Convolutional Neural Networks

International Journal of Intelligent Systems and Applications ◽

10.5815/ijisa.2020.06.02 ◽

2020 ◽

Vol 12 (6) ◽

pp. 21-32

Author(s):

Muhammad Zulqarnain ◽

◽

Rozaida Ghazali ◽

Muhammad Ghulam Ghouse ◽

Yana Mazwin Mohmad Hassim ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Time Series ◽

Financial Time Series ◽

Time Series Prediction ◽

Financial Time ◽

Data Mining Approach ◽

Learning Tasks ◽

Financial Prices ◽

Stock Indexes

Financial time-series prediction has been long and the most challenging issues in financial market analysis. The deep neural networks is one of the excellent data mining approach has received great attention by researchers in several areas of time-series prediction since last 10 years. “Convolutional neural network (CNN) and recurrent neural network (RNN) models have become the mainstream methods for financial predictions. In this paper, we proposed to combine architectures, which exploit the advantages of CNN and RNN simultaneously, for the prediction of trading signals. Our model is essentially presented to financial time series predicting signals through a CNN layer, and directly fed into a gated recurrent unit (GRU) layer to capture long-term signals dependencies. GRU model perform better in sequential learning tasks and solve the vanishing gradients and exploding issue in standard RNNs. We evaluate our model on three datasets for stock indexes of the Hang Seng Indexes (HSI), the Deutscher Aktienindex (DAX) and the S&P 500 Index range 2008 to 2016, and associate the GRU-CNN based approaches with the existing deep learning models. Experimental results present that the proposed GRU-CNN model obtained the best prediction accuracy 56.2% on HIS dataset, 56.1% on DAX dataset and 56.3% on S&P500 dataset respectively.

Download Full-text

Multiband Prediction Model for Financial Time Series with Multivariate Empirical Mode Decomposition

Discrete Dynamics in Nature and Society ◽

10.1155/2012/593018 ◽

2012 ◽

Vol 2012 ◽

pp. 1-21 ◽

Cited By ~ 7

Author(s):

Md. Rabiul Islam ◽

Md. Rashed-Al-Mahfuz ◽

Shamim Ahmad ◽

Md. Khademul Islam Molla

Keyword(s):

Time Series ◽

Empirical Mode Decomposition ◽

Time Series Data ◽

Financial Time Series ◽

Arma Model ◽

Series Data ◽

Discrete Wavelet ◽

Multivariate Empirical Mode Decomposition ◽

Financial Time ◽

Mode Decomposition

This paper presents a subband approach to financial time series prediction. Multivariate empirical mode decomposition (MEMD) is employed here for multiband representation of multichannel financial time series together. Autoregressive moving average (ARMA) model is used in prediction of individual subband of any time series data. Then all the predicted subband signals are summed up to obtain the overall prediction. The ARMA model works better for stationary signal. With multiband representation, each subband becomes a band-limited (narrow band) signal and hence better prediction is achieved. The performance of the proposed MEMD-ARMA model is compared with classical EMD, discrete wavelet transform (DWT), and with full band ARMA model in terms of signal-to-noise ratio (SNR) and mean square error (MSE) between the original and predicted time series. The simulation results show that the MEMD-ARMA-based method performs better than the other methods.

Download Full-text