On the forecasting of high‐frequency financial time series based on ARIMA model improved by deep learning

Li, Zhenwei; Han, Jing; Song, Yisheng

doi:10.1002/for.2677

Cited by 58 publications

(33 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the performance of these models is excellent in the time series prediction task. Li et al [ 48 ] built a model combining ARIMA and LSTM to improve the prediction accuracy of high-frequency financial time series. Pan et al [ 49 ] applied the model based on the LSTM network to predict urban traffic flow and greatly improved the prediction effect via the spatial correlation.…”

Section: Related Workmentioning

confidence: 99%

A Novel Encoder-Decoder Model for Multivariate Time Series Forecasting

Zhang

Chen

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The time series is a kind of complex structure data, which contains some special characteristics such as high dimension, dynamic, and high noise. Moreover, multivariate time series (MTS) has become a crucial study in data mining. The MTS utilizes the historical data to forecast its variation trend and has turned into one of the hotspots. In the era of rapid information development and big data, accurate prediction of MTS has attracted much attention. In this paper, a novel deep learning architecture based on the encoder-decoder framework is proposed for MTS forecasting. In this architecture, firstly, the gated recurrent unit (GRU) is taken as the main unit structure of both the procedures in encoding and decoding to extract the useful successive feature information. Then, different from the existing models, the attention mechanism (AM) is introduced to exploit the importance of different historical data for reconstruction at the decoding stage. Meanwhile, feature reuse is realized by skip connections based on the residual network for alleviating the influence of previous features on data reconstruction. Finally, in order to enhance the performance and the discriminative ability of the new MTS, the convolutional structure and fully connected module are established. Furthermore, to better validate the effectiveness of MTS forecasting, extensive experiments are executed on two different types of MTS such as stock data and shared bicycle data, respectively. The experimental results adequately demonstrate the effectiveness and the feasibility of the proposed method.

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel Encoder-Decoder Model for Multivariate Time Series Forecasting

Zhang

Chen

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Intelligent automation such as deep learning methods is significant in tourism forecasting (Tussyadiah, 2020). For example, in time‐series forecasting, an ARIMA model result can be improved using the deep learning approach (Li et al, 2020). However, overfitting is the major challenge of neural networks and deep learning methods (Kraft et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

ANN–polynomial–Fourier series modeling and Monte Carlo forecasting of tourism data

Danbatta

Varol

2022

Journal of Forecasting

View full text Add to dashboard Cite

Modeling and forecasting of tourism data have received attention in the past decades. Turkey is one of the countries that benefit significantly from the tourism industry. Several time-series models have been recommended to best describe tourist arrivals to Turkey. However, in the 21st century, the world experiences great uncertainty in most possible event outcomes. These uncertainties are very difficult to account for. We proposed a hybrid artificial neural network (ANN)-polynomial-Fourier method to model the number of foreign visitors to Turkey from January 2004 to December 2020. The proposed model performance before and during the COVID-19 pandemic is evaluated separately. We evaluate the model performance by comparing with results from Danbatta and Varol (2021, https://doi.org/10.1142/S179396232141004X), Fourier series, and ARIMA models. To account for prediction uncertainties, we ran 300 Monte Carlo simulations within ±2σ from the model regression curve. According to the result outcomes, the proposed ANN-polynomial-Fourier has proven worthy to be considered a candidate model for the Turkish tourism data. The multistep ahead forecast suggests a 10.22% increase in the monthly foreign visitors' arrivals to Turkey in the year 2021.

show abstract

“…But there are also works focused the extraction of the information contained in the high-frequency component. These works are based on a variety of statistical methods and learning models; see, e.g., Brooks and Hinich (2006), Christensen et al (2012), Granger (1998), Li et al (2020), Luo and Tian (2020), and references therein.…”

Section: Introductionmentioning

confidence: 99%