EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting the Long-Term Dependencies in Time Series Using Recurrent Artificial Neural Networks

Cristian Ubal, Gustavo Di-Giorgi, Javier E. Contreras-Reyes, Rodrigo Salas

Machine Learning and Knowledge Extraction · 02.10.2023 · 5 (4) · 1340-1358

DOI: 10.3390/make5040068 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 02.10.2023. Verfasst von Cristian Ubal und 3 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: ANID-Millennium Science Initiative Program ICN2021_004, ANID FONDECYT, FONDECYT.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Long-term dependence is an essential feature for the predictability of time series. Estimating the parameter that describes long memory is essential to describing the behavior of time series models. However, most long memory estimation methods assume that this parameter has a constant value throughout the time series, and do not consider that the parameter may change over time. In this work, we propose an automated methodology that combines the estimation methodologies of the fractional differentiation parameter (and/or Hurst parameter) with its application to Recurrent Neural Networks (RNNs) in order for said networks to learn and predict long memory dependencies from information obtained in nonlinear time series. The proposal combines three methods that allow for better approximation in the prediction of the values of the parameters for each one of the windows obtained, using Recurrent Neural Networks as an adaptive method to learn and predict the dependencies of long memory in Time Series. For the RNNs, we have evaluated four different architectures: the Simple RNN, LSTM, the BiLSTM, and the GRU. These models are built from blocks with gates controlling the cell state and memory. We have evaluated the proposed approach using both synthetic and real-world data sets. We have simulated ARFIMA models for the synthetic data to generate several time series by varying the fractional differentiation parameter. We have evaluated the proposed approach using synthetic and real datasets using Whittle’s estimates of the Hurst parameter classically obtained in each window. We have simulated ARFIMA models in such a way that the synthetic data generate several time series by varying the fractional differentiation parameter. The real-world IPSA stock option index and Tree Ringtime series datasets were evaluated. All of the results show that the proposed approach can predict the Hurst exponent with good performance by selecting the optimal window size and overlap change.

Förderung

  • ANID-Millennium Science Initiative Program ICN2021_004
  • ANID FONDECYT
  • FONDECYT
  • Universidad de Valparaiso

Zitieren

APA

Ubal, C., Di-Giorgi, G., Contreras-Reyes, J. E., & Salas, R. (2023). Predicting the Long-Term Dependencies in Time Series Using Recurrent Artificial Neural Networks. Machine Learning and Knowledge Extraction, 5(4), 1340-1358. https://doi.org/10.3390/make5040068

Vancouver

Ubal C, Di-Giorgi G, Contreras-Reyes JE, Salas R. Predicting the Long-Term Dependencies in Time Series Using Recurrent Artificial Neural Networks. Machine Learning and Knowledge Extraction. 2023;5(4):1340-1358. doi:10.3390/make5040068

BibTeX
@article{Ubal2023,
  author = {Ubal, Cristian and Di-Giorgi, Gustavo and Contreras-Reyes, Javier E. and Salas, Rodrigo},
  title = {Predicting the Long-Term Dependencies in Time Series Using Recurrent Artificial Neural Networks},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2023},
  volume = {5},
  number = {4},
  pages = {1340--1358},
  doi = {10.3390/make5040068}
}
Kostenlos starten →