EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Data-Centric Benchmarking of Neural Network Architectures for the Univariate Time Series Forecasting Task

Philipp Schlieper, Mischa Dombrowski, An Nguyen, Dario Zanca, Bjoern Eskofier

Forecasting · 26.08.2024 · 6 (3) · 718-747

DOI: 10.3390/forecast6030037 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Forecasting, online erschienen am 26.08.2024. Verfasst von Philipp Schlieper und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Time series forecasting has witnessed a rapid proliferation of novel neural network approaches in recent times. However, performances in terms of benchmarking results are generally not consistent, and it is complicated to determine in which cases one approach fits better than another. Therefore, we propose adopting a data-centric perspective for benchmarking neural network architectures on time series forecasting by generating ad hoc synthetic datasets. In particular, we combine sinusoidal functions to synthesize univariate time series data for multi-input-multi-output prediction tasks. We compare the most popular architectures for time series, namely long short-term memory (LSTM) networks, convolutional neural networks (CNNs), and transformers, and directly connect their performance with different controlled data characteristics, such as the sequence length, noise and frequency, and delay length. Our findings suggest that transformers are the best architecture for dealing with different delay lengths. In contrast, for different noise and frequency levels and different sequence lengths, LSTM is the best-performing architecture by a significant amount. Based on our insights, we derive recommendations which allow machine learning (ML) practitioners to decide which architecture to apply, given the dataset’s characteristics.

Zitieren

APA

Schlieper, P., Dombrowski, M., Nguyen, A., Zanca, D., & Eskofier, B. (2024). Data-Centric Benchmarking of Neural Network Architectures for the Univariate Time Series Forecasting Task. Forecasting, 6(3), 718-747. https://doi.org/10.3390/forecast6030037

Vancouver

Schlieper P, Dombrowski M, Nguyen A, Zanca D, Eskofier B. Data-Centric Benchmarking of Neural Network Architectures for the Univariate Time Series Forecasting Task. Forecasting. 2024;6(3):718-747. doi:10.3390/forecast6030037

BibTeX
@article{Schlieper2024,
  author = {Schlieper, Philipp and Dombrowski, Mischa and Nguyen, An and Zanca, Dario and Eskofier, Bjoern},
  title = {Data-Centric Benchmarking of Neural Network Architectures for the Univariate Time Series Forecasting Task},
  journal = {Forecasting},
  year = {2024},
  volume = {6},
  number = {3},
  pages = {718--747},
  doi = {10.3390/forecast6030037}
}
Kostenlos starten →